Implement empty or -ENOSYS functions for vgpu if
CONFIG_TEGRA_GR_VIRTUALIZATION is not enabled, and remove ifdefs around
the calling code.
Change-Id: Idc75c9bc486d661786bc222bd9e0380aa7766e78
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/552898
Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
At this stage, ctxsw is always in reset state, because we're powering GPU
up, or we have reset the whole GR partition. Remove the code to invoke a
second reset.
Fix waiting for FE idle. We should wait after each bundle, and break if any
iteration fails.
Change-Id: I0846f67c6d860a485dea62ff870deafe55a47365
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/552799
When calculating fractional divider in GPCPLL NA mode quantize voltage
before (used to do it after) applying DFS_COEFF, to follow h/w order.
Bug 1555318
Change-Id: I37be2bc73cd1f849695b94acc4ff21caf26e8b97
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/552741
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
The return value of gk20a_busy must be checked since it may not succeed
in some cases. Add the __must_check attribute that generates a compiler
warning for code that does not read the return value and fix all uses of
the function to take error cases into account.
Bug 200040921
Change-Id: Ibc2b119985fa230324c88026fe94fc5f1894fe4f
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/542552
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
- Removed unnecessary static "initialized" variable (sw_ready flag is
protecting from multiple initializations, anyway).
- Used max frequency at min voltage to set initial configuration of
GPCPLL in both NA and non-NA mode. For backward compatibility made
sure initial PLL output rate do not exceed 1/3 of VCO minimum.
Bug 1555318
Change-Id: If970c27442ea1109d4503a322998a6a26159c345
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/552370
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Expose a debugfs entry pmu_security. It allows checking if PMU was
booted in secure or non-secure mode.
Change-Id: Iea584b696440779bee0900edccabd4e5b2997805
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/552456
Move nvgpu ioctls from the many user space interface headers to a new
single nvgpu.h header under include/uapi. No new code or replaced names
are introduced; this change only moves the definitions and changes
include directives accordingly.
Bug 1434573
Change-Id: I4d02415148e437a4e3edad221e08785fac377e91
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/542651
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
To help remove the nvhost dependency from nvgpu, rename ioctl defines
and structures used by nvgpu such that nvhost is replaced by nvgpu.
Duplicate some structures as needed.
Update header guards and such accordingly.
Change-Id: Ifc3a867713072bae70256502735583ab38381877
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/542620
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
In preparation for GM20B GPCPLL NA data integration:
- Added VCO control initialization code (no data, yet)
- Replaced absolute safe margin with relative percentage
(preliminary 8%)
- Retrieved maximum safe frequency at minimum voltage from GPU DVFS
table, instead of hard-coded macro (also fix the name of the limit:
maximum instead of minimum)
- Updated comments
Bug 1555318
Change-Id: I49a7a90cc4bc29e181065ebd2cf9d214edae6465
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/542462
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Proper error number for invalid request number is EINVAL instead of
EFAULT, so change it in ioctl calls.
Change-Id: I8fddd34e012700550e9e30fe17ba7152b3a0417b
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/542563
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Change CDE swizzling shader kernel size to 8x8 to avoid waste with
relatively small surfaces.
Map compbit backing store and destination surface as cacheable.
Clean up kernel size calculation.
Bug 1546619
Change-Id: Ie97c019b4137d2f2230da6ba3034387b1ab1468a
Signed-off-by: Jussi Rasanen <jrasanen@nvidia.com>
Reviewed-on: http://git-master/r/501158
Reviewed-by: Arto Merilainen <amerilainen@nvidia.com>
Tested-by: Arto Merilainen <amerilainen@nvidia.com>
Added configuration option to enable GM20b GPCPLL noise aware (NA)
mode. In this mode PLL output frequency is automatically adjusted when
GM20b voltage is fluctuating.
NA mode is disabled by default.
Bug 1555318
Change-Id: Ia9741fd02ddacaf4743e5397b729293fa5181f84
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/534079
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Added support for GM20b GPCPLL frequency change in NA mode outside of
bypass. In this case the respective PLL DVFS detection settings are
updated in flight. The implemented algorithm relies on characterization
providing two frequency limits at the same voltage: max frequency on
the F/V curve (Fmax@V) in NA mode with characterized DVFS coefficient,
and safe frequency under the curve when DVFS coefficient is zero
(Fsafe@V, which is effectively the same as Fmax@V in legacy/non-DVFS
mode).
