Commit Graph

11865 Commits

Author SHA1 Message Date
Evan Quan
6dee4829cf drm/amd/powerplay: correct UVD/VCE/VCN power status retrieval
VCN should be used for Vega20 later ASICs while UVD and VCE
are for previous ASICs.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 02:02:22 -05:00
Evan Quan
a3ebbdb95f drm/amd/powerplay: correct Navi10 VCN powergate control (v2)
No VCN DPM bit check as that's different from VCN PG. Also
no extra check for possible double enablement/disablement
as that's already done by VCN.

v2: check return value of smu_feature_set_enabled

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 02:02:22 -05:00
Evan Quan
e21e3581e2 drm/amd/powerplay: support VCN powergate status retrieval for SW SMU
Commonly used for VCN powergate status retrieval for SW SMU.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 02:02:22 -05:00
Evan Quan
201cd702b7 drm/amd/powerplay: support VCN powergate status retrieval on Raven
Enable VCN powergate status report on Raven.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 02:02:22 -05:00
Evan Quan
a02709818f drm/amd/powerplay: add new sensor type for VCN powergate status
VCN is widely used in new ASICs and different from tranditional
UVD and VCE.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 02:02:22 -05:00
Wang Xiayang
929e571c04 drm/amdgpu: fix a potential information leaking bug
Coccinelle reports a path that the array "data" is never initialized.
The path skips the checks in the conditional branches when either
of callback functions, read_wave_vgprs and read_wave_sgprs, is not
registered. Later, the uninitialized "data" array is read
in the while-loop below and passed to put_user().

Fix the path by allocating the array with kcalloc().

The patch is simplier than adding a fall-back branch that explicitly
calls memset(data, 0, ...). Also it does not need the multiplication
1024*sizeof(*data) as the size parameter for memset() though there is
no risk of integer overflow.

Signed-off-by: Wang Xiayang <xywang.sjtu@sjtu.edu.cn>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 01:26:09 -05:00
Christian König
67d0859e27 drm/amdgpu: fix error handling in amdgpu_cs_process_fence_dep
We always need to drop the ctx reference and should check
for errors first and then dereference the fence pointer.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 01:26:09 -05:00
Evan Quan
f0bc1ee473 drm/amd/powerplay: enable SW SMU reset functionality
Move SMU irq handler register to sw_init as that's totally
software related. Otherwise, it will prevent SMU reset working.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 00:07:16 -05:00
Evan Quan
479156f2e5 drm/amd/powerplay: fix null pointer dereference around dpm state relates
DPM state relates are not supported on the new SW SMU ASICs. But still
it's not OK to trigger null pointer dereference on accessing them.

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>
2019-07-31 00:06:58 -05:00
Alex Deucher
090efd946d drm/amdgpu/powerplay: use proper revision id for navi
The PCI revision id determines the sku.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 00:05:37 -05:00
Kevin Wang
45a660143b drm/amd/powerplay: fix temperature granularity error in smu11
in this patch,
drm/amd/powerplay: add callback function of get_thermal_temperature_range
the driver missed temperature granularity change on other temperature.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 00:01:05 -05:00
Kevin Wang
2c0f07fe3c drm/amd/powerplay: add callback function of get_thermal_temperature_range
1. the thermal temperature is asic related data, move the code logic to
xxx_ppt.c.
2. replace data structure PP_TemperatureRange with
smu_temperature_range.
3. change temperature uint from temp*1000 to temp (temperature uint).

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-31 00:00:49 -05:00
Kent Russell
d65848657c drm/amdkfd: Fix byte align on VegaM
This was missed during the addition of VegaM support

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:59:00 -05:00
Evan Quan
59de58f84f drm/amd/powerplay: determine the features to enable by pptable only
Per current logics, the features to enable are determined together
by driver and pptable. This is not efficient in co-debug with
firmware team.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:35 -05:00
Hawking Zhang
861324983d drm/amdgpu: correct irq type used for sdma ecc
we should pass irq type, instead of irq client id,
to irq_get/put interface

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:35 -05:00
Evan Quan
b4af964e75 drm/amd/powerplay: make power limit retrieval as asic specific
The power limit retrieval should be done per asic. Since we may
need to lookup in the pptable and that's really asic specific.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:35 -05:00
Evan Quan
1f23cadbe0 drm/amd/powerplay: correct arcturus current clock level calculation
There may be 1Mhz delta between target and actual frequency. That
should be taken into consideration for current level check.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:35 -05:00
Evan Quan
60d435b73d drm/amd/powerplay: support UMD PSTATE settings on arcturus
Enable arcturus UMD PSTATE support.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:35 -05:00
Evan Quan
4bf76e60b9 drm/amd/powerplay: fix arcturus real-time clock frequency retrieval
Make sure we can still get the accurate gfxclk/uclk/socclk frequency
even on dpm disabled.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Kevin Wang
790ef68afc drm/amd/powerplay: remove redundancy debug log in smu
remove redundacy debug log in smu.
eg:
[ 6897.969447] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6897.969448] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6897.969448] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6899.024114] amdgpu: [powerplay] Unsupported SMU message: 38
[ 6899.024151] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6899.024151] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6899.024152] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6900.078296] amdgpu: [powerplay] Unsupported SMU message: 38
[ 6900.078332] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6900.078332] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6900.078333] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6901.133230] amdgpu: [powerplay] Unsupported SMU message: 38

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
8a856ced35 drm/amd/powerplay: correct the bitmask used in arcturus
Those bitmask prefixed by "SMU_" should be used.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
55bf7e6243 drm/amd/powerplay: add missing arcturus feature maps
Add missing feature maps for arcturus.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
d427cf8f7f drm/amd/powerplay: support fan speed retrieval on arcturus
Support arcturus fan speed retrieval.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
631807f091 drm/amd/powerplay: support real-time clock retrieval on arcturus
Enable arcturus real-time clock retrieval.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
ba74c8bf88 drm/amd/powerplay: support sensor reading on arcturus
Support sensor reading for gpu loading, power and
temperatures.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
832a7062a0 drm/amd/powerplay: init arcturus SMU metrics table on bootup
Initialize arcturus SMU metrics table.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
1f96ecef6f drm/amd/powerplay: correct UVD/VCE/VCN power status retrieval
VCN should be used for Vega20 later ASICs while UVD and VCE
are for previous ASICs.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
5fa790f6c9 drm/amd/powerplay: correct Navi10 VCN powergate control (v2)
No VCN DPM bit check as that's different from VCN PG. Also
no extra check for possible double enablement/disablement
as that's already done by VCN.

v2: check return value of smu_feature_set_enabled

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
bf2bf52383 drm/amd/powerplay: support VCN powergate status retrieval for SW SMU
Commonly used for VCN powergate status retrieval for SW SMU.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
ab9e314886 drm/amd/powerplay: support VCN powergate status retrieval on Raven
Enable VCN powergate status report on Raven.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
9829e3d89b drm/amd/powerplay: add new sensor type for VCN powergate status
VCN is widely used in new ASICs and different from tranditional
UVD and VCE.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Le Ma
7d0e6329df drm/amdgpu: update more sdma instances irq support
Update for sdma ras ecc_irq and other minors.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Le Ma
9d4d7236ef drm/amd/include: adjust base offset of SMUIO and THM for Arcturus
Arcturus has different _BASE_IDX value in some HWIP_offset.h. To make source
files like smu_v11_0.c and soc15.c that include HWIP_offset.h of Vega20
reusable for Arcturus, align this base offset with Vega20.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
3ff101b8ab drm/amd/powerplay: hold on the arcturus gfx dpm support in driver
As for now, only "Prefetcher" is guarded to be working from
SMU firmware.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
7c16d24abe drm/amdgpu: correct VCN powergate routine for acturus
Arcturus VCN should powergate in the way as Navi.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:34 -05:00
Evan Quan
fe089e1dd7 drm/amd/powerplay: enable arcturus powerplay
Arcturus powerplay is ready to use.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
cca4fafc09 drm/amd/powerplay: initialize arcturus MP1 and THM base address
Initialize base address for those IPs which are used in powerplay.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
22e1831734 drm/amd/powerplay: enable SW SMU routine support for arcturus
Enable arcturus SW SMU routines.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
a94235af11 drm/amd/powerplay: update arcturus_ppt.c/h V3
Arcturus ASIC specific powerplay interfaces.

V2: correct SMU msg naming
    drop unnecessary debugs

V3: rebase (Alex)

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
c8893d5ce7 drm/amd/powerplay: update arcturus_ppsmc.h
Correct header and fix typo.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
22808306f2 drm/amd/powerplay: update smu11_driver_if_arcturus.h
It guides how driver should interface with SMU in arcturus.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
7c8bcaf408 drm/amd/powerplay: add SW SMU interface for dumping pptable out (v2)
This is especially useful in early bring up phase.

v2: disabled by default (Alex)

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Evan Quan
4c35e77865 drm/amd/powerplay: add smcdpminfo table v4_6 support
New smcdpminfo table used in arcturus.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Jay Cornwall
1faa3b8054 drm/amdkfd: Save/restore vcc on gfx10
VCC moved out of user SGPR allocation in gfx10. It's now stored
in SGPRs 106-107.

Also fixes incorrect SGPR read offsets.

Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: shaoyunl <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Jay Cornwall
f9e346aba1 drm/amdkfd: Save/restore flat_scratch_lo/hi on gfx10
These moved from SGPRs in gfx9 to HWREG in gfx10.

Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: shaoyunl <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Jay Cornwall
7ce55e0b6f drm/amdkfd: Fix gfx10 wave64 VGPR context restore
Copy/paste error, first 4 VGPRs are separated by 64 dwords (256 bytes).

Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: shaoyunl <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Nicholas Kazlauskas
f16d523f9d drm/amd/display: Support uclk switching for DCN2
[Why]
We were previously forcing the uclk for every state to max and reducing
the switch time to prevent uclk switching from occuring. This workaround
was previously needed in order to avoid hangs + underflow under certain
display configurations.

Now that DC has the proper fix complete we can drop the hacks and
improve power for most display configurations.

[How]
We still need the function pointers hooked up to grab the real uclk
states from pplib. The rest of the prior hack can be reverted.

The key requirements here are really just DC support, updated firmware,
and support for disabling p-state support when needed in pplib/smu.

When these requirements are met uclk switching works without underflow
or hangs.

Fixes: 02316e963a ("drm/amd/display: Force uclk to max for every state")

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Nicholas Kazlauskas
fb6959ae50 drm/amd/display: Embed DCN2 SOC bounding box
[Why]
In order to support uclk switching on NV10 the SOC bounding box
needs to be updated.

[How]
We currently read the constants from the gpu info FW, but supporting
workarounds in DC for different versions of the FW adds additional
complexity to the codebase.

NV10 has been released so it's cleanest to keep the bounding box and
source code in sync by embedding the bounding box like we do for
other ASICs.

Fixes: 02316e963a ("drm/amd/display: Force uclk to max for every state")

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Wang Xiayang
1a2c29bce0 drm/amdgpu: fix a potential information leaking bug
Coccinelle reports a path that the array "data" is never initialized.
The path skips the checks in the conditional branches when either
of callback functions, read_wave_vgprs and read_wave_sgprs, is not
registered. Later, the uninitialized "data" array is read
in the while-loop below and passed to put_user().

Fix the path by allocating the array with kcalloc().

The patch is simplier than adding a fall-back branch that explicitly
calls memset(data, 0, ...). Also it does not need the multiplication
1024*sizeof(*data) as the size parameter for memset() though there is
no risk of integer overflow.

Signed-off-by: Wang Xiayang <xywang.sjtu@sjtu.edu.cn>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Christian König
6494120695 drm/amdgpu: fix error handling in amdgpu_cs_process_fence_dep
We always need to drop the ctx reference and should check
for errors first and then dereference the fence pointer.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Kenneth Feng
6e92e156aa drm/amdgpu/powerplay: provide the interface to disable uclk switch for DAL
provide the interface for DAL to disable uclk switch on navi10.
in this case, the uclk will be fixed to maximum.
this is a workaround when display configuration causes underflow issue.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Thong Thai
c74dbe44ea drm/amd/amdgpu/vcn_v2_0: Move VCN 2.0 specific dec ring test to vcn_v2_0
VCN 2.0 firmware now requires a packet start command to be sent before
any other decode ring buffer command.

Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:33 -05:00
Alex Deucher
3207dcf3af drm/amdgpu/gfx10: update golden settings for navi14
Updated settings for hw team.

Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Kevin Wang
98eb03bbf0 drm/amd/powerplay: implment sysfs feature status function in smu
1. Unified feature enable status format in sysfs
2. Rename ppfeature to pp_features to adapt other pp sysfs node name
3. this function support all asic, not asic related function.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Acked-by: Rui Huang <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Kevin Wang
26dd668155 drm/amd/powerplay: move smu_feature_update_enable_state to up level
this function is not ip or asic related function,
so move it to top level as public api in smu.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Kevin Wang
cb33363d0e drm/amd/powerplay: add smu feature name support
add smu_get_feature_name support in smu.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Kevin Wang
6b294793e3 drm/amd/powerplay: add smu message name support
add smu_get_message_name support in smu.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Kevin Wang
0ba5eda81a drm/amd/powerplay: move smu types to smu_types.h
move some enum type (message, feature, clock) to smu_types.h.
these types is too long in amdgpu_smu.h, and not clearly.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Joseph Greathouse
2c89731803 drm/amdgpu: Default disable GDS for compute+gfx
Units in the GDS block default to allowing all VMIDs access to all
entries. Disable shader access to the GDS, GWS, and OA blocks from all
compute and gfx VMIDs by default. For compute, HWS firmware will set
up the access bits for the appropriate VMID when a compute queue
requires access to these blocks.
The driver will handle enabling access on-demand for graphics VMIDs.

Leaving VMID0 with full access because otherwise HWS cannot save or
restore values during task switch.

v2: Fixed code and comment styling.

Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Thong Thai
333fe325fe drm/amd/amdgpu/vcn_v2_0: Mark RB commands as KMD commands
Sets the CMD_SOURCE bit for VCN 2.0 Decoder Ring Buffer commands. This
bit was previously set by the RBC HW on older firmware. Newer firmware
uses a SW RBC and this bit has to be set by the driver.

Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Alex Deucher
d3b9f39d84 drm/amdgpu/display: fix the build without CONFIG_DRM_AMD_DC_DSC_SUPPORT
Some code was missing the CONFIG_DRM_AMD_DC_DSC_SUPPORT guard.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Andrey Grodzovsky
f2bd8a0ed7 drm/amdgpu: Fix amdgpu_display_supported_domains logic.
Add restriction to dissallow GTT domain if the relevant BO
doesn't have USWC flag set to avoid the APU hang scenario.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Alex Deucher
354e6e14ef drm/amdgpu/powerplay: use proper revision id for navi
The PCI revision id determines the sku.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:48:32 -05:00
Alex Deucher
a3a09142f4 drm/amdgpu: put the SMC into the proper state on reset/unload
When doing a GPU reset or unloading the driver, we need to
put the SMU into the apprpriate state for the re-init after
the reset or unload to reliably work.

I don't think this is necessary for BACO because the SMU actually
controls the BACO state to it needs to be active.

For suspend (S3), the asic is put into D3 so the SMU would be
powered down so I don't think we need to put the SMU into
any special state.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:44 -05:00
Alex Deucher
1c074a6383 drm/amdgpu/powerplay: add set_mp1_state for vega12
This sets the SMU into the proper state for various
operations (shutdown, unload, GPU reset, etc.).

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:41 -05:00
Alex Deucher
e254102d50 drm/amdgpu/powerplay: add set_mp1_state for vega10
This sets the SMU into the proper state for various
operations (shutdown, unload, GPU reset, etc.).

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:39 -05:00
Alex Deucher
a906277d22 drm/amdgpu/powerplay: add set_mp1_state for vega20
This sets the SMU into the proper state for various
operations (shutdown, unload, GPU reset, etc.).

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:35 -05:00
Alex Deucher
479baeacd8 drm/amdgpu/powerplay: return success if set_mp1_state is not set
Some asics (APUs) don't have this callback so we want to return
success.  Avoids spurious error messages on APUs.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:25 -05:00
Alex Deucher
a2c28e34f8 drm/amdgpu/powerplay: add a new interface to set the mp1 state
This is required for certain cases such as various GPU resets
(mode1, mode2), BACO, shutdown, unload, etc. to put the SMU into
the appropriate state for when the hw is re-initialized.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:21 -05:00
Alex Deucher
2ddc6c3ef9 drm/amdgpu: add reset_method asic callback for navi
Navi uses either mode1 or baco depending on various
conditions.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:17 -05:00
Alex Deucher
ee360c0b7c drm/amdgpu: add reset_method asic callback for soc15
APUs only support mode2 reset.  dGPUs use either mode1 or
baco depending on various conditions.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:13 -05:00
Alex Deucher
9bc1932f5c drm/amdgpu: add reset_method asic callback for vi
VI always uses the legacy pci based reset.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:10 -05:00
Alex Deucher
6d0f50dafe drm/amdgpu: add reset_method asic callback for cik
CIK always uses the legacy pci based reset.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:24:06 -05:00
Alex Deucher
dd81eede77 drm/amdgpu: add reset_method asic callback for si
SI always uses the legacy pci based reset.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:23:56 -05:00
Alex Deucher
0cf3c64f29 drm/amdgpu: add an asic callback to determine the reset method
Sometimes the driver may have to behave differently depending
on the method we are using to reset the GPU.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:23:44 -05:00
Evan Quan
4d7fd9e20b drm/amd/powerplay: enable SW SMU reset functionality
Move SMU irq handler register to sw_init as that's totally
software related. Otherwise, it will prevent SMU reset working.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:23:37 -05:00
Evan Quan
f0d2a7dc11 drm/amd/powerplay: fix null pointer dereference around dpm state relates
DPM state relates are not supported on the new SW SMU ASICs. But still
it's not OK to trigger null pointer dereference on accessing them.

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>
2019-07-30 23:23:29 -05:00
Evan Quan
fcd90fee8a drm/amd/powerplay: minor fixes around SW SMU power and fan setting
Add checking for possible invalid input and null pointer. And
drop redundant code.

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>
2019-07-30 23:23:21 -05:00
Shirish S
1c42591591 drm/amd/display: enable S/G for RAVEN chip
enables gpu_vm_support in dm and adds
AMDGPU_GEM_DOMAIN_GTT as supported domain

v2:
Move BO placement logic into amdgpu_display_supported_domains

v3:
Use amdgpu_bo_validate_uswc in amdgpu_display_supported_domains.

v4:
amdgpu_bo_validate_uswc moved to sepperate patch.

Signed-off-by: Shirish S <shirish.s@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:23:12 -05:00
Andrey Grodzovsky
ddcb7fc62f drm/amdgpu: Add check for USWC support for amdgpu_display_supported_domains
This verifies we don't add GTT as allowed domain for APUs when USWC
is disabled.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:55 -05:00
Andrey Grodzovsky
3d1b8ec76b drm/amdgpu: Create helper to clear AMDGPU_GEM_CREATE_CPU_GTT_USWC
Move the logic to clear AMDGPU_GEM_CREATE_CPU_GTT_USWC in
amdgpu_bo_do_create into standalone helper so it can be reused
in other functions.

v4:
Switch to return bool.

v5: Fix typos.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:48 -05:00
Andrey Grodzovsky
e4c4073b01 drm/amdgpu: Fix hard hang for S/G display BOs.
HW requires for caching to be unset for scanout BO
mappings when the BO placement is in GTT memory.
Usually the flag to unset is passed from user mode
but for FB mode this was missing.

v2:
Keep all BO placement logic in amdgpu_display_supported_domains

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Shirish S <shirish.s@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:41 -05:00
Jonathan Kim
24f9aacfb0 drm/amdgpu: adding xgmi error monitoring
monitor xgmi errors via mc pie status through fica registers.

Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
Reviewed-by: Kent Russell <Kent.Russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:34 -05:00
Jonathan Kim
64671c0fdc drm/amdgpu: add perfmon and fica atomics for df
adding perfmon and fica atomic operations to adhere to data fabrics finite
state machine requirements for indirect register access.

Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
Reviewed-by: Kent Russell <Kent.Russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:26 -05:00
Jay Cornwall
306fc9c568 drm/amdkfd: Remove dead code from gfx8/gfx9 trap handlers
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:18 -05:00
Jay Cornwall
a36e896740 drm/amdkfd: Replace gfx10 trap handler with correct branch
Previously submitted code was taken from an incorrect branch and
was non-functional.

Cc: Oak Zeng <oak.zeng@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-By: Oak Zeng <oak.zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:11 -05:00
Jay Cornwall
7c2eaf5cdb drm/amdkfd: Fix lost single step exceptions in gfx9 trap handler
If the trap is entered due to MODE.DEBUG_EN=1 and SAVECTX is raised
concurrently the handler cannot identify the source of the exception.
This causes the debugger to lose single step exception notification
when a context save request arrives at the same time.

When MODE.DEBUG_EN=1 and STATUS.HALT=0 (exception not already handled)
jump to the second-level trap handler upon entering the trap. The
second-level trap will set STATUS.HALT=1 and return to the shader.
If SAVECTX was raised then control flow will return to the trap, which
will then handle the context save request.

Cc: Tony Tye <tony.tye@amd.com>
Cc: Laurent Morichetti <laurent.morichetti@amd.com>
Cc: Qingchuan Shi <qingchuan.shi@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Laurent Morichetti <laurent.morichetti@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:22:02 -05:00
Jay Cornwall
8c7a5d9e6f drm/amdkfd: Use SQC when TCP would fail in gfx9 context save.
When a wavefront raises TRAPSTS.XNACK_ERROR with STATUS.ALLOW_REPLAY=0
subsequent memory instructions have undefined behavior. In practice
SQC stores continue to work but TCP stores do not.

Context save is permitted to fail after XNACK error because the
wavefront will be halted and subsequently terminated. However the
debugger has an interest in retrieving the wavefront VGPR/LDS state.

Detect the out-of-spec case and use SQC stores during context save
in place of TCP stores.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:19:47 -05:00
tiancyin
5f4814deab drm/amdgpu/gmc10: fix pte mytpe field error for navi14
navi14 share same PTE format with navi10.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: tiancyin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:19:35 -05:00
James Zhu
6913848087 drm/amdgpu: use VCN firmware offset for cache window
Since we are using the signed FW now, and also using PSP firmware loading,
but it's still potential to break driver when loading FW directly
instead of PSP, so we should add offset.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:19:28 -05:00
Kevin Wang
668a9469f1 drm/amd/powerplay: fix temperature granularity error in smu11
in this patch,
drm/amd/powerplay: add callback function of get_thermal_temperature_range
the driver missed temperature granularity change on other temperature.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:19:21 -05:00
Evan Quan
780f3a9c5b drm/amd/powerplay: some cosmetic fixes
Drop redundant check, duplicate check, duplicate setting
and fix the return value.

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>
2019-07-30 23:19:13 -05:00
Evan Quan
d3a593e97e drm/amd/powerplay: no pptable transfer and dpms enabled with "dpm=0"
Honor the 'dpm' module parameter setting on SW SMU routine as what
we did on previous ASICs. SMU FW loading is still proceeded even
with "dpm=0".

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>
2019-07-30 23:18:58 -05:00
Colin Ian King
87abff7788 drm/amd/display: fix a missing null check on a failed kzalloc
Currently the allocation of config may fail and a null pointer
dereference on config can occur.  Fix this by added a null
check on a failed allocation of config.

Addresses-Coverity: ("Dereference null return")
Fixes: c2cd9d04ec ("drm/amd/display: Hook up calls to do stereo mux and dig programming to stereo control interface")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:18:53 -05:00
Chuhong Yuan
ef1de36181 drm/amd/display: Use dev_get_drvdata
Instead of using to_pci_dev + pci_get_drvdata,
use dev_get_drvdata to make code simpler.

Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:18:46 -05:00
Chuhong Yuan
911d8b3069 drm/amdgpu: Use dev_get_drvdata where possible
Instead of using to_pci_dev + pci_get_drvdata,
use dev_get_drvdata to make code simpler.

Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:18:41 -05:00
Nick Desaulniers
0f0727d971 drm/amd/display: readd -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines
arch/x86/Makefile disables SSE and SSE2 for the whole kernel.  The
AMDGPU drivers modified in this patch re-enable SSE but not SSE2.  Turn
on SSE2 to support emitting double precision floating point instructions
rather than calls to non-existent (usually available from gcc_s or
compiler_rt) floating point helper routines for Clang.

This was originally landed in:
commit 1011745073 ("drm/amd/display: add -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines")
but reverted in:
commit 193392ed9f ("Revert "drm/amd/display: add -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines"")
due to bugreports from GCC builds. Add guards to only do so for Clang.

Link: https://bugs.freedesktop.org/show_bug.cgi?id=109487
Link: https://github.com/ClangBuiltLinux/linux/issues/327

Suggested-by: Sedat Dilek <sedat.dilek@gmail.com>
Suggested-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:18:33 -05:00
Kent Russell
4cab85afe9 drm/amdkfd: Fix byte align on VegaM
This was missed during the addition of VegaM support

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:17:35 -05:00
Kevin Wang
7a81637105 drm/amd/powerplay: add callback function of get_thermal_temperature_range
1. the thermal temperature is asic related data, move the code logic to
xxx_ppt.c.
2. replace data structure PP_TemperatureRange with
smu_temperature_range.
3. change temperature uint from temp*1000 to temp (temperature uint).

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-30 23:17:14 -05:00
Linus Torvalds
88c5083442 Wimplicit-fallthrough patches for 5.3-rc2
Hi Linus,
 
 Please, pull the following patches that mark switch cases where we are
 expecting to fall through. These patches are part of the ongoing efforts
 to enable -Wimplicit-fallthrough. Most of them have been baking in linux-next
 for a whole development cycle.
 
 Also, pull the Makefile patch that globally enables the
 -Wimplicit-fallthrough option.
 
 Finally, some missing-break fixes that have been tagged for -stable:
 
  - drm/amdkfd: Fix missing break in switch statement
  - drm/amdgpu/gfx10: Fix missing break in switch statement
 
 Notice that with these changes, we completely get rid of all the
 fall-through warnings in the kernel.
 
 Thanks
 
 Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEkmRahXBSurMIg1YvRwW0y0cG2zEFAl06XP0ACgkQRwW0y0cG
 2zHPXhAAsatJGNIg7vuSicVipJBIlwgRLwtbE2rV+MCneUAZj37O9NtBgbxHNoJ+
 5TBB8sLpNCw3rEvPKwm6vicRgntMclEY1vaplPOHt3RiY4lqVSIkpvFSCw1hGur3
 +34+O++n/6HbtY96T+DN5WGMXrU3JSe46xnBLIt0BOoUwyKMaNdntiyd79GrrnyB
 BwPkHrmB+9FEVq+dHmPnRIhc9WUfIdily3+j1CIncaM4eXKWLjoUlOIw1VcSEc4X
 SSdFh2co+3nm/6O54ZxUEC1PyuQZWedsgFmeiTrOanG3AEWQ/jX7GwXvPlgraa2E
 F5MzGUOQwXYL/IzXl1vGjQc4+FV4nhIjEBTDdZseOp7FP5xkHyyOwzGDEmaMXpXT
 XThb+k7Q6EbiSPLFcz8zkCwNB8ngNJMNOsGP3JPFD06MfquqdzP7T1BsHcNtiMVo
 FNwQg9KtvbK9F7a9lXDqfcxfuEScbqSvnKWWwNLImCqIBATYirJzeTeLvTbVWpA2
 iyXF3ylIclsSMOvCtaz41iuoqNh12eqw2UIFPBmkU2wpVkTt+ZIn0Apgom90xe1K
 tSUqMBbBMoHVtsBsILdkdz/m6FJpK+YmmwpRrJSDvPxA5c9caD7cj+62amW/gP4z
 Hi6mC4hw1H5bKMsC2PP/QgJcmS/pgo1zwA9J2a2NNJbYPATHfKI=
 =J2sO
 -----END PGP SIGNATURE-----

Merge tag 'Wimplicit-fallthrough-5.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gustavoars/linux

Pull Wimplicit-fallthrough enablement from Gustavo A. R. Silva:
 "This marks switch cases where we are expecting to fall through, and
  globally enables the -Wimplicit-fallthrough option in the main
  Makefile.

  Finally, some missing-break fixes that have been tagged for -stable:

   - drm/amdkfd: Fix missing break in switch statement

   - drm/amdgpu/gfx10: Fix missing break in switch statement

  With these changes, we completely get rid of all the fall-through
  warnings in the kernel"

* tag 'Wimplicit-fallthrough-5.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gustavoars/linux:
  Makefile: Globally enable fall-through warning
  drm/i915: Mark expected switch fall-throughs
  drm/amd/display: Mark expected switch fall-throughs
  drm/amdkfd/kfd_mqd_manager_v10: Avoid fall-through warning
  drm/amdgpu/gfx10: Fix missing break in switch statement
  drm/amdkfd: Fix missing break in switch statement
  perf/x86/intel: Mark expected switch fall-throughs
  mtd: onenand_base: Mark expected switch fall-through
  afs: fsclient: Mark expected switch fall-throughs
  afs: yfsclient: Mark expected switch fall-throughs
  can: mark expected switch fall-throughs
  firewire: mark expected switch fall-throughs
2019-07-27 11:04:18 -07:00
Christoph Hellwig
9a4903e49e mm/hmm: replace the block argument to hmm_range_fault with a flags value
This allows easier expansion to other flags, and also makes the callers a
little easier to read.

Link: https://lore.kernel.org/r/20190726005650.2566-4-rcampbell@nvidia.com
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-26 11:10:53 -03:00
Ralph Campbell
1f96180792 mm/hmm: replace hmm_update with mmu_notifier_range
The hmm_mirror_ops callback function sync_cpu_device_pagetables() passes a
struct hmm_update which is a simplified version of struct
mmu_notifier_range. This is unnecessary so replace hmm_update with
mmu_notifier_range directly.

Link: https://lore.kernel.org/r/20190726005650.2566-2-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
[jgg: white space tuning]
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-07-26 11:10:53 -03:00
Dave Airlie
4d5308e785 Merge tag 'drm-fixes-5.3-2019-07-24' of git://people.freedesktop.org/~agd5f/linux into drm-fixes
drm-fixes-5.3-2019-07-24:

amdgpu:
- RAS fixes for vega20
- Navi VCN fix
- DC audio fixes
- DC DSC fixes
- DC dongle fixes
- DC clk mgr fixes
- Fix DDC lines on some RV2 boards
- GDS fixes for compute
- Navi SMU fixes

ttm:
- Use the same attributes when freeing d_page->vaddr

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190724210527.3415-1-alexander.deucher@amd.com
2019-07-26 14:10:26 +10:00
Gustavo A. R. Silva
9e87891799 drm/amd/display: Mark expected switch fall-throughs
In preparation to enabling -Wimplicit-fallthrough, mark switch
cases where we are expecting to fall through.

Warning level 3 was used: -Wimplicit-fallthrough=3

This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
2019-07-25 20:13:22 -05:00
Gustavo A. R. Silva
12fce1ab4a drm/amdkfd/kfd_mqd_manager_v10: Avoid fall-through warning
In preparation to enabling -Wimplicit-fallthrough, this patch silences
the following warning:

drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c: In function ‘mqd_manager_init_v10’:
./include/linux/dynamic_debug.h:122:52: warning: this statement may fall through [-Wimplicit-fallthrough=]
 #define __dynamic_func_call(id, fmt, func, ...) do { \
                                                    ^
./include/linux/dynamic_debug.h:143:2: note: in expansion of macro ‘__dynamic_func_call’
  __dynamic_func_call(__UNIQUE_ID(ddebug), fmt, func, ##__VA_ARGS__)
  ^~~~~~~~~~~~~~~~~~~
./include/linux/dynamic_debug.h:153:2: note: in expansion of macro ‘_dynamic_func_call’
  _dynamic_func_call(fmt, __dynamic_pr_debug,  \
  ^~~~~~~~~~~~~~~~~~
./include/linux/printk.h:336:2: note: in expansion of macro ‘dynamic_pr_debug’
  dynamic_pr_debug(fmt, ##__VA_ARGS__)
  ^~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c:432:3: note: in expansion of macro ‘pr_debug’
   pr_debug("%s@%i\n", __func__, __LINE__);
   ^~~~~~~~
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_mqd_manager_v10.c:433:2: note: here
  case KFD_MQD_TYPE_COMPUTE:
  ^~~~

by removing the call to pr_debug() in KFD_MQD_TYPE_CP:

"The mqd init for CP and COMPUTE will have the same  routine." [1]

This bug was found thanks to the ongoing efforts to enable
-Wimplicit-fallthrough.

[1] https://lore.kernel.org/lkml/c735a1cc-a545-50fb-44e7-c0ad93ee8ee7@amd.com/

Reviewed-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
2019-07-25 20:13:01 -05:00
Gustavo A. R. Silva
d64062b57e drm/amdgpu/gfx10: Fix missing break in switch statement
Add missing break statement in order to prevent the code from falling
through to case AMDGPU_IRQ_STATE_ENABLE.

This bug was found thanks to the ongoing efforts to enable
-Wimplicit-fallthrough.

Fixes: a644d85a5c ("drm/amdgpu: add gfx v10 implementation (v10)")
Cc: stable@vger.kernel.org
Reviewed-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
2019-07-25 20:12:50 -05:00
Gustavo A. R. Silva
737298d188 drm/amdkfd: Fix missing break in switch statement
Add missing break statement in order to prevent the code from falling
through to case CHIP_NAVI10.

This bug was found thanks to the ongoing efforts to enable
-Wimplicit-fallthrough.

Fixes: 14328aa58c ("drm/amdkfd: Add navi10 support to amdkfd. (v3)")
Cc: stable@vger.kernel.org
Reviewed-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
2019-07-25 20:12:38 -05:00
Leo Li
a1b27e9922 drm/amd/display: Implement MST Aux device registration
Implement late_register and early_unregister hooks for MST connectors.
Call drm helpers for MST connector registration, which registers the
AUX devices.

Cc: Jerry Zuo <Jerry.Zuo@amd.com>
Cc: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190723232808.28128-10-sunpeng.li@amd.com
2019-07-25 17:52:17 -04:00
Leo Li
db432cd096 drm/amd/display: Use connector kdev as aux device parent
Set the connector's kernel device as the parent for the aux kernel
device. This allows udev rules to access connector attributes when
creating symlinks to aux devices.

For example, the following udev rule:

SUBSYSTEM=="drm_dp_aux_dev", SUBSYSTEMS=="drm", ATTRS{edid}=="*",
	SYMLINK+="drm_dp_aux/by-name/$id"

Will create the following symlinks using the connector's name:

$ ls /dev/drm_dp_aux/by-name/
card0-DP-1  card0-DP-2  card0-DP-3

Cc: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Cc: Jerry (Fangzhi) Zuo <Jerry.Zuo@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190723232808.28128-6-sunpeng.li@amd.com
2019-07-25 17:51:57 -04:00
Nicholas Kazlauskas
92e6475ae0 drm/amd/display: Set enabled to false at start of audio disable
[Why]
In an effort to stop redundant calls to dce110_disable_audio_stream
the audio->enabled flag was added to the audio resource struct. While
this state probably shouldn't have been tracked on the audio struct
itself it still works fine for some sequences.

However, it does not work for cases where we're freeing the audio
resource (such as hotplugs) or when dynamic audio is enabled.

In these cases the pipe_ctx->stream_res.audio = NULL before we can
set audio->enabled = false. The next time we acquire the audio resource
such as on hotplug the audio will not be enabled for the stream since
DC thinks it's still enabled.

Audio state tracking should cover this sequence.

[How]
Set audio->enabled = false at the start as long as we have
pipe_ctx->stream_res.audio.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Zhan Liu <Zhan.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-23 15:27:09 -05:00
Alex Deucher
1bcff32679 drm/amdgpu/smu: move fan rpm query into the asic specific code
On vega20, there is an SMU message to query it.  On navi, it's fetched
from the metrics table.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-22 15:25:32 -05:00
Kevin Wang
b840e4d5fe drm/amd/powerplay: custom peak clock freq for navi10
v2:
add function smu_default_set_performance_level as default dpm level handler.
change function name smu_set_performance_level to smu_asic_set_performance_level

v1:
1.NAVI10_PEAK_SCLK_XTX    1830 Mhz
2.NAVI10_PEAK_SCLK_XT     1755 Mhz
3.NAVI10_PEAK_SCLK_XL     1625 Mhz

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Jack Gui <Jack.Gui@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-22 15:23:07 -05:00
Alex Deucher
95ccc15508 drm/amdgpu/smu: move fan rpm query into the asic specific code
On vega20, there is an SMU message to query it.  On navi, it's fetched
from the metrics table.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-22 14:57:39 -05:00
Hawking Zhang
d52d6de280 drm/amdgpu: set sdma irq src num according to sdma instances
Otherwise, it will cause driver access non-existing sdma registers
in gpu reset code path

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-22 14:57:31 -05:00
Kevin Wang
b629167d68 drm/amd/powerplay: remove redundancy debug log in smu
remove redundacy debug log in smu.
eg:
[ 6897.969447] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6897.969448] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6897.969448] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6899.024114] amdgpu: [powerplay] Unsupported SMU message: 38
[ 6899.024151] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6899.024151] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6899.024152] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6900.078296] amdgpu: [powerplay] Unsupported SMU message: 38
[ 6900.078332] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6900.078332] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6900.078333] amdgpu: [powerplay] smu 11 clk dpm feature 1 is not enabled
[ 6901.133230] amdgpu: [powerplay] Unsupported SMU message: 38

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-22 14:57:22 -05:00
Kevin Wang
ebf8fc31cb drm/amd/powerplay: custom peak clock freq for navi10
v2:
add function smu_default_set_performance_level as default dpm level handler.
change function name smu_set_performance_level to smu_asic_set_performance_level

v1:
1.NAVI10_PEAK_SCLK_XTX    1830 Mhz
2.NAVI10_PEAK_SCLK_XT     1755 Mhz
3.NAVI10_PEAK_SCLK_XL     1625 Mhz

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Jack Gui <Jack.Gui@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-22 14:57:06 -05:00
Maxime Ripard
03b0f2ce73 Linus 5.3-rc1
-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAl0006weHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGaDUIAJ4oTyVWpMRZkfG6
 vVY8qVMU3zlzEqRiyLYjkXoe/mGpuU/UVTyyStllxZ+Gg9da0mGwlugScKriPJof
 4KRUDDTGX5DrfEOo+0brKvM+PYh9uGViPgKXzyv7i6BrnX2z3JdBR4bKNuEYlAJ9
 N93Qg7v05SBHIq2Gfp3klrdWbsTTW2EaDTLbcgifXLnfKyFr47kwsmXAHPlTFP0p
 dYsZHHmf14Y9n1+ToZeVINgjQFr6mFn6ygY/PqTnd6vCgEEfP9eENJ4BZCtN1ZL/
 V0BO9MyJ5iZV0AfwSEKydk+kDEvO16TG/nyDrECVuur7AXsBx18ZplVc787f6GK+
 dyCQJ3U=
 =XLAF
 -----END PGP SIGNATURE-----
gpgsig -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQRcEzekXsqa64kGDp7j7w1vZxhRxQUCXTYRHQAKCRDj7w1vZxhR
 xY5IAQC0H/r62rlFq+JpbmksutMqvIferowP7HUk6yOaAKdVawD/c1qsTk/xxI0x
 StrxRCDqeGA7D2R/ZNb/4sobnn7+oAM=
 =k9CF
 -----END PGP SIGNATURE-----

Merge v5.3-rc1 into drm-misc-next

Noralf needs some SPI patches in 5.3 to merge some work on tinydrm.

Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
2019-07-22 21:24:10 +02:00
Linus Torvalds
31cc088a4f drm fixes for -rc1:
nouveau:
 - bugfixes + TU116 enabling (minor iteration):w
 
 amdgpu:
 - large pile of fixes for new hw support this release (navi, vega20)
 - audio hotplug fix
 - bunch of corner cases and small fixes all over for amdgpu/kfd
 
 komeda:
 - back out some new properties (from this merge window) that needs
   more pondering.
 
 bochs: fb pitch setup
 
 ... plus a new panel quirk
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEb4nG6jLu8Y5XI+PfTA9ye/CYqnEFAl0x4sAACgkQTA9ye/CY
 qnFAAw/+JJy7fo95tIVM81p8yDxugpS3+fAJNTnKIndE2behYHPnKCrRk8BhDr0O
 x5xPy4yZHOTndmpDlLUCpV6b8xOvEX+orCNWsqbI2/Kff4yqtBRXhxBhM/3byMth
 nvfjwKVHDLo6SbL0SIIhZTTYBdBDa9zbilJjY86Xn2GdSiiyF/mC3Fhx21tXVTwq
 guoaRDcHAlAwvprKube1dC5y5IXoljJg+w6ydqwma/qUP08As/g0FiI9XvUuzLmY
 ffezdDrsHZPlNIVjGKr2QMhPl6DFSzQRV5UbqXGw7f9s6vW71qtt8a9F+rFk7Ers
 Uq0mqT9VgX6qQ9aBCyXax5UyFj+xr3Owan/D1QEyrUMPpkZHdubz5cliqw20dtYy
 1KNpZtMXR29swGn7J0o/VmtFsRr86+yX9/gL2dY8QDhGCAo/7tYRdDFXBApB+Fgb
 G3Z3Q6YYib6Rom7x3oiZpraf+KY9a+N5RTTrUgvSSxvC7SxxHw/PJbnX7Cjb13fU
 luFw1qs53qv0ytg++UQWivEf5pm/FonhBFq/KikMwtD+LhdtoIm186gPexpV6eaY
 hJZnr9BDafUCwxGZQZ4y01VUwPI5neXTUur8KVOCPqBgtFSR2m6ipgEnZUk9ltLm
 l73MfVbjbvpthds/2+8XDhzB3hnwmTzJlcXN1cQ2RJOEYoBwpe4=
 =s190
 -----END PGP SIGNATURE-----

Merge tag 'drm-next-2019-07-19' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Daniel Vetter:
 "Dave is back in shape, but now family got it so I'm doing the pull.
  Two things worthy of note:

   - nouveau feature pull was way too late, Dave&me decided to not take
     that, so Ben spun up a pull with just the fixes.

   - after some chatting with the arm display maintainers we decided to
     change a bit how that's maintained, for more oversight/review and
     cross vendor collab.

  More details below:

  nouveau:
   - bugfixes
   - TU116 enabling (minor iteration) :w

  amdgpu:
   - large pile of fixes for new hw support this release (navi, vega20)
   - audio hotplug fix
   - bunch of corner cases and small fixes all over for amdgpu/kfd

  komeda:
   - back out some new properties (from this merge window) that needs
     more pondering.

  bochs:
   - fb pitch setup

  core:
   - a new panel quirk
   - misc fixes"

* tag 'drm-next-2019-07-19' of git://anongit.freedesktop.org/drm/drm: (73 commits)
  drm/nouveau/secboot/gp102-: remove WAR for SEC2 RTOS start bug
  drm/nouveau/flcn/gp102-: improve implementation of bind_context() on SEC2/GSP
  drm/nouveau: fix memory leak in nouveau_conn_reset()
  drm/nouveau/dmem: missing mutex_lock in error path
  drm/nouveau/hwmon: return EINVAL if the GPU is powered down for sensors reads
  drm/nouveau: fix bogus GPL-2 license header
  drm/nouveau: fix bogus GPL-2 license header
  drm/nouveau/i2c: Enable i2c pads & busses during preinit
  drm/nouveau/disp/tu102-: wire up scdc parameter setter
  drm/nouveau/core: recognise TU116 chipset
  drm/nouveau/kms: disallow dual-link harder if hdmi connection detected
  drm/nouveau/disp/nv50-: fix center/aspect-corrected scaling
  drm/nouveau/disp/nv50-: force scaler for any non-default LVDS/eDP modes
  drm/nouveau/mcp89/mmu: Use mcp77_mmu_new instead of g84_mmu_new on MCP89.
  drm/amd/display: init res_pool dccg_ref, dchub_ref with xtalin_freq
  drm/amdgpu/pm: remove check for pp funcs in freq sysfs handlers
  drm/amd/display: Force uclk to max for every state
  drm/amdkfd: Remove GWS from process during uninit
  drm/amd/amdgpu: Fix offset for vmid selection in debugfs interface
  drm/amd/powerplay: update vega20 driver if to fit latest SMU firmware
  ...
2019-07-19 12:29:43 -07:00
Dale Zhao
7a83645ac0 drm/amd/display: handle active dongle port type is DP++ or DP case
[Why]:
Some active dongles have DP++ port and DP port at the same time. Current
code doesn't cover DP++ case and processes as default DVI case, in which
audio is disabled. Because of dual mode, DP case is also treat as DVI case
for the other port.

[How]:
According DP 1.4 spec, add DP++ procedure similar with HDMI case. Also
add None dongle type for DP case.

Signed-off-by: Dale Zhao <dale.zhao@amd.com>
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:27 -05:00
Nicholas Kazlauskas
21ffcc94d5 drm/amd/display: Copy GSL groups when committing a new context
[Why]
DC configures the GSL group for the pipe when pipe_split is enabled
and we're switching flip types (buffered <-> immediate flip) on DCN2.

In order to record what GSL group the pipe is using DC stores it in
the pipe's stream_res. DM is not aware of this internal grouping, nor
is DC resource.

So when DM creates a dc_state context and passes it to DC the current
GSL group is lost - DM never knew about it in the first place.

After 3 immediate flips we run out of GSL groups and we're no longer
able to correctly perform *any* flip for multi-pipe scenarios.

[How]
The gsl_group needs to be copied to the new context.

DM has no insight into GSL grouping and could even potentially create
a brand new context without referencing current hardware state. So this
makes the most sense to have happen in DC.

There are two places where DC can apply a new context:
- dc_commit_state
- dc_commit_updates_for_stream

But what's shared between both of these is apply_ctx_for_surface.

This logic only matters for DCN2, so it can be placed in
dcn20_apply_ctx_for_surface. Before doing any locking (where the GSL
group is setup) we can copy over the GSL groups before committing the
new context.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Hersen Wu <hersen.wu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Lewis Huang
291ac8fb0c drm/amd/display: Add debug entry to destroy disconnected edp link
Add a flag to dc_debug_options to determine if a disconnected edp link
should be destroyed.

Signed-off-by: Lewis Huang <Lewis.Huang@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Tony Cheng
46825fcfbe drm/amd/display: avoid power gate domains that doesn't exist
Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Fatemeh Darbehani
9295f1113c drm/amd/display: Add SMU version field to clk_mgr_internal
For some platforms, we need to know SMU version for driver/SMU
compatibility. This change adds that field.

Signed-off-by: Fatemeh Darbehani <fatemeh.darbehani@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Jun Lei
057fc695e9 drm/amd/display: support "dummy pstate"
[why]
Existing support in DC for pstate only accounts for a single latency.  This is sufficient when the
variance of latency is small, or that pstate support isn't necessary for correct ASIC functionality.

Newer ASICs violate both existing assumptions.  PState support is mandatory of correct ASIC
functionality, but not all latencies have to be supported.  Existing code supports a "full p state" which
allows memory clock to change, but is hard for DCN to support (as it requires very large buffers).
New code will now fall back to a "dummy p state" support when "full p state" cannot be support.
This easy p state support should always be allowed.

[how]
Define a new latency in socBB.  Add fallback logic to support it.  Note DML is also updated to ensure
that fallback will always work.

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Eric Yang
0488a56465 drm/amd/display: fix mpcc assert condition
[Why]
In DCN2x asic, the MPCC status register definition changed, and
our logic for assert is incorrect. disabled is valid state,
where we should see idle and not busy, where as in not
disabled state, we should see not idle.

[How]
Change assert condition to be more sensible.

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Eric Yang
dcbb45b6ee drm/amd/display: do not read link setting if edp not connected
[Why]
Previously assume eDP sink present if connector present. Do not
need to enforce this restriction. Fix issue where driver attempt
to read link setting even though no edp connected.

{How]
Only read link setting after reading connection status.

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Tai Man
1b1ff454bd drm/amd/display: Increase size of audios array
[Why]
The audios array defined in "struct resource_pool" is only 6 (MAX_PIPES)
but the max number of audio devices (num_audio) is 7. In some projects,
it will run out of audios array.

[How]
Incraese the audios array size to 7.

Signed-off-by: Tai Man <taiman.wong@amd.com>
Reviewed-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Aric Cyr
f53fc02b9a drm/amd/display: 3.2.42
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Zhan Liu
ba94b08d0b drm/amd/display: drop ASSERT() if eDP panel is not connected
[Why]
For boards that support eDP but do not have a physical eDP
display connected an ASSERT will be thrown. This is not a
critical failure and shouldn't be treated as such.

[How]
Drop the assertion.

Signed-off-by: Zhan Liu <zhan.liu@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Nicholas Kazlauskas
3f52aa9f9f drm/amd/display: Set enabled to false at start of audio disable
[Why]
In an effort to stop redundant calls to dce110_disable_audio_stream
the audio->enabled flag was added to the audio resource struct. While
this state probably shouldn't have been tracked on the audio struct
itself it still works fine for some sequences.

However, it does not work for cases where we're freeing the audio
resource (such as hotplugs) or when dynamic audio is enabled.

In these cases the pipe_ctx->stream_res.audio = NULL before we can
set audio->enabled = false. The next time we acquire the audio resource
such as on hotplug the audio will not be enabled for the stream since
DC thinks it's still enabled.

Audio state tracking should cover this sequence.

[How]
Set audio->enabled = false at the start as long as we have
pipe_ctx->stream_res.audio.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Zhan Liu <Zhan.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Julian Parkin
f591344e89 drm/amd/display: Clean up dynamic metadata logic
[Why]
Code to enable DCN20 dynamic metadata feature is duplicated in two places
and was added to DCE110 enable stream.

[How]
Create DCN20 specific enable stream function for clarity, and add a hardware
sequencer function to program dynamic metadata to avoid the duplicate
code.

Signed-off-by: Julian Parkin <julian.parkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Alvin Lee
ce08aad389 drm/amd/display: Only enable audio if speaker allocation exists
[Why]

In dm_helpers_parse_edid_caps, there is a corner case where no speakers
can be allocated even though the audio mode count is greater than 0.
Enabling audio when no speaker allocations exists can cause issues in
the video stream.

[How]

Add a check to not enable audio unless one or more speaker allocations
exist (since doing this can cause issues in the video stream).

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Julian Parkin
8897810adf drm/amd/display: Fix dc_create failure handling and 666 color depths
[Why]
It is possible (but very unlikely) that constructing dc fails
before current_state is created.

We support 666 color depth in some scenarios, but this
isn't handled in get_norm_pix_clk. It uses exactly the
same pixel clock as the 888 case.

[How]
Check for non null current_state before destructing.

Add case for 666 color depth to get_norm_pix_clk to
avoid assertion.

Signed-off-by: Julian Parkin <julian.parkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Jun Lei
6da16270ee drm/amd/display: populate last calculated bb state with max clocks
[why]
update_bounding_box calculates intermediate bb states based on clock relationship
however, the last state doesn't need to maintain a minimum relationship, but should
actually contain maximum of every clock.  otherwise maximum clocks are not usable

[how]
once the calculated bb is built, override the last state with max values

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Dmytro Laktyushkin
12e2b2d4c6 drm/amd/display: add dcc programming for dual plane
Add dual plane dcc programming support for
surfaces.

Removes unions from plane size and dcc params as they
serve no practical purpose only making our code
more convoluted. This results in easy dual plane
dcc and surface size programming.

Temporary diags_dm code is used to handle the interface
change without breaking functionality as a diags change
needs to be applied after this one.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:26 -05:00
Reza Amini
f7938bc0f0 drm/amd/display: Implement DAL3 GPU Integer Scaling
[WHY]
Users want to not have filtering when scaling by integer
multiples to native timing.

[HOW]
If timing is a multiple integer of view, we set number of taps
to 1 (effectivly closest neighbour).

Signed-off-by: Reza Amini <Reza.Amini@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Tony Cheng <Tony.Cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Dingchen Zhang
f1cdc98fd9 drm/amd/display: add pipe CRC sources without disabling dithering.
[Why]
need to verify the impact of spatial dithering on 8bpc bypass mode.

[How]
added CRC sources and configure dihter option from dc stream.

Signed-off-by: Dingchen Zhang <dingchen.zhang@amd.com>
Reviewed-by: Hanghong Ma <Hanghong.Ma@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Dmytro Laktyushkin
e9bcc1e030 drm/amd/display: use min disp and dpp clk debug option for dcn2
This allows to set a minimum display and dpp clock on dcn2+ HW
by adjusting clocks used for dml calculations.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Charlene Liu
39bca3599a drm/amd/display: add a option to force the clock at every mode change.
[Description]
This is for HW negative stress testing use.
force reset the dispclk and dppclk even the same clock already set in HW.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Murton Liu
54eef8a411 drm/amd/display: Change offset_to_id to reflect what id_to_offset returns
id_to_offset does not point to the same reg offset that offset_to_id checks for,
causing unintended asserts

Signed-off-by: Murton Liu <murton.liu@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Charlene Liu
925f566cb7 drm/amd/display: add set and get clock for testing purposes
add dc_set_clock
add dc_get_clock

this is for testing and diagnostics to get/set DPPCLK and DISPCLK.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Derek Lai
30db43b62c drm/amd/display: allocate 4 ddc engines for RV2
[Why]
Driver will create 0, 1, and 2 ddc engines for RV2,
but some platforms used 0, 1, and 3.

[How]
Still allocate 4 ddc engines for RV2.

Signed-off-by: Derek Lai <Derek.Lai@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Murton Liu
c2cd9d04ec drm/amd/display: Hook up calls to do stereo mux and dig programming to stereo control interface
[Why]
Implementation of stereo mux register is complete, but unused. Need to
call functions to write relevant configs.

[How]
Add function to write stereo config for enable/disable case and call in
stereo control interface.

Signed-off-by: Murton Liu <murton.liu@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Aric Cyr
692626fc4d drm/amd/display: 3.2.41
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Ilya Bakoulin
473e0ecbb4 drm/amd/display: Fixes for some MPO cases
[Why]
Alpha could be improperly applied (only affecting half the
frame) for some source pixel formats.

[How]
Change how alpha is enabled in MPC/DPP LB and change the
bottom plane blend mode in MPC.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Ilya Bakoulin
8bee5c5c7e drm/amd/display: Cache the use_pitch_c conditional
For clarity, save the use_pitch_c logic to a bool

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Eric Bernstein <eric.bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Nevenko Stupar
69866d1323 drm/amd/display: Add DIG_CLOCK_PATTERN register
Add this register for future use

Signed-off-by: Nevenko Stupar <Nevenko.Stupar@amd.com>
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Qingqing Zhuo
290129c256 drm/amd/display: Add CM_BYPASS via debug option
[Why]
bypass CM block and MPC ogam for debug or triage use.

[How]
create a new flag cm_bypass_mode, which will set both CM_CONTROL
and MPCC_OGAM_MODE to bypass when set to 1.

Signed-off-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Vitaly Prosyak
a208009869 drm/amd/display: Add MPC 3DLUT resource management
[Why & How]
Number of 3DLUT's in MPC are not equal to number of pipes.
Resource management is required.
Activate on FPGA entire tm solution  which includes
the following :hdr multiplier, shaper, 3dlut.

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Gary Kattan <Gary.Kattan@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Joshua Aberback
70f1476a7e drm/amd/display: Add debug option to disable timing sync
[Why]
We want a debug option to disable timing sync for testing.

[How]
New dc debug option that must be false to call program_timing_sync

Signed-off-by: Joshua Aberback <joshua.aberback@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Nikola Cornij
d68a745417 drm/amd/display: Clear FEC_READY shadow register if DPCD write fails
[why]
As a fail-safe, in case 'set FEC_READY' DPCD write fails, a HW shadow
register should be cleared and the internal FEC stat should be set to
'not ready'. This is to make sure HW settings will be consistent with
FEC_READY state on the RX.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Chris Park <Chris.Park@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Krunoslav Kovac
e752058b86 drm/amd/display: Optimize gamma calculations
[Why&How]

1. Stack usage is pretty high as fixed31_32 struct is 8 bytes and we
have functions with >30 vars on the stack.

2. Optimize gamma calculation by reducing number of calls to
dc_fixpt_pow Our X points are divided into 32 regions wth 16 pts each.
Each region is 2x the previous, meaning x[i] = 2*x[i-16] for i>=16.
Using (2x)^gamma = 2^gamma * x^gamma, we can recursively compute powers
of gamma, we just need first 16 pts to start it up. dc_fixpt_pow() is
expensive, it computes x^y by doing exp(y*logx) Exp is done by Taylor
series approximation, and log by Newton-like approximation that also
uses exp internally. In short, it's significantly heavier than
run-of-the-mill addition/subtraction/multiply.

Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Eric Yang
c43f89f81c drm/amd/display: put back front end initialization sequence
[Why]
Seamless boot optimization removed proper front end power off sequence.
In driver disable enable case, this causes driver to power gate hubp
and dpp while there is still memory fetching going on, this can cause
invalid memory requests to be generated which will hang data fabric.

[How]
Put back proper front end power off sequence

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Tony Cheng <Tony.Cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:25 -05:00
Nikola Cornij
008a4016c5 drm/amd/display: Set FEC_READY always before link training
[why]
Right now we FEC_READY is set only before the final link training,
i.e. at mode set time. This means FEC_READY won't be set when doing
link training as a response to HPD. It also fails UCD400 FEC test in
DP compliance.

[how]
Move FEC_READY setup to link training.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Abdoulaye Berthe <Abdoulaye.Berthe@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:24 -05:00
Eric Bernstein
a280a71f5e drm/amd/display: Use helper for determining HDMI signal
Use helper to determine if HDMI signal when processing avmute.

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:24 -05:00
Murton Liu
d40605b6d0 drm/amd/display: Implement generic MUX registers (v2)
[Why]
Logic & structures for generic regs does not exist in DC currently.

[How]
Implement register masks/shifts and relevant functions for generic mux,
similar to existing HPD and DDC objects.

V2: fix includes for kalloc/free (Alex)

Signed-off-by: Murton Liu <murton.liu@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:27:24 -05:00
Alvin Lee
4c6a961807 drm/amd/display: Wait for flip to complete
[why]
In pipe split issue occurs when we program immediate flip while vsync flip is pending

[how]
Don't program immediate flip until flip is no longer pending

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jaehyun Chung <Jaehyun.Chung@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Aric Cyr
351960b098 drm/amd/display: 3.2.40
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Fatemeh Darbehani
7e6472966e drm/amd/display: Change min_h_sync_width from 8 to 4
[Why]
Some display's hsync width is lower than the minimum dcn20 is set
to support right now. This will cause optc1_validate_timing to fail which
eventually will result in wrong set mode. This was set to 8 as per
HW team's request for no valid reason.

