Age | Commit message (Collapse) | Author |
|
The cpu hotplug drivers should only bother updating state or switching
to the G cluster if the driver is not disabled
Bug 1032096
Change-Id: Ice938b094bbf48fef47afa3915b1a48362fb256d
Signed-off-by: Sai Charan Gurrappadi <sgurrappadi@nvidia.com>
Reviewed-on: http://git-master/r/122859
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
This is required as it is causing performance regression for SD, eMMC and USB
Bug 1006055
Bug 1021754
This reverts commit 2f5a59bbeee465fb33d012b8dc714fa0c1637209.
Change-Id: Ie54c28859ead976b5c554191d42eb22569370063
Signed-off-by: naveen kumar arepalli <naveenk@nvidia.com>
Reviewed-on: http://git-master/r/118575
Reviewed-by: Simone Willett <swillett@nvidia.com>
Tested-by: Simone Willett <swillett@nvidia.com>
|
|
Add profile [0, 0, 0] which effectively disables runnable threads
Bug 1003531
Change-Id: Ia45e533d5a6531b06c44c6d95f2f7cfd93cf976e
Signed-off-by: Xiao Bo Zhao <xiaoboz@nvidia.com>
Reviewed-on: http://git-master/r/118219
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
Added different bias levels to RT and added the option to
modify the bias level through sysfs knobs
Bug 1003531
Reviewed-on: http://git-master/r/114271
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Tested-by: Xiao Bo Zhao <xiaoboz@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
(cherry picked from commit 654bc674034f384d8826806fb443d4e9c67b9b3b)
Change-Id: I2e647a65fb89926dd9f0b2ac3edc3dca8eb659a1
Reviewed-on: http://git-master/r/118201
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Xiao Bo Zhao <xiaoboz@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
|
|
Tuned the sensitivity level of the hot-plug governor's balancing algorithm to 60% from 75%
Bug 958978
Change-Id: I972ed908995e348e8b3b0afb8108c44b66c80eae
Signed-off-by: Wen Yi <wyi@nvidia.com>
(cherry picked from commit 07a69db5af4c971b2c2d161ee149580ab5b40633)
Reviewed-on: http://git-master/r/111641
Reviewed-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Tested-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
Modified the hot-plug governor down_delay to be 500ms instead of 2s
Bug 958978
Change-Id: I55b5a4994f8e4564879cfd206fc683ff6f32d9ac
Signed-off-by: Wen Yi <wyi@nvidia.com>
(cherry picked from commit dd477396f2762f871255fb9d0800431d7534754d)
Reviewed-on: http://git-master/r/111640
Reviewed-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Tested-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
Tuned the runnable threads threshold from 5/9/13 to 5/9/10 in order to improve performance
Bug 958978
Change-Id: I77abcd0077845517f2b5f7487c547f8a5157c2c7
Signed-off-by: Wen Yi <wyi@nvidia.com>
(cherry picked from commit 25a97f57661353fbb5ee40faed296befbf635178)
Reviewed-on: http://git-master/r/111639
Reviewed-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Tested-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
Sample scheduler runnable threads average in auto-hotplug work
function and use it to determine the auto-hotplug target for number
of on-line cores. Use cpu up delay as sampling period, and enforce
down delay by checking last cpu configuration change time stamp.
Bug 958978
Change-Id: I4280a11d39914687e6ffaa6f38df594d10aedaa9
Signed-off-by: Alex Frid <afrid@nvidia.com>
(cherry picked from commit 507e2ef5e4f09b23de2e924003dba259d3c8bc3c)
Reviewed-on: http://git-master/r/111638
Reviewed-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Tested-by: Sai Gurrappadi <sgurrappadi@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
Bug 949219
Change-Id: I91a67d30869e9800c483f112d58b9f76e2dbe361
Signed-off-by: Sanjay Singh Rawat <srawat@nvidia.com>
Reviewed-on: http://git-master/r/103534
Reviewed-by: Simone Willett <swillett@nvidia.com>
Tested-by: Simone Willett <swillett@nvidia.com>
|
|
On Tegra3 switch and stay on G-CPU if minimum 1 is requested via
PM QoS interface. Allow return to LP-CPU only if request is at
default 0 level.
Change-Id: Ie1a732fe6c6a1dcd2f7e78be01e32dcc5a7993a6
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/102120
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Donghan Ryu <dryu@nvidia.com>
Reviewed-by: Satya Popuri <spopuri@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
On Tegra3, if PM QoS hotplug request is received when auto-hotplug
is disabled, do not enable auto-hotplug as side effect of the
request.