Transition between two Fmax@V points on the curve includes:
- Lowering frequency to Fsafe@V for the minimum V of the transition
end-points
- Setting DVFS coefficient to zero
- Changing DVFS calibration point to the new voltage
- Setting DVFS coefficient characterized for the new voltage
- Setting final target frequency
Note that voltage is changed by Tegra SoC DVFS before (when voltage
increases), or after (whet voltage decreases) the above procedure.
This commit kept NA mode disabled.
Bug 1555318
Change-Id: Ib5620aaa113dc1caa69ecd402d9c6f68e39c472c
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/501042
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Added support for GM20b GPCPLL dynamic ramp in NA mode that requires
ramping of both integer NDIV and fractional SDM_DIN controls. If NA
mode is enabled, dynamic ramp is used only for transition to / from
disabled state. PLL frequency in NA mode is still changed under bypass
only.
This commit kept NA mode disabled.
Bug 1555318
Change-Id: I91f5722a485d1b66b6113aa9c35a2fe36c38ea80
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/500637
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Added basic support for GM20b GPCPLL noise-aware(NA) mode. In this
mode PLL internal DVFS mechanism is engaged, and output frequency is
scaled with voltage automatically. The scaling coefficients in this
commit are preliminary, pending characterization.
If NA mode is enabled, any frequency change is done under PLL bypass,
with no dynamic ramp allowed.
This commit kept NA mode disabled.
Bug 1555318
Change-Id: I8d96a10006155635797331bae522fb048d3dc4a0
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/499488
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Channel gpfifo cannot be submitted if the channel has no vm, so add a
check for it and bail out if no as is bound. Clean up other similar
checks too.
Change-Id: Ibb0fe08e44e34bbaaa00ebd02dce6cc4d93ca5d9
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/538887
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
nvhost_sync_create_fence returns ERR_PTRs instead of NULLs on error;
check for its errors with IS_ERR.
Change-Id: I9752e0d8fa703b2872918b23721ae973be58bf35
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/533794
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Arto Merilainen <amerilainen@nvidia.com>
Retrieve channel count from gm20b specific header instead of the
gk20a header. This increases channel count from 128 to 512.
Change-Id: I96d4887432852795f7f526e33f0d3d2458f3af0e
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/500623
Boards require a rework to make railgating and DVFS work realiably.
The information whether the board has been reworked or not will be
available on DTS.
This patch adds a DTS check to the GPU driver initialisation. If the
rework information is not available (or the rework has been marked as
disabled), railgating and DVFS are disabled.
Bug 1555485
Change-Id: Ie86fe35fb94377403472faffcbcaec645b6e40d9
Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-on: http://git-master/r/500218
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Invalid method needs to be cleared in gm20b to prevent getting same
interrupt again.
Change-Id: I4d83d1a27e5c711b5d82b95552be84d5f16a13e0
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/500286
Restrict reading of FE object table to the number of entries
available.
Change-Id: I11275ecd14e53f0b763d00d65042adb4b1e8ae6f
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/449306
Runlist event is not sent in gm20b for updated runlist. Polling is
the preferred way also for gk20a.
Bug 1555239
Change-Id: I60de084db69f848f63451f1f3078f183ca51ba50
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/500241
Add poll interface and control ioctls for waiting for GPU job completion
via semaphores.
Poll on a gk20a channel file waits for events from pending semaphore
interrupts (stalling) of that channel. New ioctls enable and disable the
events, and clear a single interrupt event so that next poll doesn't
wake up for it again.
Bug 1528781
Change-Id: I5c6238966b5d0900c8ab263c6a7f8f2611901f33
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/497750
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Expose supported nvgpu ioctls to userspace via bits in the flags field
of nvhost_gpu_characteristics; currently define two bits for special
memory allocation support.
Bug 1539747
Change-Id: I1bc9333b12825d07a00b7a4136ae9d35816a5855
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/495942
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
L2 bypass registers have moved in gm20b. Move the code to
ltc_common.c, which gets compiled once per chip version.