[How]
Changing min_h_sync_width to 4 will let us validate timing for
preffered mode and light up the headset. This change was made
to Vega 10 before for a similar issue.

Signed-off-by: Fatemeh Darbehani <fatemeh.darbehani@amd.com>
Reviewed-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Alvin Lee
1b3c61036e drm/amd/display: Remove second initialization of pp_smu
[why]
We initialize pp_smu twice

[how]
Remove second initialization of pp_smu

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jaehyun Chung <Jaehyun.Chung@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Su Sung Chung
18b401874a drm/amd/display: fix not calling ppsmu to trigger PME
[why]
dcn20_clk_mgr_construct was not initializing pp_smu, and PME call gets
filtered out by the null check

[how]
initialize pp_smu dcn20_clk_mgr_construct

Signed-off-by: Su Sung Chung <Su.Chung@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Tai Man
5feb9f07a2 drm/amd/display: use encoder's engine id to find matched free audio device
[Why]
On some platforms, the encoder id 3 is not populated. So the encoders
are not stored in right order as index (id: 0, 1, 2, 4, 5) at pool. This
would cause encoders id 4 & id 5 to fail when finding corresponding
audio device, defaulting to the first available audio device. As result,
we cannot stream audio into two DP ports with encoders id 4 & id 5.

[How]
It need to create enough audio device objects (0 - 5) to perform matching.
Then use encoder engine id to find matched audio device.

Signed-off-by: Tai Man <taiman.wong@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Harry Wentland
252f3d950d drm/amd/display: Remove unnecessary NULL check in set_preferred_link_settings
[Why]
link_stream is never NULL here as we've dereferenced it a couple lines before
and have done so for a couple months now.

[How]
- Drop the NULL check.
- Initialize where we know link_stream is non-NULL

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Charlene Liu
03f3e40c8b drm/amd/display: Do not fill Null packet in the blank period
[Description]
Do not fill Null packet in the blank period for new packet gen
This is based on HW IP team recommended default setting change.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Zi Yu Liao
5a42dc2be0 drm/amd/display: fix DMCU hang when going into Modern Standby
[why]
When the system is going into suspend, set_backlight gets called
after the eDP got blanked. Since smooth brightness is enabled,
the driver will make a call into the DMCU to ramp the brightness.
The DMCU would try to enable ABM to do so. But since the display is
blanked, this ends up causing ABM1_ACE_DBUF_REG_UPDATE_PENDING to
get stuck at 1, which results in a dead lock in the DMCU firmware.

[how]
Disable brightness ramping when the eDP display is blanked.

Signed-off-by: Zi Yu Liao <ziyu.liao@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Alvin Lee
1d0610bc26 drm/amd/display: Disable Audio on reinitialize hardware
[Why]
When we recover from hang, we do not want to skip the audio enable call.

[How]
Disable audio in dc_reinitialize_hardware

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Nikola Cornij
75c3500023 drm/amd/display: Power-gate all DSCs at driver init time
[why]
DSC should be powered-on only on as-needed basis, i.e. if the mode
requires it

[how]
Loop over all the DSCs at driver init time and power-gate each

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Nevenko Stupar <Nevenko.Stupar@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Dmytro Laktyushkin
8fca3d9415 drm/amd/display: Remove dsc disable_ich flag programming.
Current default is sufficient for a flag that does not change.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Derek Lai
701c75cea2 drm/amd/display: Read max down spread
[Why]
When launch D10.2, driver will write DPCD 0x107 with 0x00

[How]
Read MAX_DOWNSPREAD (0x0003h) then keep in current
link settings

Signed-off-by: Derek Lai <Derek.Lai@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Ilya Bakoulin
eced4bceed drm/amd/display: Fix some HUBP programming issues
[Why]
A hubp pointer was being passed to DCN1 functions, which
expect the enclosing structure (for the purpose of container_of macros)
to be dcn10_hubp, but the actual type was dcn20_hubp.

[How]
Copy existing DCN1 functions and alter them slightly for use with
dcn20_hubp.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:10 -05:00
Ilya Bakoulin
24f1d1cee2 drm/amd/display: Check for valid stream_encode
Before accessing it's vtable, check that stream_encoder is non-null.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Ilya Bakoulin
4fb6ec466d drm/amd/display: Expose enc2_set_dynamic_metadata
[Why]
Need to implement register programming for HDR dynamic
metadata transmission and tests.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Aric Cyr
6d58f99444 drm/amd/display: 3.2.39
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
SivapiriyanKumarasamy
d35d77a6a5 drm/amd/display: Wait for backlight programming completion in set backlight level
[WHY]
Currently we don't wait for blacklight programming completion in DMCU
when setting backlight level. Some sequences such as PSR static screen
event trigger reprogramming requires it to be complete.

[How]
Add generic wait for dmcu command completion in set backlight level.

Signed-off-by: SivapiriyanKumarasamy <sivapiriyan.kumarasamy@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Dingchen Zhang
8fb843d179 drm/amd/display: add functionality to get pipe CRC source.
[Why]
We need to check the pipe crc source through debugfs for bypass mode test.

[How]
add implementation of amdgpu_dm_crtc_get_crc_sources and hook into drm_crtc
callback get_crc_sources.

Signed-off-by: Dingchen Zhang <dingchen.zhang@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Dingchen Zhang
14b2584636 drm/amd/display: add functionality to grab DPRX CRC entries.
[Why]
We need to compare DPRX CRCs with framebuffer CRCs for digital bypass mode.

[How]
Hook into DRM to grab DP receiver CRCs through drm_dp_start_crc.

Signed-off-by: Dingchen Zhang <dingchen.zhang@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Julian Parkin
2425347697 drm/amd/display: Poll for GPUVM context ready (v2)
[Why]
Hardware docs state that we must wait until the GPUVM context is ready
after programming it.

[How]
Poll until the valid bit of PAGE_TABLE_BASE_ADDR_LO32 is set to 1 after
programming it.

v2: fix include for udelay (Alex)

Signed-off-by: Julian Parkin <julian.parkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Anthony Koo
88eac241a1 drm/amd/display: add monitor patch to add T7 delay
[Why]
Specifically to one panel,
TCON is able to accept active video signal quickly, but
the Source Driver requires 2-3 frames of extra time.

It is a Panel issue since TCON needs to take care of
all Sink requirements including Source Driver. But in
this case it does not.

Customer is asking to add fixed T7 delay as panel
workaround.

[How]
Add monitor specific patch to add T7 delay

Signed-off-by: Anthony Koo <anthony.koo@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Dmytro Laktyushkin
606b355170 drm/amd/display: add hdmi2.1 dsc pps packet programming
This change adds EMP packet programming for enabling dsc with
hdmi. The packets are structured according to VESA HDMI 2.1x
r2 spec, section 10.10.2.2.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Su Sung Chung
c1f2e01540 drm/amd/display: refactor dump_clk_registers
[why]
for 2 purposes:

1. get raw register value dumped on the log, which will make it easier
to talk to other team who only knows about the register

2. enable other HW to be able to use the same interface as raven to log
clock register data

Signed-off-by: Su Sung Chung <Su.Chung@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Wenjing Liu
29344d152d drm/amd/display: wait for the whole frame after global unlock
[why]
The current code will not wait for the entire frame
 after global unlock.
This causes dsc dynamic target bpp update corruption when
there is a surface update immediately happens after this.

[how]
Wait for the entire whole frame after unlock before continuing
the rest of stream and surface update.

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Nevenko Stupar
40fd9090ae drm/amd/display:Use Pixel clock in 100Hz units for HDMI Audio wall clock DTO
[Why]
-Pass and use pixel clock in 100 Hz to Audio for HDMI
audio DTO for Audio wall clock programming so audio DTO gets
increased precision for timings with /1001 factor.
-For HDMI TMDS for N and CTS ACR tables are based on 10 KHz
units, these does not need to be modified as N and CTS values
are still valid using current tables.

Signed-off-by: Nevenko Stupar <Nevenko.Stupar@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Nicholas Kazlauskas
7cecfe9d19 drm/amd/display: Copy max_clks_by_state after dce_clk_mgr_construct
[Why]
For DCE110, DCE112 and DCE120 the max_clks_by_state for the clk_mgr are
copied from their respective table before the call to
dce_clk_mgr_construct, but then dce_clk_mgr_construct overwrites
these with the dce80_max_clks_by_state.

[How]
Copy these after we call dce_clk_mgr_construct so we're using the
right tables.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Murton Liu
08d238e689 drm/amd/display: Clock does not lower in Updateplanes
[why]
We reset the optimized_required in atomic_plane_disable
flag immediately after it is set in atomic_plane_disconnect, causing us to
never have flag set during next flip in UpdatePlanes.

[how]
Optimize directly after each time plane is removed.

Signed-off-by: Murton Liu <murton.liu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
David Galiffi
0430017149 drm/amd/display: Incorrect Read Interval Time For CR Sequence
[WHY]
TRAINING_AUX_RD_INTERVAL (DPCD 000Eh) modifies the read interval
for the EQ training sequence. CR read interval should remain 100 us.
Currently, the CR interval is also being modified.

[HOW]
lt_settings->cr_pattern_time should always be 100 us.

Signed-off-by: David Galiffi <david.galiffi@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Aric Cyr
0b6cbbd5da drm/amd/display: 3.2.38
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:09 -05:00
Charlene Liu
c70b401630 drm/amd/display: Split out common HUBP registers and code
There are shared regs and code across DCN generations. Pull them out
into a shared common location.

Also, expose some dcn20 init functions.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Samson Tam
08900ab732 drm/amd/display: skip retrain in dc_link_set_preferred_link_settings() if using passive dongle
[Why]
Fixes issue when we have a display connected using a passive
dongle and then emulate over it using a DP connection at 1 x 1.62 Ghz.
System hangs because register bus returns back 0xFFFFFFFF for all
register reads after setting register DIG_BE_CNTL in
dcn10_link_encoder_connect_dig_be_to_fe().  Hang occurs later
when trying to do a register read.

[How]
At the start of the emulation, dc_link_set_preferred_link_settings()
and dp_retrain_link_dp_test() is called, even though it is connected
using a passive dongle.

Add an extra condition in dp_retrain_link_dp_test() to check for
link->dongle_max_pix_clk > 0.  This is the only way we know if the
connection is using passive dongle so we don't retrain DP.

Signed-off-by: Samson Tam <Samson.Tam@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Jun Lei
6d988a557e drm/amd/display: swap system aperture high/low
[why]
Currently logical values are swapped in HW, causing
system aperture to be undefined, so VA and PA cannot co-exist

[how]
program values correctly

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Nikola Cornij
771b286379 drm/amd/display: Set one 4:2:0-related PPS field as recommended by DSC spec
[why]
'second_line_offset_adj' was mistakenly left at zero, even though DSC spec
v1.2a recommends setting this field to 512 for 4:2:0.

[how]
Set 'second_line_offset_adj' to 512 for 4:2:0 and leave at zero otherwise

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Dmytro Laktyushkin
a6f30079b8 drm/amd/display: Set default block_size, even in unexpected cases
We're not expected to enter the default case, but not returning a
default value here is incorrect.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Eric Yang
5e335add0b drm/amd/display: early return when pipe_cnt is 0 in bw validation
[Why]
Unintentionally introduced behaviour change from previous refactor,
which causes clks to be 0 in no stream cases, which will cause
divide by 0.

[How]
Skip calculation of clocks when no stream. Which is the same as old
behaviour.

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Tony Cheng <tong.cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
David Francis
64af142a8c drm/amd/display: Update drm_dsc to reflect native 4.2.0 DSC spec
[Why]
Some parts of the DSC spec relating to 4.2.0 were not reflected in
drm_dsc_compute_rc_parameters, causing unexpected config failures

[How]
Add nsl_bpg_offset and rbs_min computation

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Chiawen Huang
63b9caff98 drm/amd/display: Add aux tracing log in dce
[Why]
dce was re-arch'd, therefore adding aux tracing log into new dce

[How]
The porting from submit_channel_request/process_channel_reply of aux_engine_dce110.c

Signed-off-by: Chiawen Huang <chiawen.huang@amd.com>
Reviewed-by: Tony Cheng <tong.cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Harmanprit Tatla
ac3d76e066 drm/amd/display: No audio endpoint for Dell MST display
[Why]
There are certain MST displays (i.e. Dell P2715Q)
that although have the MST feature set to off may still
report it is a branch device and a non-zero
value for downstream port present.
This can lead to us incorrectly classifying a
dp dongle connection as being active and
disabling the audio endpoint for the display.

[How]
Modified the placement and
condition used to assign
the is_branch_dev bit.

Signed-off-by: Harmanprit Tatla <harmanprit.tatla@amd.com>
Reviewed-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Jun Lei
ff4258d590 drm/amd/display: cap DCFCLK hardmin to 507 for NV10
[why]
Due to limitation in SMU/PPLIB, it is not possible to know Fmax @ Vmin for DCFCLK.
This causes issues at high display configurations where extra headroom of DCFCLK
can enable P-state switching

[how]
Use existing override logic.  If override not defined, then force
min = 507

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Eric Yang
6de202373b drm/amd/display: move bw calc code into helpers
[Why]
For better readability and reusability

[How]
Move snippets of BW calculation code into helpers.

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Fatemeh Darbehani <Fatemeh.Darbehani@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Aric Cyr
4bc846908b drm/amd/display: 3.2.37
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Dmytro Laktyushkin
ec16ac6b42 drm/amd/display: fix dsc disable
A regression caused dsc to never get disabled in certain situations.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Jun Lei
b48935b3bf drm/amd/display: fix up HUBBUB hw programming for VM
[why]
Some values were not being converted or bit-shifted properly for
HW registers, causing black screen

[how]
Fix up the values before programming HW

Signed-off-by: Jun Lei <jun.lei@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Aric Cyr
125cfef3e4 drm/amd/display: 3.2.36
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
David Galiffi
e0a6440a29 drm/amd/display: Add ability to set preferred link training parameters.
[WHY]
To add support for OS requirement to set preferred link training
parameters.

[HOW]
Create new structure of dp link training overrides. During link training
processes, these values should be used instead of the default training
parameters.

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:08 -05:00
Jun Lei
93c25fbdc3 drm/amd/display: initialize p_state to proper value
[why]
On some modes SMU will be in infinite loop state at boot, this is
because driver assumes p_state_support is false, but this is the
opposite of the assumed boot state by SMU.  we optimize away
notifying SMU about no pstate, and so they will get stuck

[how]
when we init clk manager, init pstate to true, so it matches driver load
assumption

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Leo Liu
53ef3969dd drm/amdgpu: use VCN firmware offset for cache window
Since we are using the signed FW now, and also using PSP firmware loading,
but it's still potential to break driver when loading FW directly
instead of PSP, so we should add offset.

Signed-off-by: Leo Liu <leo.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Kevin Wang
c49b1b59a2 drm/amd/powerplay: change sysfs pp_dpm_xxx format for navi10
v2:
set average clock value on level 1 when current clock equal
min or max clock (fine grained dpm support).

the navi10 gfxclk (sclk) support fine grained DPM,
so use level 1 to show current dpm freq in sysfs pp_dpm_xxx

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Hawking Zhang
33c976c961 drm/amdgpu: drop ras self test
this function is not needed any more. error injection is
the only way to validate ras but it can't be executed in
amdgpu_ras_init, where gpu is even not initialized

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Hawking Zhang
a5dd40ca81 drm/amdgpu: only allow error injection to UMC IP block
error injection to other IP blocks (except UMC) will be enabled
until RAS feature stablize on those IP blocks

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Hawking Zhang
4d249d3abd drm/amdgpu: disable GFX RAS by default
GFX RAS has not been stablized yet. disable GFX ras until
it is fully funcitonal.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Hawking Zhang
fb2a36075a drm/amdgpu: do not create ras debugfs/sysfs node for ASICs that don't have ras ability
driver shouldn't init any ras debugfs/sysfs node for ASICs that don't have ras
hardware ability

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Evan Quan
3a48c10d7f drm/amd/powerplay: report bootup clock as max supported on dpm disabled
With gfxclk or uclk dpm disabled, it's reasonable to report bootup clock
as the max supported.

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>
2019-07-18 14:18:07 -05:00
Joseph Greathouse
fbdc5d8d84 drm/amdgpu: Default disable GDS for compute VMIDs
The GDS and GWS blocks default to allowing all VMIDs to
access all entries. Graphics VMIDs can handle setting
these limits when the driver launches work. However,
compute workloads under HWS control don't go through the
kernel driver. Instead, HWS firmware should set these
limits when a process is put into a VMID slot.

Disable access to these devices by default by turning off
all mask bits (for OA) and setting BASE=SIZE=0 (for GDS
and GWS) for all compute VMIDs. If a process wants to use
these resources, they can request this from the HWS
firmware (when such capabilities are enabled). HWS will
then handle setting the base and limit for the process when
it is assigned to a VMID.

This will also prevent user kernels from getting 'stuck' in
GWS by accident if they write GWS-using code but HWS
firmware is not set up to handle GWS reset. Until HWS is
enabled to handle GWS properly, all GWS accesses will
MEM_VIOL fault the kernel.

v2: Move initialization outside of SRBM mutex

Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Jonathan Kim
c52e7ebce7 drm/amdgpu: exposing fica registers to df offsets
exposing fica registers to poll df pie data for xgmi error counters for
vega20.

Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
Reviewed-by: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Evan Quan
c06403045a drm/amd/powerplay: input check for unsupported message/clock index
This can avoid them to be handled in a wrong way without notice.
Since not all SMU messages/clocks are supported on every SMU11 ASIC.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Evan Quan
7e01a2ec96 drm/amd/powerplay: correct SW SMU valid mapping check
Current implementation is not actually able to detect
invalid message/table/workload mapping.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Alex Deucher
a08a4dae7a drm/amdgpu: flag arcturus as experimental for now
Current support will only work in internal engineering
boards.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Alex Deucher
ad91b134a2 drm/amdgpu: drop unused function definitions
These were dropped and the headers never got cleaned up.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
James Zhu
1da418ba65 drm/amdgpu:add all VCN rings into schedule request queue
Add all VCN instances' decode/encode/jpeg decode rings into
drm_sched_rq list.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Boyuan Zhang <boyuan.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Oak Zeng
47a7fe5316 drm/amdkfd: Increase vcrat size for GPU
GPU cache info (part of virtual CRAT) size depends on CU number.
For arcturus, CU number has been increased. So the required memory
for vcrat also increases.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Le Ma
69d4de94f8 drm/amdgpu: enable all 8 sdma instances for Arcturus silicon
The more 6 sdma instances work fine now with DF fix in vbios:
  * mmDF_PIE_AON_MiscClientsEnable(0x1c728)=0x3fe(DF_ALL_INSTANCE)
       [9:4]MmhubsEnable=3f (change from 0)

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:07 -05:00
Jay Cornwall
37f86a9b36 drm/amdkfd: Merge gfx9/arcturus trap handlers, add ACC VGPR save
ACC VGPRs are a secondary VGPR set of same size as the primary VGPRs.
Save them as a block immediately following VGPRs.

Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Yong Zhao
5ddd4a9a7c drm/amdgpu: Add more detail to the VM fault printing
With the printing, we don't need to parse the value on our own any more.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Oak Zeng
e30d90fca3 drm/amdkfd: Add device id for real asics
Add pci device ids.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Le Ma
fc1e272e8d drm/amdgpu: limit sdma instances to 2 for Arcturus in BU phase
Another 6 sdma instances do not work at present. Disable them to unblock KFD
for silicon bringup as a workaround

Signed-off-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Hawking Zhang
f9cf36fcaf drm/amdgpu: skip gfx 9 common golden settings for arct
They are not needed by arct

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Oak Zeng
3baa24f0fc drm/amdkfd: Add arcturus CWSR trap handler
CWSR (compute wave save/restore) is used for
preempting compute queues.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Yong Zhao
54bd77f3d0 amd/powerplay: No SW XGMI dpm for Arcturus rev 2
xgmi dpm is handled by the SMU.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Le Ma
a80955176d drm/amdgpu: clean up nonexistent firmware declaration for Arcturus
CPG firmwares are not used.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Hawking Zhang
22f5ea4ca0 drm/amdgpu: init gds config for arct
arct has 4KB gds (4 banks inside) so the max_wave_id
should be 0xfff

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Hawking Zhang
bfa3a9bb98 drm/amdgpu: keep stolen memory for arct
Any dce register read back from arct is invalid. use hard code
stolen memory for arct until we validate the s3.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Hawking Zhang
d57c3d5634 drm/amdgpu: init arct external rev id
Properly set the external silicon revision id.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Hawking Zhang
582870de56 drm/amdgpu: add arct gc golden settings
Golden GC register settings from the hw team.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Hawking Zhang
ca1961a2f5 drm/amdgpu: add arct sdma golden settings
Golden SDMA register settings from the hw team.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Feifei Xu
48c69cda45 drm/amdgpu: add pci DID for Arcturus GL-XL.
Add device ids for Arcturus.

Signed-off-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Le Ma <Le.Ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
Le Ma
6c54afc7e8 drm/amdgpu: assign fb_start/end in mmhub v9.4 interface
Align with mmhub v1.0.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
James Zhu
cd1fd7b381 drm/amdgpu: add harvest support for Arcturus
Add VCN harvest support for Arcturus

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:06 -05:00
James Zhu
fa739f4b06 drm/amdgpu: add multiple instances support for Arcturus
Arcturus has dual-VCN. Need add multiple instances support for Arcturus.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
James Zhu
c01b6a1d38 drm/amdgpu: modify amdgpu_vcn to support multiple instances
Arcturus has dual-VCN. Need Restruct amdgpu_device::vcn to support
multiple vcns. There are no any logical changes here

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
James Zhu
989b6a0549 drm/amdgpu: add vcn nbio doorbell range setting for 2nd vcn instance
add vcn nbio doorbell range setting for 2nd vcn instance

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
James Zhu
8b75a521c0 drm/amdgpu/: increase AMDGPU_MAX_RINGS to add 2nd vcn instance
increase AMDGPU_MAX_RINGS to add 2nd vcn instance

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
James Zhu
6da061dca9 drm/amdgpu/: add doorbell assignment for 2nd vcn instance
add doorbell assignment for 2nd vcn instance

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
James Zhu
a07d163c90 drm/amdgpu/: add ucodeID for 2nd vcn instance
add ucodeID for 2nd vcn instance

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
James Zhu
8a6fcd3532 drm/amdgpu/: add clientID for 2nd vcn instance
add clientID for 2nd vcn instance, remove unused SOC15_IH_CLIENTID_SYSHUB.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Oak Zeng
b6689cf7b9 drm/amdkfd: Set number of xgmi optimized SDMA engines for arcturus
some sdma engines are optimized for xgmi on arcturus.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Le Ma
5fb7c66508 drm/amdgpu: correct ip for mmHDP_READ_CACHE_INVALIDATE register access
Use the proper IP index for HDP registers.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Le Ma
7d0670f441 drm/amdgpu: set system aperture to cover whole FB region in mmhub v9.4
In XGMI configuration, the FB region covers vram region from peer
device, adjust system aperture to cover all of them

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Le Ma
75b2fce2d8 drm/amdgpu: skip get/update xgmi topology info when no psp exists
We don't currently have psp support for arcturus so provide a alternative
mechanism in the meantime.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Chengming Gui
e7773c1c11 drm/amd/powerplay: get smc firmware and pptable
get smc firmware and pptable for arcturus

Signed-off-by: Chengming Gui <Jack.Gui@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Chengming Gui
1fb8cfc2a3 drm/amdgpu/powerplay: add smu11 driver interface for arcturus. (v2)
add smu11_driver_if_arcturus.h file.

v2: add license, fix header guard (Alex)

Signed-off-by: Chengming Gui <Jack.Gui@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Chengming Gui
6fba59060c drm/amdgpu/powerplay: add arcturus ppt functions
add arcturus_ppsmc.h arcturus_ppt.c and arcturus_ppt.h files.

This is the initial power management support for Arcturus.

Signed-off-by: Chengming Gui <Jack.Gui@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Leo Liu
530e30fc32 drm/amdgpu: enable the Doorbell support for VCN2.5
Including decode, encode, and JPEG decode rings

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Leo Liu
39a5053fb2 drm/amdgpu: add vcn doorbell range function to nbio7.4 (v2)
To setup the aperture for VCN2.5

v2: setup vcn doorbells in vcn2.5 hw_init (Alex)

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Leo Liu
08249a3a32 drm/amdgpu: enable VCN2.5 on Arcturus
VCN is the video decode and encode engine on Arcturus

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Leo Liu
8001073708 drm/amdgpu/VCN2.5: set JPEG decode ring functions
Also reuse most of the JPEG2.0 decode ring functions

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Leo Liu
e87d5a7a23 drm/amdgpu: add JPEG2.5 HW start and stop
JPEG engine initialization and suspend sequences

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:05 -05:00
Leo Liu
a4767886e5 drm/amdgpu/VCN2.5: set encode ring functions
Also reuse most of the VCN2.0 encode ring functions

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Leo Liu
185a579700 drm/amdgpu/VCN2.5: set decode ring functions
Also reuse most of the VCN2.0 decode ring functions

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Leo Liu
a7c0e4019f drm/amdgpu: add Arcturus to the VCN family
including firmware support etc.

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Leo Liu
cbead2bdfc drm/amdgpu: add VCN2.5 VCPU start and stop
HW engine initialization and suspend sequences.

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Leo Liu
28c17d7207 drm/amdgpu: add VCN2.5 basic supports
i.e. basic VCN IP SW structures

VCN is the video codec block on the GPU.

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Leo Liu
cdbd115eaf drm/amdgpu/VCN2: expose rings functions
They can be reused by VCN2.x family

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Leo Liu
22a8f44286 drm/amdgpu/VCN2: put IB internal registers offset to structure
So the ring functions can be shared with different VCN versions
with different internal registers offsets

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Le Ma
eec28ef03c drm/amdgpu: declare sdma firmware binary files for Arcturus
So that they are properly picked up as a driver dependency.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
James Zhu
db6a49d958 drm/amdgpu: Clear build undefined warning
Add amdgpu_amdkfd_arcturus_get_functions stub when
CONFIG_HSA_AMD is undefinded.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Oak Zeng
eb39aff7e0 drm/amdgpu: Enable xgmi support for Arcturus
xgmi is a high performance cross-GPU communication channel.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Oak Zeng
2f2eab3acc drm/amdgpu: Hack xgmi topology info when there is no psp fw
This is only needed on emulation platform where psp fw might
not be available, to hack xgmi topology info such as hive id and
node id.

v2: Add offset to hacked hive/node id
v3: Don't use introduce new module parameter.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Yong Zhao
0ad8c5e296 drm/amdkfd: Support MMHUB1 in kfd interrupt path
Handle interrupts for second mmhub.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Yong Zhao
c9ffdf5acd drm/amdgpu: Set VM_L2_CNTL.PDE_FAULT_CLASSIFICATION to 0 for MMHUB 9.4
Should be set to 0 for mmhub 9.4.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Oak Zeng
3e205a0849 drm/amdkfd: Implement kfd2kgd_calls for Arcturus
Arcturus shares most of the kfd2kgd_calls with gfx9. But due to
SDMA register address change, it can't share SDMA related functions.
Export gfx9 kfd2kgd_calls and implement SDMA related functions
for Arcturus.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Oak Zeng
35cdc81bfa drm/amdkfd: Fix sdma_bitmap overflow issue
In the original formula, when sdma queue number is 64,
the left shift overflows. Use an equivalence that won't
overflow.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Oak Zeng
3a68a638a9 drm/amdkfd: Change arcturus sdma engines number
Arcturus has 8 sdma engines

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Yong Zhao <yong.zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Yong Zhao
a23e72d7e9 drm/amdkfd: Support two MMHUBs when setting up page table base in KFD
2 mmhubs on arcturus.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Yong Zhao
6d5311ab2c drm/amdkfd: Expose function mmhub_v9_4_setup_vm_pt_regs() for kfd to use
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:04 -05:00
Yong Zhao
49adcf8a6f amd/amdkfd: Add ASIC ARCTURUS to kfd
Add initial support for ARCTURUS to kfd.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Oak Zeng
2fb1e49fda drm/amdkfd: Support bigger gds size
Extend map_process and set_resources pm4 packet to support
bigger gds size for arcturus.

v2: Only make the change for v9

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Oak Zeng
3a65d14d25 drm/amdkfd: Extend PM4 packets to support 8 SDMA
Extend map_queue and unmap_queue PM4 packets to support 8
SDMA engines. The new format is backward compatible.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Oak Zeng
7f40581c2e drm/amdgpu: Initialize asic functions for Arcturus
After cherry-picking doorbell rework changes from drm-next
branch, Arcturus asic functions pointer need to be initialized
to init doorbell index for Arcturus.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
f864e3e655 drm/amdgpu: add paging queue support for 8 SDMA instances on Arcturus
Properly enable all 8 instances for paging queue.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
f9c84ae582 drm/amdgpu: correct programming of ih_chicken for Arcturus
ih_chicken is a register that is not allowed to access by driver
in the L0 security policy.
psp bl need to enable field to allow driver to use physical
bus address for ih ring on secure part.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Snow Zhang <snow.zhang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
5ce40fd86c drm/amdgpu: add Arcturus chip_name for init sdma microcode
So we load the proper firmware for arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
121d859918 drm/amdgpu: enable 8 SDMA instances for Arcturus
All the 8 SDMA instances work fine on the latest Gopher build model.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Snow Zhang <Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
5cd54ab85d drm/amdgpu: correct Arcturus SDMA address space base index
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
3d81f67a1b drm/amdgpu: support sdma 2~7 doorbell range register offset
Update the doorbell range registers to support additional
SDMA rings.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
f5cdc2da46 drm/amdgpu: skip all gfx ring settings for Arcturus
Not needed on Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
f8b733b9d4 drm/amdgpu: skip load cp gfx firmware for Arcturus
Arcturus has no CPG component any more.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
24c44c8917 drm/amdgpu: optimize gfx9 init_microcode function
Split each type of firmware into single function for easy to maintain.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
65e60f6e06 drm/amdgpu: add Arcturus gpu info firmware
Add GPU info firmware for Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
f2d6657111 drm/amdgpu: skip pasid mapping for second mmhub on Arcturus
There's no LUT register for second mmhub to convert pasid since it has no ATC.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
2065aa5494 drm/amdgpu: skip to get 3D engine clockgating state for Arcturus
It's because Arcturus has not 3D engine.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
2564444f8c drm/amdgpu: add to set rlc funcs for Arcturus
Shared with other gfx9 parts so use the same functions.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
763bee0fb3 drm/amdgpu: add number of mec for Arcturus
MEC is the CP compute microcontroller.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:03 -05:00
Le Ma
6155e98ac0 drm/amdgpu: add gfx config for Arcturus
Add Arcturus GFX config.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
84519350a7 drm/amdgpu: add support for Arcturus firmware
Add support for Arcturus gfx firmwares.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
9f6ef81620 drm/amdgpu/dce_virtual: add Arcturus virtual display support
Virtual dce is a sw only display driver for emulation and
virtualization and cases where we want to use a virtual
display subsystem.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
7fafd613c0 drm/amdgpu: set Arcturus fw load type as direct
We currently only support direct firmware loading.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
61cf44c1db drm/amdgpu: add to set Arcturus ip blocks
Add IP blocks for Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
0e54df0572 drm/amdgpu/soc15: add Arcturus common ip blocks
Add common IP blocks for Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
0fe6a7b49f drm/amdgpu: support hdp flush for more sdma instances
The bit RSVD_ENG0 to RSVD_ENG5 in GPU_HDP_FLUSH_REQ/GPU_HDP_FLUSH_DONE
can be leveraged for sdma instance 2~7 to poll register/memory.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
b482a134ad drm/amdgpu: specify sdma instance 5~7 with second mmhub type
On Arcturus, sdma instance 5~7 is connected to the second mmhub. The vmhub type
in amdgpu_ring_funcs is constant, so we create an individual amdgpu_ring_funcs
with different vmhub type(AMDGPU_MMHUB_1) for these sdma instances.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
667a48226e drm/amdgpu: reorganize sdma v4 code to support more instances
This change is needed for Arcturus which has 8 sdma instances.
The CG/PG part is not covered for now.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
51c608984f drm/amdgpu: update vmc interrupt routine to support 3 vmhubs
There is one more vmc interrupt and mmhub on Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
7d19b15f70 drm/amdgpu: add VMC1 interrupt client id for Arcturus
New IH client id for VMC1.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
e78705ec5a drm/amdgpu: dynamically initialize IP offset for Arcturus
Add support for the IP offsets on Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
113b47e780 drm/amdgpu: increase max number of ip base instances to 8
For Arcturus, the number of IP base instances is 8.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
fa5d2e6f0a drm/amdgpu: add SDMA 2~7 ip block type
Add IP block type.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
8024f1d5e1 drm/amdgpu: add SDMA 2~7 interrupt client id for Arcturus
Add new client ids.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
51cce480fd drm/amdgpu: use new mmhub interfaces for Arcturus
Arcturus has two MMHUBs.

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Snow Zhang < Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
2cb2ea1e07 drm/amdgpu: add mmhub v9.4.1 block for Arcturus (v2)
Arcturus as an updated mmhub block. mmhub is the
memory controller hub used for sdma and multimedia.

v2: squash in AGP BAR programming (Alex)

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
c8a6e2a317 drm/amdgpu: add one more mmhub instance for Arcturus (v2)
v2: set mmhub num under CHIP_ARCTURUS switch case and add one more mmhub id_mgr

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:02 -05:00
Le Ma
1daa2bfa17 drm/amdgpu: add new member in amdgpu_device for vmhub counts per asic chip
It aims to replace AMDGPU_MAX_VMHUBS in for loop to initialize registers.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Le Ma
a2d15ed733 drm/amdgpu: rename AMDGPU_GFXHUB/MMHUB macro with hub number
The number of GFXHUB/MMHUB may be expanded in later ASICs.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Le Ma
3de2ff5d60 drm/amdgpu: add gmc basic support for Arcturus
Add initial GMC support for Arcturus

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Le Ma
d6c3b24ea2 drm/amdgpu: add Arcturus asic type
Add asic type for Arcturus.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Le Ma
f1cf876931 drm/amdgpu: add Arcturus ip_offset header (v3)
Provides the absolute offsets of the IP register
blocks.

v2: update chip name in source code
v3: squash in MP offset updates (Alex)

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Leo Liu
c54a60db0d drm/amdgpu: add VCN2.5 headers
VCN is the multi-media block.

Signed-off-by: Leo Liu <leo.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Le Ma
4f727ecefe drm/amdgpu: add sdma 4.2.2 header files for Arcturus
SDMA is the system DMA block.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Le Ma
0e96cf7f67 drm/amdgpu: add mmhub 9.4.1 header files for Acrturus
mmhub is the GPU memory hub used by SDMA and VCN.

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Alex Deucher
d1daf8502e drm/amdgpu: consolidate navi14 IP init
It's the same as navi10.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Alex Deucher
2665ec4171 drm/amdgpu: disable concurrent flushes on Navi14
Same thing applies to navi14 as navi10.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Jack Xiao
ba02636de5 drm/amdgpu: enable gfxoff code path for navi14
Based on navi10 gfxoff logic, enable the related code
path for navi14.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Xiaojie Yuan
0377b08823 drm/amdgpu/vcn: enable indirect DPG SRAM mode for navi14
Enable VCN dynamic powergating for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Xiaojie Yuan
e017bb8035 drm/amd/powerplay: disable gfxoff for navi14
gfxoff doesn't work on navi14 yet, so disable it for now

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:01 -05:00
Xiaojie Yuan
03917df7e5 drm/amdgpu/nv: set vcn pg flag for navi14
Enable VCN power gating by default.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
c5cc14e34d drm/amd/display: disable display writeback for navi14
not used.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
5e0f378d8a drm/amdgpu: enable async gfx ring for navi14
Same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
d0c39f8cbf drm/amdgpu: enable clock gatings for navi14
Set appropriate CG flags for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
29e6fd7c86 drm/amdgpu/athub2: set clock gating for navi14
same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
408c49de9b drm/amdgpu/mmhub2: set clock gating for navi14
same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
8687b47e3a drm/amdgpu: declare asd firmware for navi14
So the dependency gets properly tracked.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Snow Zhang <snow.zhang@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
James Zhu
e149a2f6ed drm/amdgpu: Enable VCN on navi14
Add navi14 vcn firmware, and enable VCN on navi14.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
baebcf2e91 drm/amd/display: skip to load dmcu firmware for navi14
not needed for navi14 at the moment.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
e470d287c3 drm/amdgpu: skip to load ta firmware for navi14
Not relevant on navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Bhawanpreet Lakha
c6e764b40a drm/amd/display: add ASICREV defines v2
Add revs for navi10 and 14.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Bhawanpreet Lakha
8fceceb69e drm/amd/display: add dm block
enable DC for navi14.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Bhawanpreet Lakha
2ebe177344 drm/amd/display: add NAVI14 in resource construct
Change the pipes to 5 if the asic is nv14

This is a temp patch, there was some refactor in the dml part of the code.
which is not in this branch. for now this is good, we can implement this
properly once we have an updated branch.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Bhawanpreet Lakha
fce651e393 drm/amd/display: add nv14 cases to amdgpu_dm
Mostly shared with navi10.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
ab5e51211c drm/amdgpu: enable sw smu ip for navi14
same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
b02ff12689 drm/amdgpu/smu11: add support for navi14
Same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
7840d8babe drm/amdgpu/psp: start rlc autoload after psp received rlcg for navi14
Update for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
4adc0732fc drm/amdgpu: enable psp ip block for navi14
Same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Snow Zhang <Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:18:00 -05:00
Xiaojie Yuan
82522b2d7f drm/amdgpu/psp: add psp support for navi14 (v3)
Same as navi10.

v2: squash in logic fix (Colin Ian King)
v3: squash in logic simplification (Alex)

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Snow Zhang <Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
691f69b6a6 drm/amdgpu: enable virtual display for navi14
Virtual display is a sw based kms interface for virtualization
and emulation.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
a29bfd1283 drm/amdgpu: add ip blocks for navi14
Add the initial IP blocks for navi14

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
5e71e011ff drm/amdgpu/soc15: add support for navi14
same as navi10

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Jack Xiao
b8cb98cd3e drm/amdgpu/gfx10: fix programming of SC_HIZ_TILE_FIFO_SIZE field
max fifo size is 128 and PA_SC_FIFO_SIZE[20:15]=SC_HIZ_TILE_FIFO_SIZE
field is programmed in units of two entries, but 6 bits is insufficient
to hold value 128/2 = 64, so set this field as 0 which is interpreted by
the hardware as maximum physical fifo size(128).

