Only initialize KFD once by moving amdgpu_amdkfd_init from
amdgpu_pci_probe to amdgpu_init. This fixes kernel oopses and hangs
when booting multi-GPU systems.

Also removed some vestiges of KFD being its own module.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Existing debug dump are all invariant, new “low 32-bit of address”
dump is not invariant
Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
There are same purpose transition events.

[How]
remove the redundant event log.
Signed-off-by: Chiawen Huang <chiawen.huang@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
The extraneous call to amdgpu_pm_compute_clocks is deprecated.

[How]
Remove it.
Signed-off-by: David Francis <David.Francis@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
Virtual sink is used when set mode happens on a disconnected display
to allow the mode set to proceed. This did not work with MST because
the logic for acquiring stream encoder uses stream signal to determine
the special handling is required, and stream signal is virtual instead
of DP in this case.

[How]
Use link type to decide instead.
Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Steven Chiu <Steven.Chiu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
The i2c and aux engines are similar, and should be placed
next to eachother for readability

[How]
Reorder the elements of the resource_pool struct
Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
Our implementation is functionally identical to DRM's

Note that instead of checking if the provided id is 0, the helper
follows through with the mode object search. However, It will still
return NULL, since 0 is not a valid object id, and missed searches
will return NULL.

[How]
Remove our implementation, and replace it with
drm_atomic_helper_best_encoder.
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[why]
AMD Stoney reference board, there are only 2 pipes (not include
underlay), and 3 connectors. resource creation, only
2 I2C/AUX engines are created. Within dc_link_aux_transfer, when
pin_data_en =2, refer to enengines[ddc_pin->pin_data->en] = NULL.
NULL point is referred later causing system crash.

[how]
each asic design has fixed number of ddc engines at hw side.
for each ddc engine, create its i2x/aux engine at sw side.
Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
Enhance aux transition debugging information.

[How]
Added Aux request and reply event log.
Signed-off-by: Chiawen Huang <chiawen.huang@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Some display need disconnect delay. Adding this parameter for future use
Signed-off-by: Derek Lai <Derek.Lai@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Although 4 unique register values exist for gamma modes, two are
actually the same (the two RAMs) It’s not possible for caller to
understand this HW specific behavior, so some parsing is necessary
in driver
Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Wesley Chalmers <Wesley.Chalmers@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]Update Code to get DTN golden log check to pass for tests run after
DAL217 tests.
[How]Change how dcn10_log_hw_state function prints HW state info
(CM_GAMUT_REMAP_Cx_Cx registers) when GAMUT REMAP is in bypass mode.
Signed-off-by: Gary Kattan <gary.kattan@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
For supporting DP YCbCr 4:2:0 output.

[How]
Update mod_build_vsc_infopacket to support Pixel
Encoding/Colorimetry Format indication for VSC SDP rev5.
Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

[Why]
We currently lock modeset by setting a boolean in dm. We want to lock
Based on what DC tells us.

[How]
Build stream_updates and plane_update based on what changed. Then we
call check_update_surfaces_for_stream() to get the update type
We lock only if update_type is not fast
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Otherwise we won't be able to use the AGP aperture.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Start to use the old AGP aperture for system memory access.

v2: Move that to amdgpu_ttm_alloc_gart
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Helper to figure out the location of the AGP BAR.

v2: fix a couple of bugs
v3: correctly add one to vram_end
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Correct sign extend the GMC addresses to 48bit.

v2: sign extending turned out easier than thought.
v3: clean up the defines and move them into amdgpu_gmc.h as well
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Since we have a lot of FAQ on the VM state machine try to improve the
documentation by adding functions for each state move.

v2: fix typo in amdgpu_vm_bo_invalidated, use amdgpu_vm_bo_relocated in
    one more place as well.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Avoid unlocking a lock we never locked.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Allows us to avoid taking the spinlock in more places.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

amdgpu_vm_bo_* functions should come much later.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

For under voltage, negative value will be applied to voltage
offset. Update the data type to cover this case.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Added vega20 overdrive support based on existing OD sysfs
APIs. However, the OD logics are simplified on vega20. So,
the behavior will be a little different and works only on
some limited levels.

V2: fix typo
    fix commit description
    revise error logs
    add support for clock OD

V3: separate clock from voltage OD settings
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Vega20 does not appear to be affected by the same issue
as vega10.  Enable the full stolen memory handling on
vega20.  Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

vega12 does not appear to be affected by the same issue
as vega10.  Enable the full stolen memory handling on
vega12.  Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Raven does not appear to be affected by the same issue
as vega10.  Enable the full stolen memory handling on
Raven.  Reserve the appropriate size at init time to avoid
display artifacts and then free it at the end of init once
the new FB is up and running.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=106639Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

No functional change, just rework it in order to adjust the
behavior on a per asic level.  The problem is that on vega10,
something corrupts the lower 8 MB of vram on the second
resume from S3.  This does not seem to affect Raven, other
gmc9 based asics need testing.
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Add BOs to the idle state again and correctly clear the flag when
new BOs are added.
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

First step to fix the LRU corruption, we accidentially tried to move things
on the LRU after dropping the lock.
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Staring at the function for six hours, just to essentially move one line
of code. The problem was that the first list_cut_position call could result
in list2 pointing to la-la-land.
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This at least allows to fail any subsequent IOCTLs with -ENODEV
after the device is gone.
Still this operation is not supported yet in graphic mode
and will lead at least to page faults and other issues.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This reverts commit a7f91061.

Felix pointed out that we need to have the BOs mapped even before
amdgpu_vm_update_directories is called.
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Always try to put the GART away from where VRAM is.

v2: correctly handle the 4GB limitation
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

This caused a confusing error message, but there is functionally
no problem since the default method is DIRECT.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Move some KFD-related (but used in amdgpu_drv.c) definitions from
kfd_priv.h to kgd_kfd_interface.h so we don't need to include kfd_priv.h
in amdgpu_drv.c. This fixes a build failure when AMDGPU is enabled but
MMU_NOTIFIER is not.
This patch also disables KFD-related module options when HSA_AMD is not
enabled.

v2: rebase (Alex)
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>