Change-Id: I8928d9ecd22e2d2df5fe60274fed30da0c565b47
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/102118
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Donghan Ryu <dryu@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
On Tegra3 secondary G-CPU may be turned off by auto-hotplug governor
in two cases: when overall CPU load is low enough to justify transition
to LP CPU, or when CPU cores usage by the scheduler is unbalanced
(skewed). In the former case down delay (currently 2sec) was inserted
before the core is turned Off. In the latter case the up delay (100ms)
was used, i.e., the same delay applied to balancing cores regardless
of the On/Off direction.
This commit would apply down delay when turning core Off in both cases
above, and keep using up delay only for turning core On.
Change-Id: Id545f8d48cbf380e24824a5adfe045ff68c1f39c
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/99708
Reviewed-by: Rohan Somvanshi <rsomvanshi@nvidia.com>
Tested-by: Rohan Somvanshi <rsomvanshi@nvidia.com>
|
|
On Tegra3 make sure cpu rate is within G-mode range before LP to G
mode switch triggered by minimum CPUs notifier.
Bug 964208
Change-Id: Ic4ee6bc7eca5ad0902da4907e4702f296a155280
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/99834
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
|
|
Cancel hotplug work when auto hotplug gets disabled to prevent
e.g. cpu_up() getting called in LP cluster.
Bug 965777
Change-Id: I058fe6a5e0c2fd3203ce9bc951d0973b60e033e0
Signed-off-by: Antti P Miettinen <amiettinen@nvidia.com>
Reviewed-on: http://git-master/r/95076
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Juha Tukkinen <jtukkinen@nvidia.com>
|
|
Switch to CPU G mode in Tegra3 suspend prepare if CPU suspend
rate is high enough. By symmetry, it guarantees that device
resume will be happening in G mode as well.
Bug 946301
Signed-off-by: Alex Frid <afrid@nvidia.com>
(cherry picked from commit 082be3604056c39442e1b42f5cfceeb089ffdaae)
Change-Id: I42e37ce8847e4916dd0fca9e4bd44096b65f7032
Reviewed-on: http://git-master/r/89352
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
|
|
Bug 945921
Reduce delays in going LP->G and G->Gn
(cherry picked from commit 51b7022f328d955cc4dbbf47b35403ea9c5e3a7b)
Signed-off-by: Diwakar Tundlam <dtundlam@nvidia.com>
Change-Id: I10f68196cb64ea20461000e9b0d64999fd714395
Reviewed-on: http://git-master/r/88169
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Tested-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
Updated Tegra3 auto-hotplug mechanism to keep minimum number of
on-line cpus above the limit specified by the PM QoS parameter
PM_QOS_MIN_ONLINE_CPUS.
Added respective debugfs node /kernel/debug/tegra_hotplug/min_cpus.
Bug 940061
Change-Id: Ic7d2e0fdb334661d46c9cd3ce0c73ae662ca3722
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/84707
Reviewed-by: Donghan Ryu <dryu@nvidia.com>
Tested-by: Gaurav Sarode <gsarode@nvidia.com>
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
|
|
Updated Tegra3 auto-hotplug state machine:
- no longer enter down state on LP CPU (there is no down path on LP)
- no longer enter idle state on G CPU (since load distribution between
G cores may change without CPU frequency change, continue polling)
- allow only disabled or idle state to be set via auto-hotplug sysfs
node, and synchronize with cpufreq governor in the latter case
Change-Id: Ibb93ddca852bbe1341fc5c52b0c83c16e9963e9d
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/71584
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Wen Yi <wyi@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Krishna Reddy <vdumpa@nvidia.com>
|
|
Updated Tegra3 auto-hotplug mechanism to keep maximum number of
online cpus within the limit specified by the PM QoS parameter
PM_QOS_MAX_ONLINE_CPUS.
Added respective debugfs node /kernel/debug/tegra_hotplug/max_cpus.
Bug 894200
Change-Id: I278cbfd91a1760b282eab186aa21883918b13800
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/71035
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Antti Miettinen <amiettinen@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
|
|
Update Tegra3 CPU clock rate after G=>LP mode switch is completed to
synchronize with cpufreq target rate.
(cherry picked from commit 870d21e5e23eff476cdd841b4ce2605393d638ef)
(cherry picked from commit 11b20d7d6206c557f00e3f7a40dec1d498345d79)
Change-Id: I62237b8d34be23a8d903937f2ebb2d395c5db1b9
Reviewed-on: http://git-master/r/63359
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Rebase-Id: Rdd1548389896521fddb2e239d6236706eb102f73
|
|
- Account for EDP affect on total available MIPS when bringing on-line
(removing off-line) new cpu core. Add multi-core overhead (in percent)
as a parameter - set by default to 10%.