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Tao Zhou
3ddec51511 drm/amdgpu/gfx10: update gfx golden settings for navi14
Updated settings from hw team.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
4904ede127 drm/amdgpu/gfx10: update gfx golden settings for navi14
Add updated settings from hw team.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
be184b4ccc drm/amdgpu/gfx: update gc_v10_1_1 golden setting
Updated settings for hw team.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
7417846725 drm/amdgpu/gfx10: add gfx v10_1_1 golden settings for navi14
Add golden settings for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Snow Zhang <Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
58acab6629 drm/amdgpu/gfx: add definition of mmCGTT_GS_NGG_CLK_CTRL
Needed for clockgating.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
d55c193dbd drm/amdgpu/gfx10: set tcp harvest for navi14
Update settings for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
e938ded648 drm/amdgpu: set rlc funcs for navi14
Same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
0c090023c6 drm/amdgpu: add me/mec configurations for navi14
Add navi14 to appropriate cases.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
41957a8ea9 drm/amdgpu/gfx10: add clockgating support for navi14
Same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
4bd80a4663 drm/amdgpu/gfx10: add gfx config for navi14
Add gfx config details for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
47b67bd7d4 drm/amdgpu/gfx10: add placeholder for navi14 golden settings
To be filled in once available.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
654bcee0e4 drm/amdgpu/gfx10: add support for navi14 firmware
Add support for navi14 CP firmware files.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
Xiaojie Yuan
9571710f0c drm/amdgpu/sdma5: set clock gating for navi14
same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:59 -05:00
tiancyin
a994b742b8 drm/amdgpu/sdma5: update sdma5 golden settings for navi14
add new registers:
	mmSDMA0_RLC3_RB_WPTR_POLL_CNTL,
	mmSDMA1_RLC3_RB_WPTR_POLL_CNTL

Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: tiancyin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
c049af3e85 drm/amdgpu/sdma5: add sdma5_0 golden settings for navi14
Add settings for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Snow Zhang <Snow.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
06823925ad drm/amdgpu/sdma5: add placeholder for navi14 golden settings
To be filled in once they are available.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
6041f2a281 drm/amdgpu/sdma5: add support for navi14 firmware
Add support for navi14 sdma firmware files.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
05d72b8d36 drm/amdgpu/gmc10: add navi14 support
same as navi10

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
c8ff09bf41 drm/amdgpu: increase max instance number for hw ip
max instance number is 6 for navi10 and 7 for navi14, and we increase the
reg_offset array size to avoid out-of-bound access

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
c20697674d drm/amdgpu/discovery: init reg base offset via ip discovery for navi14
Add IP discovery for navi14.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
a0f6d926f1 drm/amdgpu/soc15: initialize reg base for navi14 (v2)
Initialize the IP register base offsets for navi14.

v2: squash in MP, CLK, THM updates

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
e2d2607f90 drm/amdgpu: add navi14 ucode loading method
Same as navi10.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
7ecb5cd451 drm/amdgpu: set asic family and ip blocks for navi14
same with navi10

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
ed42cfe1ac drm/amdgpu: add gpu_info firmware for navi14
Add navi14 to case statement to load the GPU info firmware.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Xiaojie Yuan
87dbad02d2 drm/amdgpu: add navi14 asic type
Add CHIP_NAVI14 to the list of asic types.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:58 -05:00
Dale Zhao
b70666934b drm/amd/display: handle active dongle port type is DP++ or DP case
[Why]:
Some active dongles have DP++ port and DP port at the same time. Current
code doesn't cover DP++ case and processes as default DVI case, in which
audio is disabled. Because of dual mode, DP case is also treat as DVI case
for the other port.

[How]:
According DP 1.4 spec, add DP++ procedure similar with HDMI case. Also
add None dongle type for DP case.

Signed-off-by: Dale Zhao <dale.zhao@amd.com>
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:20 -05:00
Eric Yang
b791f9dc2d drm/amd/display: do not read link setting if edp not connected
[Why]
Previously assume eDP sink present if connector present. Do not
need to enforce this restriction. Fix issue where driver attempt
to read link setting even though no edp connected.

{How]
Only read link setting after reading connection status.

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:20 -05:00
Tai Man
7352193a33 drm/amd/display: Increase size of audios array
[Why]
The audios array defined in "struct resource_pool" is only 6 (MAX_PIPES)
but the max number of audio devices (num_audio) is 7. In some projects,
it will run out of audios array.

[How]
Incraese the audios array size to 7.

Signed-off-by: Tai Man <taiman.wong@amd.com>
Reviewed-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:20 -05:00
Zhan Liu
58caae27df drm/amd/display: drop ASSERT() if eDP panel is not connected
[Why]
For boards that support eDP but do not have a physical eDP
display connected an ASSERT will be thrown. This is not a
critical failure and shouldn't be treated as such.

[How]
Drop the assertion.

Signed-off-by: Zhan Liu <zhan.liu@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:20 -05:00
Alvin Lee
6ac25e6d5b drm/amd/display: Only enable audio if speaker allocation exists
[Why]

In dm_helpers_parse_edid_caps, there is a corner case where no speakers
can be allocated even though the audio mode count is greater than 0.
Enabling audio when no speaker allocations exists can cause issues in
the video stream.

[How]

Add a check to not enable audio unless one or more speaker allocations
exist (since doing this can cause issues in the video stream).

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:20 -05:00
Julian Parkin
0905f32977 drm/amd/display: Fix dc_create failure handling and 666 color depths
[Why]
It is possible (but very unlikely) that constructing dc fails
before current_state is created.

We support 666 color depth in some scenarios, but this
isn't handled in get_norm_pix_clk. It uses exactly the
same pixel clock as the 888 case.

[How]
Check for non null current_state before destructing.

Add case for 666 color depth to get_norm_pix_clk to
avoid assertion.

Signed-off-by: Julian Parkin <julian.parkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:20 -05:00
Derek Lai
67fd6c0d2d drm/amd/display: allocate 4 ddc engines for RV2
[Why]
Driver will create 0, 1, and 2 ddc engines for RV2,
but some platforms used 0, 1, and 3.

[How]
Still allocate 4 ddc engines for RV2.

Signed-off-by: Derek Lai <Derek.Lai@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Eric Yang
feb7eb522e drm/amd/display: put back front end initialization sequence
[Why]
Seamless boot optimization removed proper front end power off sequence.
In driver disable enable case, this causes driver to power gate hubp
and dpp while there is still memory fetching going on, this can cause
invalid memory requests to be generated which will hang data fabric.

[How]
Put back proper front end power off sequence

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Tony Cheng <Tony.Cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Alvin Lee
39fee5f60c drm/amd/display: Wait for flip to complete
[why]
In pipe split issue occurs when we program immediate flip while vsync flip is pending

[how]
Don't program immediate flip until flip is no longer pending

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jaehyun Chung <Jaehyun.Chung@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Fatemeh Darbehani
09fc26c171 drm/amd/display: Change min_h_sync_width from 8 to 4
[Why]
Some display's hsync width is lower than the minimum dcn20 is set
to support right now. This will cause optc1_validate_timing to fail which
eventually will result in wrong set mode. This was set to 8 as per
HW team's request for no valid reason.

[How]
Changing min_h_sync_width to 4 will let us validate timing for
preffered mode and light up the headset. This change was made
to Vega 10 before for a similar issue.

Signed-off-by: Fatemeh Darbehani <fatemeh.darbehani@amd.com>
Reviewed-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Tai Man
74eda776d7 drm/amd/display: use encoder's engine id to find matched free audio device
[Why]
On some platforms, the encoder id 3 is not populated. So the encoders
are not stored in right order as index (id: 0, 1, 2, 4, 5) at pool. This
would cause encoders id 4 & id 5 to fail when finding corresponding
audio device, defaulting to the first available audio device. As result,
we cannot stream audio into two DP ports with encoders id 4 & id 5.

[How]
It need to create enough audio device objects (0 - 5) to perform matching.
Then use encoder engine id to find matched audio device.

Signed-off-by: Tai Man <taiman.wong@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Zi Yu Liao
1ca068ed34 drm/amd/display: fix DMCU hang when going into Modern Standby
[why]
When the system is going into suspend, set_backlight gets called
after the eDP got blanked. Since smooth brightness is enabled,
the driver will make a call into the DMCU to ramp the brightness.
The DMCU would try to enable ABM to do so. But since the display is
blanked, this ends up causing ABM1_ACE_DBUF_REG_UPDATE_PENDING to
get stuck at 1, which results in a dead lock in the DMCU firmware.

[how]
Disable brightness ramping when the eDP display is blanked.

Signed-off-by: Zi Yu Liao <ziyu.liao@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Alvin Lee
19f876967a drm/amd/display: Disable Audio on reinitialize hardware
[Why]
When we recover from hang, we do not want to skip the audio enable call.

[How]
Disable audio in dc_reinitialize_hardware

Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Derek Lai
12d0e503dd drm/amd/display: Read max down spread
[Why]
When launch D10.2, driver will write DPCD 0x107 with 0x00

[How]
Read MAX_DOWNSPREAD (0x0003h) then keep in current
link settings

Signed-off-by: Derek Lai <Derek.Lai@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Ilya Bakoulin
288af96df1 drm/amd/display: Check for valid stream_encode
Before accessing it's vtable, check that stream_encoder is non-null.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
SivapiriyanKumarasamy
c7990daebe drm/amd/display: Wait for backlight programming completion in set backlight level
[WHY]
Currently we don't wait for blacklight programming completion in DMCU
when setting backlight level. Some sequences such as PSR static screen
event trigger reprogramming requires it to be complete.

[How]
Add generic wait for dmcu command completion in set backlight level.

Signed-off-by: SivapiriyanKumarasamy <sivapiriyan.kumarasamy@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Julian Parkin
ca6f188cdf drm/amd/display: Poll for GPUVM context ready (v2)
[Why]
Hardware docs state that we must wait until the GPUVM context is ready
after programming it.

[How]
Poll until the valid bit of PAGE_TABLE_BASE_ADDR_LO32 is set to 1 after
programming it.

v2: fix include for udelay (Alex)

Signed-off-by: Julian Parkin <julian.parkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Wenjing Liu
dd5d9348da drm/amd/display: wait for the whole frame after global unlock
[why]
The current code will not wait for the entire frame
 after global unlock.
This causes dsc dynamic target bpp update corruption when
there is a surface update immediately happens after this.

[how]
Wait for the entire whole frame after unlock before continuing
the rest of stream and surface update.

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Nicholas Kazlauskas
7f6964c5a0 drm/amd/display: Copy max_clks_by_state after dce_clk_mgr_construct
[Why]
For DCE110, DCE112 and DCE120 the max_clks_by_state for the clk_mgr are
copied from their respective table before the call to
dce_clk_mgr_construct, but then dce_clk_mgr_construct overwrites
these with the dce80_max_clks_by_state.

[How]
Copy these after we call dce_clk_mgr_construct so we're using the
right tables.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Murton Liu
492d9ec244 drm/amd/display: Clock does not lower in Updateplanes
[why]
We reset the optimized_required in atomic_plane_disable
flag immediately after it is set in atomic_plane_disconnect, causing us to
never have flag set during next flip in UpdatePlanes.

[how]
Optimize directly after each time plane is removed.

Signed-off-by: Murton Liu <murton.liu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Samson Tam
4fc1609bcd drm/amd/display: skip retrain in dc_link_set_preferred_link_settings() if using passive dongle
[Why]
Fixes issue when we have a display connected using a passive
dongle and then emulate over it using a DP connection at 1 x 1.62 Ghz.
System hangs because register bus returns back 0xFFFFFFFF for all
register reads after setting register DIG_BE_CNTL in
dcn10_link_encoder_connect_dig_be_to_fe().  Hang occurs later
when trying to do a register read.

[How]
At the start of the emulation, dc_link_set_preferred_link_settings()
and dp_retrain_link_dp_test() is called, even though it is connected
using a passive dongle.

Add an extra condition in dp_retrain_link_dp_test() to check for
link->dongle_max_pix_clk > 0.  This is the only way we know if the
connection is using passive dongle so we don't retrain DP.

Signed-off-by: Samson Tam <Samson.Tam@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Jun Lei
4a876eecf6 drm/amd/display: swap system aperture high/low
[why]
Currently logical values are swapped in HW, causing
system aperture to be undefined, so VA and PA cannot co-exist

[how]
program values correctly

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:19 -05:00
Nikola Cornij
61011e63f8 drm/amd/display: Set one 4:2:0-related PPS field as recommended by DSC spec
[why]
'second_line_offset_adj' was mistakenly left at zero, even though DSC spec
v1.2a recommends setting this field to 512 for 4:2:0.

[how]
Set 'second_line_offset_adj' to 512 for 4:2:0 and leave at zero otherwise

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Dmytro Laktyushkin
90bbf6374b drm/amd/display: Set default block_size, even in unexpected cases
We're not expected to enter the default case, but not returning a
default value here is incorrect.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Harmanprit Tatla
5b25e5f1a9 drm/amd/display: No audio endpoint for Dell MST display
[Why]
There are certain MST displays (i.e. Dell P2715Q)
that although have the MST feature set to off may still
report it is a branch device and a non-zero
value for downstream port present.
This can lead to us incorrectly classifying a
dp dongle connection as being active and
disabling the audio endpoint for the display.

[How]
Modified the placement and
condition used to assign
the is_branch_dev bit.

Signed-off-by: Harmanprit Tatla <harmanprit.tatla@amd.com>
Reviewed-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Jun Lei
db31af12a5 drm/amd/display: cap DCFCLK hardmin to 507 for NV10
[why]
Due to limitation in SMU/PPLIB, it is not possible to know Fmax @ Vmin for DCFCLK.
This causes issues at high display configurations where extra headroom of DCFCLK
can enable P-state switching

[how]
Use existing override logic.  If override not defined, then force
min = 507

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Dmytro Laktyushkin
5d109be38b drm/amd/display: fix dsc disable
A regression caused dsc to never get disabled in certain situations.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Jun Lei
0bd8ac7ed5 drm/amd/display: fix up HUBBUB hw programming for VM
[why]
Some values were not being converted or bit-shifted properly for
HW registers, causing black screen

[how]
Fix up the values before programming HW

Signed-off-by: Jun Lei <jun.lei@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Jun Lei
61f33f6aa8 drm/amd/display: initialize p_state to proper value
[why]
On some modes SMU will be in infinite loop state at boot, this is
because driver assumes p_state_support is false, but this is the
opposite of the assumed boot state by SMU.  we optimize away
notifying SMU about no pstate, and so they will get stuck

[how]
when we init clk manager, init pstate to true, so it matches driver load
assumption

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Leo Liu
c6d5245d41 drm/amdgpu: use VCN firmware offset for cache window
Since we are using the signed FW now, and also using PSP firmware loading,
but it's still potential to break driver when loading FW directly
instead of PSP, so we should add offset.

Signed-off-by: Leo Liu <leo.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Kevin Wang
1a195ed5f1 drm/amd/powerplay: change sysfs pp_dpm_xxx format for navi10
v2:
set average clock value on level 1 when current clock equal
min or max clock (fine grained dpm support).

the navi10 gfxclk (sclk) support fine grained DPM,
so use level 1 to show current dpm freq in sysfs pp_dpm_xxx

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Hawking Zhang
578a4daa1c drm/amdgpu: drop ras self test
this function is not needed any more. error injection is
the only way to validate ras but it can't be executed in
amdgpu_ras_init, where gpu is even not initialized

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Hawking Zhang
29bd650809 drm/amdgpu: only allow error injection to UMC IP block
error injection to other IP blocks (except UMC) will be enabled
until RAS feature stablize on those IP blocks

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Hawking Zhang
59d9c0ab71 drm/amdgpu: disable GFX RAS by default
GFX RAS has not been stablized yet. disable GFX ras until
it is fully funcitonal.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Hawking Zhang
5f872b723a drm/amdgpu: do not create ras debugfs/sysfs node for ASICs that don't have ras ability
driver shouldn't init any ras debugfs/sysfs node for ASICs that don't have ras
hardware ability

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
Evan Quan
23d66e75d7 drm/amd/powerplay: report bootup clock as max supported on dpm disabled
With gfxclk or uclk dpm disabled, it's reasonable to report bootup clock
as the max supported.

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>
2019-07-18 14:17:18 -05:00
Joseph Greathouse
ad28e02420 drm/amdgpu: Default disable GDS for compute VMIDs
The GDS and GWS blocks default to allowing all VMIDs to
access all entries. Graphics VMIDs can handle setting
these limits when the driver launches work. However,
compute workloads under HWS control don't go through the
kernel driver. Instead, HWS firmware should set these
limits when a process is put into a VMID slot.

Disable access to these devices by default by turning off
all mask bits (for OA) and setting BASE=SIZE=0 (for GDS
and GWS) for all compute VMIDs. If a process wants to use
these resources, they can request this from the HWS
firmware (when such capabilities are enabled). HWS will
then handle setting the base and limit for the process when
it is assigned to a VMID.

This will also prevent user kernels from getting 'stuck' in
GWS by accident if they write GWS-using code but HWS
firmware is not set up to handle GWS reset. Until HWS is
enabled to handle GWS properly, all GWS accesses will
MEM_VIOL fault the kernel.

v2: Move initialization outside of SRBM mutex

Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:17:18 -05:00
hersen wu
41a5a2a853 drm/amd/display: init res_pool dccg_ref, dchub_ref with xtalin_freq
[WHY] dc sw clock implementation of navi10 and raven are not exact the
same. dcccg, dchub reference clock initialization is done after dc calls
vbios dispcontroller_init table. for raven family, before
dispcontroller_init is called by dc, the ref clk values are referred
by sw clock implementation and program asic register using wrong
values. this causes dchub pstate error. This need provide valid ref
clk values. for navi10, since dispcontroller_init is not called,
dchubbub_global_timer_enable = 0, hubbub2_get_dchub_ref_freq will
hit aeert. this need remove hubbub2_get_dchub_ref_freq from this
location and move to dcn20_init_hw.

[HOW] for all asic, initialize dccg, dchub ref clk with data from
vbios firmware table by default. for raven asic family, use these data
from vbios, for asic which support sw dccg component, like navi10,
read ref clk by sw dccg functions and update the ref clk.

Signed-off-by: hersen wu <hersenxs.wu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:12:08 -05:00
Alex Deucher
8a5b5d425e drm/amdgpu/pm: remove check for pp funcs in freq sysfs handlers
The dpm sensor function already does this for us.  This fixes
the freq*_input files with the new SMU implementation.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:11:47 -05:00
Nicholas Kazlauskas
02316e963a drm/amd/display: Force uclk to max for every state
Workaround for now to avoid underflow.

The uclk switch time should really be bumped up to 404, but doing so
would expose p-state hang issues for higher bandwidth display
configurations.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-18 14:11:47 -05:00
Joseph Greathouse
6a5d487754 drm/amdkfd: Remove GWS from process during uninit
If we shut down a process without having destroyed its GWS-using
queues, it is possible that GWS BO will still be in the process
BO list during the gpuvm destruction. This list should be empty
at that time, so we should remove the GWS allocation at the
process uninit point if it is still around.

Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:31 -05:00
Tom St Denis
88891430a2 drm/amd/amdgpu: Fix offset for vmid selection in debugfs interface
The register debugfs interface was using the wrong bitmask for vmid
selection for GFX_CNTL.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:30 -05:00
Evan Quan
cd6e0c4ba1 drm/amd/powerplay: update vega20 driver if to fit latest SMU firmware
Optimization for the socket power calculation is introduced.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:30 -05:00
Evan Quan
93002849ff drm/amd/powerplay: maintain SMU FW backward compatibility
Do not halt driver loading on if_version mismatch. As our
driver and FWs are backward compatible.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:30 -05:00
Evan Quan
0d9d78b57b drm/amd/powerplay: correct smu_update_table usage
The interface was used in a confusing way. In profile mode scenario,
the 2nd parameter of the interface was used in a different way from
other scenarios.

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>
2019-07-17 13:34:30 -05:00
Evan Quan
f68ccf43ac drm/amd/powerplay: fix deadlock around smu_handle_task V2
As the lock was already held on the entrance to smu_handle_task.