Change-Id: I0ab4dd03c78b8ad8abc7a7b18c094b6002827587
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/499220
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Use TSG specific API gk20a_fifo_recover_tsg() in following cases :
- IOCTL_CHANNEL_FORCE_RESET
to force reset a channel in TSG, reset all the channels
- handle pbdma intr
while resetting in case of pbdma intr, if channel is part of
TSG, recover entire TSG
- TSG preempt failure
when TSG preempt times out, use TSG recover API
Use preempt_tsg() API to preempt if channel is part of TSG
Add below two generic APIs which will take care of preempting/
recovering either of channel or TSG as required
gk20a_fifo_preempt()
gk20a_fifo_force_reset_ch()
Bug 1470692
Change-Id: I8d46e252af79136be85a9a2accf8b51bd924ca8c
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/497875
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
- add support to handle MMU faults on a channel in TSG
- first get the ID and type of channel that engine is running
- if TSG, abort each channel in it
- if regular channel, abort that channel
- also, add two versions of API set_ctx_mmu_error(), one for
regular channel and another for TSG
Bug 1470692
Change-Id: Ia7b01b81739598459702ed172180adb00e345eba
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/497874
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
- add and export API "gk20a_fifo_recover_tsg()" to
recover a TSG
- if TSG is running on any engine, then trigger MMU fault
on those engines
- otherwise, abort each channel in TSG
- modify channel specific API engines_on_ch() to generic
engines_on_id() which will take an ID and a flag to specify
whether ID is for channel or TSG and return engines running
on that ID
- modify channel specific API get_faulty_channel() to generic
get_faulty_id_type() which will take pointers to ID and type
of ID (either a regular channel or TSG)
- remove runlist update from recover_ch() since
no need to touch runlist during recovery
- set error notifier first and then only abort the channels
for TSG recovery path
- also, add necessary accessors to get engine
status type as TSG
Bug 1470692
Change-Id: I7137f611f80916b3d256d4b0dc6e5cf1e93eef6f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/497873
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Restored changing GM20B GPCPLL post-divider in flight with the
following limitation: post divider transition is glitch-less only if
there is common "1" in binary representation of old and new settings.
Transitions that may create glitch are implemented in glitch-less steps
with minimum possible interim divider value (for example, 1 <=> 2
transition has interim value 3: 1 <=> 3 <=> 2).
Steps allowed for glitch-less transitions may not always have frequency
jump at/below VCO min/2 (in the example above 1st step jumps 2/3 of
VCOmin). Enabled external linear divider at 1:2 during such steps.
Used extra write of the same data when changing GM20b linear divider.
Bug 1552225
Change-Id: Ie8fba2fbe44afd34ca68f5f355bd302b7426a632
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/496319
(cherry picked from commit bdd21e0003032fe664bd20f163dbab9942fd1d1d)
Reviewed-on: http://git-master/r/499193
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
- Skipped PLL re-locking if only post-divider is changing under bypass
- Added 1us delay after switch to bypass clock source
- Changed wait for lock under bypass resolution from 2us to 1us
Change-Id: I259581c00c417752263ef3b2ea057200bb78ecbf
Signed-off-by: Alex Frid <afrid@nvidia.com>
Reviewed-on: http://git-master/r/495473
(cherry picked from commit d90a19b8bf59c608a2a3a891b34ca714dfe990e9)
Reviewed-on: http://git-master/r/499192
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Yu-Huan Hsu <yhsu@nvidia.com>
Provide sysedp_dynamic_capping with the instantaneous GPU frequency
when notifying it of the GPU load. Modify the gpu/cpu priority
decision logic to choose CPU priority until GPU frequency gets "near"
the CPU-priority-limited-GPU-fmax. Introduce the priority_bias debugfs
parameter to facilitate tuning of "near". priority_bias takes a value
from 0 to 100.
Change-Id: Ia2cba36b8ea024fb8b01b5ba195dcf6550e38121
Signed-off-by: Matt Longnecker <mlongnecker@nvidia.com>
Reviewed-on: http://git-master/r/481720
GVS: Gerrit_Virtual_Submit
Reviewed-on: http://git-master/r/498912
Reviewed-by: Timo Alho <talho@nvidia.com>