- Add balance level parameter: level value (in percent) defines minimum
speed ratio used by hotplug algorithm to determine if current CPU cores
are balanced, so that another core may be brought on-line. By default
set to 75%
Added tunables:
/sys/module/cpu_tegra3/parameters/mp_overhead
/sys/module/cpu_tegra3/parameters/balance_level
Bug 865176
Bug 867186
Original-Change-Id: I6f2e175e0b5ed14c4b85794949c1e65d0e7f4a36
Reviewed-on: http://git-master/r/49772
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Reviewed-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Tested-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Rebase-Id: Rcfefb570c30bf78f6eae155c3f3f7547ac64f128
|
|
Renamed and moved tegra cpu related function prototypes from power.h
to tegra-cpu.h. No functional changes.
Original-Change-Id: I24c25c9434bf7008e0875d1f74be502cd902c4ba
Reviewed-on: http://git-master/r/40532
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Rebase-Id: R3d90799453a86a5a9ed012d2bfe373715de6d5c3
|
|
In K39 , 'freezeable' is changed to 'freezable'.
Reference Commit Id 58a69cb47ec6991bf006a3e5d202e8571b0327a4.
Change-Id: Ie3f95db453205c05da4cf4e655ba8b12a126255b
Reviewed-on: http://git-master/r/47487
Tested-by: Gaurav Sarode <gsarode@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Reviewed-by: Daniel Willemsen <dwillemsen@nvidia.com>
Rebase-Id: R530643b91e8c252eb606ce7e789cfe34101f6edd
|
|
Original-Change-Id: I7f4fb6447c882a54d95ee3fb4c6149f4e0357d69
Reviewed-on: http://git-master/r/31457
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@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>
Tested-by: Diwakar Tundlam <dtundlam@nvidia.com>
Tested-by: Gerrit_Virtual_Submit
Rebase-Id: Rbe2ac5f11065109d34a04793f93c873441e261be
|
|
Made sure Tegra3 LP CPU mode maximum rate, and G CPU mode minimum rate
are clipped to the entries in cpufreq scaling table.
Original-Change-Id: I4c82b65be3a8680edbb501041a7158d1a7fbbd07
Reviewed-on: http://git-master/r/29703
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Rebase-Id: R99b548e992c80e4850e6d7f9443db8f7d7134956
|
|
When current CPU complex frequency is above target range:
- bring new core on-line only if cpufreq governor requests for
all already on-lined CPUs are above 50% of current CPU frequency
- off-line one core (despite high pick request) if cpufreq
governor requests for at least 2 on-lined CPUs are below 25% of
current CPU frequency
- do nothing if neither of the above conditions is true
Original-Change-Id: I77e1bd543a8fadd51974f7d574f256a6e7e2979a
Reviewed-on: http://git-master/r/29702
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Tested-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Rebase-Id: Rc5c717454d1e09ca97ccc79fff60cb33fcf854e9
|
|
- taking CPU core off-line: selected CPU with minimum load
- switching from ULP to G CPU mode: set CPU clock to cpufreq
target rate after the mode switch is completed
Original-Change-Id: I9bf4d0f4b48c262cf678c603aac02043dd602674
Reviewed-on: http://git-master/r/28420
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Original-Change-Id: I5a19be79dd8f8fe788637870a22cd34dcfea150e
Rebase-Id: Re264ec676c5c2103f7738c9eab5f4e11a4344975
|
|
Use cpufreq (cpu DFS) mutex for auto-hotplug (instead of a separate
one) to serialize cpu frequency scaling, hotplug, and CPU mode switch
operations.
Original-Change-Id: I7ea865894d1676c865294ab31a903248d9437534
Reviewed-on: http://git-master/r/24893
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Original-Change-Id: I906a23561c1567079a41590a30b29b3d52fa5de8
Rebase-Id: R5d16154c91b41fd02f2a50af7ec6868a7958dc13
|
|
Added second level virtualization (on top of virtual cpu rate control)
to support different Tegra3 CPU power modes: low power (LP) mode and
geared performance (G) mode. Virtual cpu complex (cpu_cmplx) clock is
defined as a child with two parents: virtual cpu_lp and virtual cpu_g
clocks for the respective modes. Mode switch sequence was integrated
into cpu_cmplx set parent implementation. (Before this commit mode
switch was triggered outside the clock framework, which created cpu
clock/mode synchronization problems).
Each mode clock is derived from its own super clock mux (cclk_lp and
cclk_g) to statically match Tegra3 h/w layout. (Before this commit the
code had to dynamically synchronize CPU mode and active mux selection).
This change also allowed to support PLLX output divider for low power
mode as fixed 1:2 divider with bypass control embedded into cclk_lp
parent section.
Updated auto and sysfs CPU mode switch calls to use new clock framework,
and removed clock manipulation from the low level mode switch
implementation.
Original-Change-Id: Ibc3cc495b2ff29e2d3417eff2bfd45535cbd015b
Reviewed-on: http://git-master/r/24734
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Jin Qian <jqian@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Original-Change-Id: I23ae80edbf14fb22727a6fc317cd9e5baf8bd6be
Rebase-Id: Rdcd4a2165ebd92bf4caa35d68ca81d19a3789351
|
|
Original-Change-Id: I30e6b308e6c04e4dcb914057284a949ad255d32f
Reviewed-on: http://git-master/r/22708
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Kaz Fukuoka <kfukuoka@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Original-Change-Id: I2d221d49aa98d407a18c9d2eb0f5658f56920cbc
Rebase-Id: R84fbe564a1624e2261b4b0623a5fa9d810c1d956
|
|
Do not update auto-hotplug statistic when auto-hotplug is disabled;
initialize and restart updating after it is enabled.
Original-Change-Id: I3a202ab3f0d3d194207e1e881248edac1f820802
Reviewed-on: http://git-master/r/20229
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Diwakar Tundlam <dtundlam@nvidia.com>
Tested-by: Diwakar Tundlam <dtundlam@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Original-Change-Id: Iabc61ecd866b421d7cd819d420051ada83c97b87
Rebase-Id: Rc8e222d920642c2c61587290c8542c69538354a8
|
|
Do not switch to G cluster if cpufreq spikes above LP frequency limit
for a short time - currently set threshold to 100ms. Fixed timing
update for LP cluster statistic.
Original-Change-Id: Id4f00fd5c39d7fe2aa931da30cf607a5144dc3ab
Reviewed-on: http://git-master/r/19381
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Original-Change-Id: Ief6d391a5806d6cba20b6b5b407acb9846725260
Rebase-Id: Ref560d34203900e32b63d5b6104cb0fb105e4c63
|
|
Forbid cluster switch to G cluster if the G cluster doesn't exist.
Bug 791057
Original-Change-Id: I215de2581edf5fb3c1feaa00d1c6e0b52b15dc23
Reviewed-on: http://git-master/r/19302
Tested-by: Scott Williams <scwilliams@nvidia.com>
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Original-Change-Id: Id0a7e5ad62df4d1638518fe00715aac60e4efea9
Rebase-Id: Re39a0fedb7bb0e2518cfd56d46c6565d4a6c2ef4
|
|
Add auto-hotplug statistic to track number of transitions and on-line
time for each CPU/cluster.
Original-Change-Id: Iefaf4f69068401eb7a9d4abbf725df4e21d35db9
Reviewed-on: http://git-master/r/19168
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Narendra Damahe <ndamahe@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Original-Change-Id: I62209733054dddbc18741b7fca0c481c90f3aba7
Rebase-Id: R3ef66d1e09da307a7aac93082692d8ee27075299
|
|
Initial implementation of Tegra3 quad core CPU management. Add closed
control loop on top of cpufreq DFS. Target frequency range is bounded
by Fmax(Vnominal) for low power cluster - currently set to 456MHz, and
Fmax(Vminimum) for high power cluster - currently set to 356MHz.
When CPU frequency is scaled below the target range, slave high power
CPUs are gradually brought down and eventually CPU is switched to the
low power cluster.
When CPU frequency is scaled above the target range, CPU is switched
to the high power cluster and slave high power CPUs are gradually
brought up.
The auto hotplug support is disabled on boot. It can be explicitly
enabled via sysfs interface.
Original-Change-Id: Ie0e5cf1f334d9c53932db05950cfcf5addd271d7
Reviewed-on: http://git-master/r/18500
Reviewed-by: Aleksandr Frid <afrid@nvidia.com>
Tested-by: Aleksandr Frid <afrid@nvidia.com>
Reviewed-by: Jonathan Mayo <jmayo@nvidia.com>
Reviewed-by: Scott Williams <scwilliams@nvidia.com>
Original-Change-Id: I86152069aa2bed73e0148a4bcab897811e1a5827
Rebase-Id: R9cf5f5f8868c659db526cb49ddf276a79d93ef1a
|