- V2: lock in small granularity

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:30 -05:00
Evan Quan
7ef65bbd01 drm/amd/powerplay: avoid access before allocation
No access before allocation.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:30 -05:00
Evan Quan
366cf03ec0 drm/amd/powerplay: fix memory allocation failure check V2
Fix memory allocation failure check.

- V2: fix one more similar error

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>
2019-07-17 13:34:30 -05:00
Felix Kuehling
67adb569dd drm/amdgpu: Fix silent amdgpu_bo_move failures
Under memory pressure, buffer moves between RAM to VRAM  can
fail when there is no GTT space available. In those cases
amdgpu_bo_move falls back to ttm_bo_move_memcpy, which seems to
succeed, although it doesn't really support non-contiguous or
invisible VRAM. This manifests as VM faults with corrupted page
table entries in KFD eviction stress tests.

Print some helpful messages when lack of GTT space is causing buffer
moves to fail. Check that source and destination memory regions are
supported by ttm_bo_move_memcpy before taking that fallback.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:30 -05:00
Alex Deucher
6ea624f603 drm/amdgpu: drop dead header
Not used anymore.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Noticed-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-17 13:34:20 -05:00
Nathan Chancellor
d72e04d97e drm/amd/powerplay: Use proper enums in vega20_print_clk_levels
clang warns:

drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:995:39: warning:
implicit conversion from enumeration type 'PPCLK_e' to different
enumeration type 'enum smu_clk_type' [-Wenum-conversion]
                ret = smu_get_current_clk_freq(smu, PPCLK_SOCCLK, &now);
                      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:1016:39: warning:
implicit conversion from enumeration type 'PPCLK_e' to different
enumeration type 'enum smu_clk_type' [-Wenum-conversion]
                ret = smu_get_current_clk_freq(smu, PPCLK_FCLK, &now);
                      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:1031:39: warning:
implicit conversion from enumeration type 'PPCLK_e' to different
enumeration type 'enum smu_clk_type' [-Wenum-conversion]
                ret = smu_get_current_clk_freq(smu, PPCLK_DCEFCLK, &now);
                      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~

The values are mapped one to one in vega20_get_smu_clk_index so just use
the proper enums here.

Fixes: 0967610142 ("drm/amd/powerplay: support sysfs to get socclk, fclk, dcefclk")
Link: https://github.com/ClangBuiltLinux/linux/issues/587
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 14:49:57 -05:00
Nicolai Hähnle
08473888e0 drm/amdgpu/gfx10: set SH_MEM_CONFIG.INITIAL_INST_PREFETCH
Prefetch mode 0 is not supported and can lead to hangs with certain very
specific code patterns. Set a sound prefetch mode for all VMIDs rather
than forcing all shaders to set the prefetch mode at the beginning.

Reduce code duplication a bit while we're at it. Note that the 64-bit
address mode enum and the retry all enum are both 0, so the only
functional change is in the INITIAL_INST_PREFETCH field.

Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 14:49:57 -05:00
Kenneth Feng
597292eb73 drm/amd/powerplay: enable fw ctf,apcc dfll and gfx ss
enable fw ctf, apcc dfll and gfx ss on navi10.
fw ctf: when the fw ctf is triggered, the gfx and soc power domain
are shut down. fan speed is boosted to the maximum.
gfx ss: hardware feature, sanity check has been done.
apcc dfll: can check the scoreboard in smu fw to confirm if it's enabled.
no need to do further check since the gfx hardware control the frequency once
a pcc signal comes.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 14:49:57 -05:00
Hawking Zhang
f216994613 drm/amdgpu: check kdb_bin_size to exclude kdb loading sequence
The legacy navi10 sos binary will not carry on kdb image. the kdb_start_addr
is actually the start address of sys_drv image and shouldn't be sent to psp
bootloader.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 14:49:57 -05:00
Felix Kuehling
9288b874c5 drm/amdgpu: Fix unaligned memory copies
When starting a new mm_node, the page_offset becomes 0.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 14:49:36 -05:00
Wang Xiayang
3bd532692d drm/amdgpu: replace simple_strtol() by kstrtou32()
The simple_strtol() function is deprecated. kstrto[l,u32]() is
the correct replacement as it can properly handle overflows.

This patch replaces the deprecated simple_strtol() use introduced recently.
As clk is of type uint32_t, we are safe to use kstrtou32().

It is also safe to return zero on string parsing error,
similar to the case of returning zero if buf is empty in parse_clk().

Fixes: bb5a2bdf36 ("drm/amdgpu: support dpm level modification under virtualization v3")
Signed-off-by: Wang Xiayang <xywang.sjtu@sjtu.edu.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:09:09 -05:00
Fuqian Huang
5db7b0d290 drm/amdgpu: remove memset after kzalloc
kzalloc has already zeroed the memory during the allocation.
So memset is unneeded.

Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:09:05 -05:00
Arnd Bergmann
b5203d16ae drm/amd/amdgpu: hide #warning for missing DC config
It is annoying to have #warnings that trigger in randconfig
builds like

drivers/gpu/drm/amd/amdgpu/soc15.c:653:3: error: "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
drivers/gpu/drm/amd/amdgpu/nv.c:400:3: error: "Enable CONFIG_DRM_AMD_DC for display support on navi."

Remove these and rely on the users to turn these on.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:59 -05:00
Kent Russell
9417f703af drm/amdgpu: Fix Vega20 Perf counter for pcie_bw
The perf counter for Vega20 is 108, instead of 104 which it was on all
previous GPUs, so add a check to use the appropriate value.

Signed-off-by: Kent Russell <kent.russell@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:51 -05:00
Tom St Denis
ca9db7d1e0 drm/amd/amdgpu: Add missing select_me_pipe_q() for gfx10
The ability to select GFX GRBM me/pipe/queue/vmid was missing from
the gfx10 driver.  This patch adds it.  Used by the debugfs register
interface to select GFX resources when read/writing registers.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:44 -05:00
Tom St Denis
0fa4246e8e drm/amd/amdgpu: Add VMID to SRBM debugfs bank selection
Add 5 bits to the offset for SRBM selection to handle VMIDs.  Also
update the select_me_pipe_q() callback to also select VMID.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:38 -05:00
Kevin Wang
54728170e0 drm/amd/powerplay: add helper of smu_clk_dpm_is_enabled for smu
v2: change function name to smu_clk_dpm_is_enabled.
add this helper function to check dpm clk feature is enabled.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:23 -05:00
Kevin Wang
8e33376b76 drm/amd/powerplay: fix save dpm level error for smu
the save dpm level should be save previous dpm profile level,
should not modified by get dpm level function.
eg: default auto
1. auto -> standard ==> dpm_level = standard, save_dpm = auto.
2. standard -> auto ==> dpm_level = auto, save_dpm = standard.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:12 -05:00
Kevin Wang
42b3aa9a5b drm/amd/powerplay: avoid double check feature enabled
the unforce_dpm_levels doesn't need to check feature enablement.
because the smu_get_dpm_freq_range function has check feature logic.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:08:01 -05:00
Kevin Wang
75728f512e drm/amd/powerplay: add standard profile dpm support for smu
1. the standard dpm is not support before.
2. use auto profile to adapt standard profile.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:03:10 -05:00
Kevin Wang
eaf963b5c1 drm/amd/powerplay: add socclk profile dpm support.
1.miss socclk profile support when bringup.
2.add feature check for socclk.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:03:03 -05:00
Felix Kuehling
75ee64875e drm/amdkfd: Consistently apply noretry setting
Apply the same setting to SH_MEM_CONFIG and VM_CONTEXT1_CNTL. This
makes the noretry param no longer KFD-specific. On GFX10 I'm not
changing SH_MEM_CONFIG in this commit because GFX10 has different
retry behaviour in the SQ and I don't have a way to test it at the
moment.

Suggested-by: Christian König <Christian.Koenig@amd.com>
CC: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by : Shaoyun.liu < Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:02:55 -05:00
Arnd Bergmann
7a17c8ce33 drm/amd/display: return 'NULL' instead of 'false' from dcn20_acquire_idle_pipe_for_layer
clang complains that 'false' is a not a pointer:

drivers/gpu/drm/amd/amdgpu/../display/dc/dcn20/dcn20_resource.c:2428:10: error: expression which evaluates to zero treated as a null pointer constant of type 'struct pipe_ctx *' [-Werror,-Wnon-literal-null-conversion]
                return false;

Changing it to 'NULL' looks like the right thing that will shut up
the warning and make it easier to read, while not changing behavior.

Fixes: 7ed4e6352c ("drm/amd/display: Add DCN2 HW Sequencer and Resource")
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:02:51 -05:00
Arnd Bergmann
7e446b3c76 drm/amd/display: Support clang option for stack alignment
As previously fixed for dml in commit 4769278e5c ("amdgpu/dc/dml:
Support clang option for stack alignment") and calcs in commit
cc32ad8f55 ("amdgpu/dc/calcs: Support clang option for stack
alignment"), dcn20 uses an option that is not available with clang:

clang: error: unknown argument: '-mpreferred-stack-boundary=4'
scripts/Makefile.build:281: recipe for target 'drivers/gpu/drm/amd/amdgpu/../display/dc/dcn20/dcn20_resource.o' failed

Use the same trick that we have in the other two files.

Fixes: 7ed4e6352c ("drm/amd/display: Add DCN2 HW Sequencer and Resource")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-16 13:02:39 -05:00
Linus Torvalds
be8454afc5 drm main pull request for v5.3-rc1 (sans mm changes)
-----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJdLMSbAAoJEAx081l5xIa+udkP/iWr8mw44tWYb8Wuzc/aR91v
 02X/J4S9XTQttNn/1Gpq9ItTLMf0Gc08tk1wEBBHAWi/qGaGZS2al+rv0afeuuQa
 aFhQzioDi7K/YZt92iEJhdx7wVMyydICTg3INmYlSP7/FyzLp6gBQRGSJ1kX5mHZ
 qWsFZgUOH9V5evyB6fDMleDaqFOKfcwrD7XYwbOheL/HeYQSv5AYn3VBupBFQ76L
 0hclI5VzZQ5V0nnqRTNDQVA9Yl6NTl+2eXTn5vuBtwKXEI6JJw8eihZp2oZDXqfS
 L441w7wGbkRPzN5kjMZjs1ToPMTlMveR5kL6Sc+o3DT/HmIr1odeaSDXR/93UOLd
 z0CRJ6xMC8h1ThLNHp8UgbxCKqIwYPsY2wVqjsJt7lDY5jma7Yv2YJ9ocYGHN/sO
 DVHcU6ugbwvuC5wZZtVZl5J4hjnBZwNRGSVK+iM0tkjalgdEuSFehXT7eQ8SphF/
 yI5gD1xNEwGfZ4bvZ3u/QrDCcpUAgPIUYmxEa2tPJILQWOJ9O87yc0y9Z21k9Ef1
 9yDqrFV3sPqC2xj/0ufZG/18+Yt99Ykg1jQE3RGDwD/59KAeqPbOvqTKyVODV9jE
 qje6ScSIc2G0713uss2bcaD3k+rCB5YL2JkKrk5OWW/T2+n9T+JFaiNh7dnSFFcU
 gBKyeY24OyCDMwXrby0K
 =SI+Y
 -----END PGP SIGNATURE-----

Merge tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The biggest thing in this is the AMD Navi GPU support, this again
  contains a bunch of header files that are large. These are the new AMD
  RX5700 GPUs that just recently became available.

  New drivers:
   - ST-Ericsson MCDE driver
   - Ingenic JZ47xx SoC

  UAPI change:
   - HDR source metadata property

  Core:
   - HDR inforframes and EDID parsing
   - drm hdmi infoframe unpacking
   - remove prime sg_table caching into dma-buf
   - New gem vram helpers to reduce driver code
   - Lots of drmP.h removal
   - reservation fencing fix
   - documentation updates
   - drm_fb_helper_connector removed
   - mode name command handler rewrite

  fbcon:
   - Remove the fbcon notifiers

  ttm:
   - forward progress fixes

  dma-buf:
   - make mmap call optional
   - debugfs refcount fixes
   - dma-fence free with pending signals fix
   - each dma-buf gets an inode

  Panels:
   - Lots of additional panel bindings

  amdgpu:
   - initial navi10 support
   - avoid hw reset
   - HDR metadata support
   - new thermal sensors for vega asics
   - RAS fixes
   - use HMM rather than MMU notifier
   - xgmi topology via kfd
   - SR-IOV fixes
   - driver reload fixes
   - DC use a core bpc attribute
   - Aux fixes for DC
   - Bandwidth calc updates for DC
   - Clock handling refactor
   - kfd VEGAM support

  vmwgfx:
   - Coherent memory support changes

  i915:
   - HDR Support
   - HDMI i2c link
   - Icelake multi-segmented gamma support
   - GuC firmware update
   - Mule Creek Canyon PCH support for EHL
   - EHL platform updtes
   - move i915.alpha_support to i915.force_probe
   - runtime PM refactoring
   - VBT parsing refactoring
   - DSI fixes
   - struct mutex dependency reduction
   - GEM code reorg

  mali-dp:
   - Komeda driver features

  msm:
   - dsi vs EPROBE_DEFER fixes
   - msm8998 snapdragon 835 support
   - a540 gpu support
   - mdp5 and dpu interconnect support

  exynos:
   - drmP.h removal

  tegra:
   - misc fixes

  tda998x:
   - audio support improvements
   - pixel repeated mode support
   - quantisation range handling corrections
   - HDMI vendor info fix

  armada:
   - interlace support fix
   - overlay/video plane register handling refactor
   - add gamma support

  rockchip:
   - RX3328 support

  panfrost:
   - expose perf counters via hidden ioctls

  vkms:
   - enumerate CRC sources list

  ast:
   - rework BO handling

  mgag200:
   - rework BO handling

  dw-hdmi:
   - suspend/resume support

  rcar-du:
   - R8A774A1 Soc Support
   - LVDS dual-link mode support
   - Additional formats
   - Misc fixes

  omapdrm:
   - DSI command mode display support

  stm
   - fb modifier support
   - runtime PM support

  sun4i:
   - use vmap ops

  vc4:
   - binner bo binding rework

  v3d:
   - compute shader support
   - resync/sync fixes
   - job management refactoring

  lima:
   - NULL pointer in irq handler fix
   - scheduler default timeout

  virtio:
   - fence seqno support
   - trace events

  bochs:
   - misc fixes

  tc458767:
   - IRQ/HDP handling

  sii902x:
   - HDMI audio support

  atmel-hlcdc:
   - misc fixes

  meson:
   - zpos support"

* tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm: (1815 commits)
  Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next"
  Revert "mm: adjust apply_to_pfn_range interface for dropped token."
  mm: adjust apply_to_pfn_range interface for dropped token.
  drm/amdgpu/navi10: add uclk activity sensor
  drm/amdgpu: properly guard the generic discovery code
  drm/amdgpu: add missing documentation on new module parameters
  drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback
  drm/amd/display: avoid 64-bit division
  drm/amdgpu/psp11: simplify the ucode register logic
  drm/amdgpu: properly guard DC support in navi code
  drm/amd/powerplay: vega20: fix uninitialized variable use
  drm/amd/display: dcn20: include linux/delay.h
  amdgpu: make pmu support optional
  drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent
  drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq
  drm/amd/powerplay: Use memset to initialize metrics structs
  drm/amdgpu/mes10.1: Fix header guard
  drm/amd/powerplay: add temperature sensor support for navi10
  drm/amdgpu: fix scheduler timeout calc
  drm/amdgpu: Prepare for hmm_range_register API change (v2)
  ...
2019-07-15 19:04:27 -07:00
Kevin Wang
64974ab249 drm/amd/powerplay: add pstate mclk(uclk) support for navi10
add pstate mclk(uclk) support.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-12 08:00:10 -05:00
Kevin Wang
d36893362d drm/amd/powerplay: fix smu clock type change miss error
in the smu module, use the smu_xxxclk type to identify the CLK type
use SMU_SCLK, SMU_MCLK to replace PP_SCLK, PP_MCLK.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-12 08:00:10 -05:00
Hawking Zhang
4298935924 drm/amdgpu: support key database loading for navi10
Starting from navi10, driver should send Key Database Load command
to bootloader before loading sys_drv and sos

Signed-off-by: John Clements <John.Clements@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-12 08:00:10 -05:00
Hawking Zhang
3840fe256a drm/amdgpu: switch to macro for psp bootloader command
The command will be sent to psp bootloader from driver
to ask psp bootloader to exerise tOS, sys_drv and kdb loading

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-12 08:00:10 -05:00
Paul Menzel
5f0f531c4f drm/amdgpu: Print out voltage in DM_PPLIB
As the clock is already logged, also log the voltage.

Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 22:04:22 -05:00
Nicholas Kazlauskas
6ce8f31667 drm/amd/display: Add drm_audio_component support to amdgpu_dm
[Why]
The drm_audio_component can be used to give pin ELD notifications
directly to the sound driver. This fixes audio endpoints disappearing
due to missing unsolicited notifications.

[How]
Send the notification via the audio component whenever we enable or
disable audio state on a stream. This matches what i915 does with
their drm_audio_component and what Takashi Iwai's proposed hack for
radeon/amdpgu did.

This is a bit delayed in when the notification actually occurs, however.
We wait until after all the programming is complete rather than sending
the notification mid sequence.

Particular care is needed for the get ELD callback since it can happen
outside the locking and fencing DRM does for atomic commits.

Cc: Leo Li <sunpeng.li@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:24 -05:00
Nicholas Kazlauskas
5fdb7c4c7f drm/amd/display: Expose audio inst from DC to DM
[Why]
In order to give pin notifications to the sound driver from DM we need
to know whether audio is enabled on a stream and what pin it's using
from DC.

[How]
Expose the instance via stream status if it's a mapped resource for
the stream. It will be -1 if there's no audio mapped.

Cc: Leo Li <sunpeng.li@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:24 -05:00
Eric Huang
70df8273ca drm/amdkfd: fix cp hang in eviction
The cp hang occurs in OCL conformance test only on supermicro
platform which has 40 cores and the test generates 40 threads.
The root cause is race condition in non-protected flags.

The fix is to add flags of is_evicted and is_active(init_mqd())
into protected area.

Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:24 -05:00
Alex Deucher
63e2fef631 drm/amdgpu: enable IP discovery by default on navi
Use the IP discovery table rather than hardcoding the
settings in the driver.

Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:24 -05:00
tiancyin
a349b39253 drm/amdgpu/discovery: fix DCE_HWIP mapping error in hw_id_map array
ID of DCE_HWIP from vbios is DMU_HWID,
mismatch cause null pointer crash in navi10 modprobe.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: tiancyin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:24 -05:00
Kenneth Feng
a54166d79a drm/amd/powerplay: bug fix for sysfs
when we set profile_peak to sysfs:power_dpm_force_performance_level,
we gets the wrong socclk level and mclk level.this patch fix this issue.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:23 -05:00
Evan Quan
617a64dc85 drm/amd/powerplay: increase the SMU msg response waiting time
This is expected to fix some mode1 reset failures. And this
affects SMU part only as the timeout setting for other parts
is controlled by a different macro.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:23 -05:00
Felix Kuehling
7e4dec5803 drm/amdgpu: Fix potential integer overflows
With mm_nodes larger than 4GB, byte_count in amdgpu_fill_buffer would
overflow.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-11 14:37:23 -05:00
Alex Deucher
32eaeae0ef drm/amdgpu/psp: add a mutex to protect access to the psp ring
We need to serialize access to the psp ring if there are multiple
callers at runtime.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-09 17:43:39 -05:00
Alex Deucher
7f963d9f69 drm/amdgpu/navi10: add uclk activity sensor
Query the metrics table for the current uclk activity.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-09 17:43:36 -05:00
Alex Deucher
f54eeab4e7 drm/amdgpu: properly guard the generic discovery code
It's only available on navi and newer.

Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-09 17:43:31 -05:00
Alex Deucher
4056278714 drm/amdgpu: add missing documentation on new module parameters
New parameters added for navi lack documentation.

Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-09 17:43:26 -05:00
Marek Olšák
83145f110e drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback
This RELEASE_MEM use has the Release semantic, which means we should write
back but not invalidate. Invalidations only make sense with the Acquire
semantic (ACQUIRE_MEM), or when RELEASE_MEM is used to do the combined
Acquire-Release semantic, which is a barrier, not a fence.

The undesirable side effect of doing invalidations for the Release semantic
is that it invalidates caches while shaders are running, because the Release
can execute in the middle of the next IB.

UMDs should use ACQUIRE_MEM at the beginning of IBs. Doing cache
invalidations for a fence (like in this case) doesn't do anything
for correctness.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-09 17:43:09 -05:00
Arnd Bergmann
5f65ae344f drm/amd/display: avoid 64-bit division
On 32-bit architectures, dividing a 64-bit integer in the kernel
leads to a link error:

ERROR: "__udivdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!
ERROR: "__divdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!

Change the two recently introduced instances to a multiply+shift
operation that is also much cheaper on 32-bit architectures.
We can do that here, since both of them are really 32-bit numbers
that change a few percent.

Fixes: bedbbe6af4 ("drm/amd/display: Move link functions from dc to dc_link")
Fixes: f18bc4e53a ("drm/amd/display: update calculated bounding box logic for NV")
Acked-by: Slava Abramov <slava.abramov@amd.com>
Tested-by: Slava Abramov <slava.abramov@amd.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 14:27:23 -05:00
Alex Deucher
173da95d93 drm/amdgpu/psp11: simplify the ucode register logic
Split it between navi10 and newer and everything before
navi10.

Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 14:01:30 -05:00
Alex Deucher
f8a7976b75 drm/amdgpu: properly guard DC support in navi code
Need to add appropriate ifdef.

Acked-by: Leo Li <sunpeng.li@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:42 -05:00
Arnd Bergmann
de48ebdd5b drm/amd/powerplay: vega20: fix uninitialized variable use
If smu_get_current_rpm() fails, we can't use the output,
as that may be uninitialized:

drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3023:8: error: variable 'current_rpm' is used uninitialized whenever '?:' condition is false [-Werror,-Wsometimes-uninitialized]
        ret = smu_get_current_rpm(smu, &current_rpm);
              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/../powerplay/inc/amdgpu_smu.h:735:3: note: expanded from macro 'smu_get_current_rpm'
        ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0)
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3024:12: note: uninitialized use occurs here
        percent = current_rpm * 100 / pptable->FanMaximumRpm;
                  ^~~~~~~~~~~
drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3023:8: note: remove the '?:' if its condition is always true
        ret = smu_get_current_rpm(smu, &current_rpm);
              ^
drivers/gpu/drm/amd/amdgpu/../powerplay/inc/amdgpu_smu.h:735:3: note: expanded from macro 'smu_get_current_rpm'
        ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0)
         ^
drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3020:22: note: initialize the variable 'current_rpm' to silence this warning
        uint32_t current_rpm;

Propagate the error code in that case.

Fixes: ee0db82027 ("drm/amd/powerplay: move PPTable_t uses into asic level")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:39 -05:00
Arnd Bergmann
c602b36fe2 drm/amd/display: dcn20: include linux/delay.h
Without this header, we get a compiler error in some configurations:

.../dc/dcn20/dcn20_hwseq.c: In function 'dcn20_hwss_wait_for_blank_complete':
.../dc/dcn20/dcn20_hwseq.c:1493:3: error: implicit declaration of function 'udelay' [-Werror=implicit-function-declaration]

Note: the use of udelay itself may be problematic, as can occupy
the CPU for 200ms in a busy-loop here.

Fixes: 7ed4e6352c ("drm/amd/display: Add DCN2 HW Sequencer and Resource")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:27 -05:00
Arnd Bergmann
d155bef063 amdgpu: make pmu support optional
When CONFIG_PERF_EVENTS is disabled, we cannot compile the pmu
portion of the amdgpu driver:

drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c:48:38: error: no member named 'hw' in 'struct perf_event'
        struct hw_perf_event *hwc = &event->hw;
                                     ~~~~~  ^
drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c:51:13: error: no member named 'attr' in 'struct perf_event'
        if (event->attr.type != event->pmu->type)
            ~~~~~  ^
...

Use conditional compilation for this file.

Fixes: 9c7c85f7ea ("drm/amdgpu: add pmu counters")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:22 -05:00
Nathan Chancellor
985863d00a drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent
clang warns (trimmed for brevity):

drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3023:8: warning:
variable 'current_rpm' is used uninitialized whenever '?:' condition is
false [-Wsometimes-uninitialized]
        ret = smu_get_current_rpm(smu, &current_rpm);
              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

smu_get_current_rpm expands to a ternary operator conditional on
smu->funcs->get_current_rpm being not NULL. When this is false,
current_rpm will be uninitialized. Zero initialize current_rpm to
avoid using random stack values if that ever happens.

Fixes: ee0db82027 ("drm/amd/powerplay: move PPTable_t uses into asic level")
Link: https://github.com/ClangBuiltLinux/linux/issues/588
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:18 -05:00
Nathan Chancellor
68c3bd9501 drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq
clang warns (trimmed for brevity):

drivers/gpu/drm/amd/amdgpu/../powerplay/smu_v11_0.c:1098:10: warning:
variable 'freq' is used uninitialized whenever '?:' condition is false
[-Wsometimes-uninitialized]
                ret =  smu_get_current_clk_freq_by_table(smu, clk_id, &freq);
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

If get_current_clk_freq_by_table is ever NULL, freq will fail to be
properly initialized. Zero initialize it to avoid using uninitialized
stack values.

smu_get_current_clk_freq_by_table expands to a ternary operator
conditional on smu->funcs->get_current_clk_freq_by_table being not NULL.
When this is false, freq will be uninitialized. Zero initialize freq to
avoid using random stack values if that ever happens.

Fixes: e36182490d ("drm/amd/powerplay: fix dpm freq unit error (10KHz -> Mhz)")
Link: https://github.com/ClangBuiltLinux/linux/issues/585
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:11 -05:00
Nathan Chancellor
d693e8e349 drm/amd/powerplay: Use memset to initialize metrics structs
clang warns:

drivers/gpu/drm/amd/amdgpu/../powerplay/navi10_ppt.c:601:33: warning:
suggest braces around initialization of subobject [-Wmissing-braces]
        static SmuMetrics_t metrics = {0};
                                       ^
                                       {}
drivers/gpu/drm/amd/amdgpu/../powerplay/navi10_ppt.c:905:26: warning:
suggest braces around initialization of subobject [-Wmissing-braces]
        SmuMetrics_t metrics = {0};
                                ^
                                {}
2 warnings generated.

One way to fix these warnings is to add additional braces like clang
suggests; however, there has been a bit of push back from some
maintainers[1][2], who just prefer memset as it is unambiguous, doesn't
depend on a particular compiler version[3], and properly initializes all
subobjects. Do that here so there are no more warnings.

[1]: https://lore.kernel.org/lkml/022e41c0-8465-dc7a-a45c-64187ecd9684@amd.com/
[2]: https://lore.kernel.org/lkml/20181128.215241.702406654469517539.davem@davemloft.net/
[3]: https://lore.kernel.org/lkml/20181116150432.2408a075@redhat.com/

Fixes: 98e1a543c7 ("drm/amd/powerplay: add function get current clock freq interface for navi10")
Fixes: ab43c4bf1c ("drm/amd/powerplay: fix fan speed show error (for hwmon pwm)")
Link: https://github.com/ClangBuiltLinux/linux/issues/583
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:08 -05:00
Nathan Chancellor
f19367da96 drm/amdgpu/mes10.1: Fix header guard
clang warns:

 In file included from drivers/gpu/drm/amd/amdgpu/nv.c:53:
 drivers/gpu/drm/amd/amdgpu/../amdgpu/mes_v10_1.h:24:9: warning:
 '__MES_V10_1_H__' is used as a header guard here, followed by #define of
 a different macro [-Wheader-guard]
 #ifndef __MES_V10_1_H__
         ^~~~~~~~~~~~~~~
 drivers/gpu/drm/amd/amdgpu/../amdgpu/mes_v10_1.h:25:9: note:
 '__MES_v10_1_H__' is defined here; did you mean '__MES_V10_1_H__'?
 #define __MES_v10_1_H__
         ^~~~~~~~~~~~~~~
         __MES_V10_1_H__
 1 warning generated.

Capitalize the V.

Fixes: 886f82aa7a ("drm/amdgpu/mes10.1: add ip block mes10.1 (v2)")
Link: https://github.com/ClangBuiltLinux/linux/issues/582
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:56:02 -05:00
Kevin Wang
e5aa29ce23 drm/amd/powerplay: add temperature sensor support for navi10
the hwmon interface need temperature sensor type support.
1. SENSOR_HOTSPOT_TEMP
2. SENSOR_EDGE_TEMP(SENSOR_GPU_TEMP)
3. SENSOR_MEM_TEMP

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:55:39 -05:00
Flora Cui
71cc9ef3f6 drm/amdgpu: fix scheduler timeout calc
scheduler timeout is in jiffies
v2: move timeout check to amdgpu_device_get_job_timeout_settings after
parsing the value
v3: add lockup_timeout param check. 0: keep default value. negative:
infinity timeout.
v4: refactor codes.

Signed-off-by: Flora Cui <flora.cui@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:55:20 -05:00
Philip Yang
e5eaa7cc0c drm/amdgpu: Prepare for hmm_range_register API change (v2)
An upcoming change in the hmm_range_register API requires passing in
a pointer to an hmm_mirror instead of mm_struct. To access the
hmm_mirror we need pass bo instead of ttm to amdgpu_ttm_tt_get_user_pages
because mirror is part of amdgpu_mn structure, which is accessible from bo.

v2: fix building without CONFIG_HMM_MIRROR (Arnd)

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-08 13:55:00 -05:00
Linus Torvalds
927ba67a63 Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer updates from Thomas Gleixner:
 "The timer and timekeeping departement delivers:

  Core:

   - The consolidation of the VDSO code into a generic library including
     the conversion of x86 and ARM64. Conversion of ARM and MIPS are en
     route through the relevant maintainer trees and should end up in
     5.4.

     This gets rid of the unnecessary different copies of the same code
     and brings all architectures on the same level of VDSO
     functionality.

   - Make the NTP user space interface more robust by restricting the
     TAI offset to prevent undefined behaviour. Includes a selftest.

   - Validate user input in the compat settimeofday() syscall to catch
     invalid values which would be turned into valid values by a
     multiplication overflow

   - Consolidate the time accessors

   - Small fixes, improvements and cleanups all over the place

  Drivers:

   - Support for the NXP system counter, TI davinci timer

   - Move the Microsoft HyperV clocksource/events code into the
     drivers/clocksource directory so it can be shared between x86 and
     ARM64.

   - Overhaul of the Tegra driver

   - Delay timer support for IXP4xx

   - Small fixes, improvements and cleanups as usual"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits)
  time: Validate user input in compat_settimeofday()
  timer: Document TIMER_PINNED
  clocksource/drivers: Continue making Hyper-V clocksource ISA agnostic
  clocksource/drivers: Make Hyper-V clocksource ISA agnostic
  MAINTAINERS: Fix Andy's surname and the directory entries of VDSO
  hrtimer: Use a bullet for the returns bullet list
  arm64: vdso: Fix compilation with clang older than 8
  arm64: compat: Fix __arch_get_hw_counter() implementation
  arm64: Fix __arch_get_hw_counter() implementation
  lib/vdso: Make delta calculation work correctly
  MAINTAINERS: Add entry for the generic VDSO library
  arm64: compat: No need for pre-ARMv7 barriers on an ARMv8 system
  arm64: vdso: Remove unnecessary asm-offsets.c definitions
  vdso: Remove superfluous #ifdef __KERNEL__ in vdso/datapage.h
  clocksource/drivers/davinci: Add support for clocksource
  clocksource/drivers/davinci: Add support for clockevents
  clocksource/drivers/tegra: Set up maximum-ticks limit properly
  clocksource/drivers/tegra: Cycles can't be 0
  clocksource/drivers/tegra: Restore base address before cleanup
  clocksource/drivers/tegra: Add verbose definition for 1MHz constant
  ...
2019-07-08 11:06:29 -07:00
Kevin Wang
3e2bb60ab2 drm/amdgpu: add mode1 (psp) reset for navi asic
add mode1 (by psp) reset for navi asic.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05 15:59:20 -05:00
xinhui pan
f1c1314be4 drm/amdgpu: Disable ras features on all IPs before gpu reset
Perform a ras_suspend to disable ras on all IPs to workaround
some ROCm stability issue.

Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05 15:59:20 -05:00
Kevin Wang
767acabdac drm/amd/powerplay: add baco smu reset function for smu11
add baco reset support for smu11.
it can help gpu do asic reset when gpu recovery.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05 15:59:08 -05:00
Jack Xiao
e3000669a7 drm/amd/powerplay: increase waiting time for smu response
We observed some SMU commands take more time for execution,
so increase waiting time for response.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05 15:54:55 -05:00
Yrjan Skrimstad
69064bbe7e drm/amd/powerplay/smu7_hwmgr: replace blocking delay with non-blocking
This driver currently contains a repeated 500ms blocking delay call
which causes frequent major buffer underruns in PulseAudio. This patch
fixes this issue by replacing the blocking delay with a non-blocking
sleep call.

Signed-off-by: Yrjan Skrimstad <yrjan@skrimstad.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05 15:54:55 -05:00
Fuqian Huang
d12c202289 drm/amdgpu: Use kmemdup rather than duplicating its implementation
kmemdup is introduced to duplicate a region of memory in a neat way.
Rather than kmalloc/kzalloc + memcpy, which the programmer needs to
write the size twice (sometimes lead to mistakes), kmemdup improves
readability, leads to smaller code and also reduce the chances of mistakes.
Suggestion to use kmemdup rather than using kmalloc/kzalloc + memcpy.

Reviewed-by: Christian König <Christian.Koenig@amd.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-05 15:54:55 -05:00
Felix Kuehling
a5b1615529 drm/amdkfd: Disable idle optimization for chained runlist
This works around difficult-to-reproduce soft hangs on oversubscribed
runlists.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03 14:32:10 -05:00
Felix Kuehling
7a049244a0 drm/amdkfd: Add chained_runlist_idle_disable flag to pm4_mes_runlist
New flag to disable an idle runlist optimization that is causing soft
hangs with some diffult-to-reproduce customer workloads. This will
serve as a workaround until the problem can be reproduced and the
root-cause determined.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03 14:32:04 -05:00
Felix Kuehling
f4fd28b6c7 drm/amdgpu: Fix tracking of invalid userptrs
Restore the code that resets mem->invalid. Othewise so mapping
userptrs after they got an MMU notifiers would always be skipped.

This also avoids unnecessarily calling get_user_pages on BOs that
have not been invalidated since the last try.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03 14:31:57 -05:00
Felix Kuehling
e7e2505326 drm/amdgpu: Use FENCE_OWNER_KFD in process_sync_pds_resv
We don't want eviction fences to trigger when waiting for page table
updates to complete during restore. In theory there shouldn't be any
unsignaled eviction fences in the PD reservation object, but I'm
seeing them in instrumented code for reasons not fully understood.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03 14:31:51 -05:00
Felix Kuehling
819ec5acf7 drm/amdkfd: Print a warning when the runlist becomes oversubscribed
Oversubscription of queues or processes results in poor performance
mostly because HWS blinbly schedules busy and idle queues, resulting
in poor occupancy if many queues are idle.

Let users know with a warning message when transitioning from a
non-oversubscribed to an oversubscribed runlist.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-03 14:31:26 -05:00
Jack Xiao
ba9e93c5fa drm/amdkfd: remove an unused variable
Just for cleanup.

Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-02 16:14:22 -05:00
Alex Deucher
843747253b drm/amdgpu/display: fix interrupt client id for navi
All asics newer than vega10 use client ids, so simplify the
check.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-02 15:46:24 -05:00
Jack Xiao
aabf3a951c drm/amdkfd: remove duplicated PCIE atomics request
Since amdgpu has always requested PCIE atomics, kfd don't
need duplicated PCIE atomics enablement. Referring to amdgpu
request result is enough.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 14:54:47 -05:00
Jack Xiao
b2109d8ed6 drm/amdgpu: enable PCIE atomics ops support
GPU atomics operation depends on PCIE atomics support.
Always enable PCIE atomics ops support in case that
it hasn't been enabled.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 14:54:40 -05:00
Jack Xiao
bae17d2a1b drm/amdgpu: add field indicating if has PCIE atomics support
The new field in amdgpu device is used to record whether the
system has PCIE atomics support. The field can be exposed to
UMD or kfd whether PCIE atomics have supported.

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 14:54:31 -05:00
Evan Quan
04796a3e44 drm/amd/powerplay: use hardware fan control if no powerplay fan table
Otherwise, you may get divided-by-zero error or corrput the SMU fan
control feature.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Slava Abramov <slava.abramov@amd.com>
Acked-by: Slava Abramov <slava.abramov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 14:54:22 -05:00
Evan Quan
fdafb3597a drm/amdgpu: fix MGPU fan boost enablement for XGMI reset
MGPU fan boost feature should not be enabled until all the
devices from the same hive are all back from reset.

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>
2019-07-01 14:54:12 -05:00
Marek Olšák
4b22e7e33f drm/amdgpu: handle AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID on gfx10
Add the gfx10 equivalent of the gfx9 code.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 14:53:50 -05:00
Marek Olšák
9ed2c993d7 drm/amdgpu: fix transform feedback GDS hang on gfx10 (v2)
v2: update emit_ib_size
(though it's still wrong because it was wrong before)

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 14:53:30 -05:00
Alex Deucher
25f09f8588 drm/amdgpu/gfx9: use reset default for PA_SC_FIFO_SIZE
Recommended by the hw team.

Reviewed-and-Tested-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2019-07-01 12:16:26 -05:00
Alex Deucher
535cfa75a6 drm/amdgpu/gfx10: use reset default for PA_SC_FIFO_SIZE
Recommended by the hw team.

Reviewed-and-Tested-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 12:14:16 -05:00
Alex Deucher
02d7a73b50 drm/amdgpu/gfx9: use reset default for PA_SC_FIFO_SIZE
Recommended by the hw team.

Reviewed-and-Tested-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 12:14:02 -05:00
Lyude Paul
688f3d1ebe drm/amdgpu: Don't skip display settings in hwmgr_resume()
I'm not entirely sure why this is, but for some reason:

921935dc64 ("drm/amd/powerplay: enforce display related settings only on needed")

Breaks runtime PM resume on the Radeon PRO WX 3100 (Lexa) in one the
pre-production laptops I have. The issue manifests as the following
messages in dmesg:

[drm] UVD and UVD ENC initialized successfully.
amdgpu 0000:3b:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring vce1 test failed (-110)
[drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <vce_v3_0> failed -110
[drm:amdgpu_device_resume [amdgpu]] *ERROR* amdgpu_device_ip_resume failed (-110).

And happens after about 6-10 runtime PM suspend/resume cycles (sometimes
sooner, if you're lucky!). Unfortunately I can't seem to pin down
precisely which part in psm_adjust_power_state_dynamic that is causing
the issue, but not skipping the display setting setup seems to fix it.
Hopefully if there is a better fix for this, this patch will spark
discussion around it.

Fixes: 921935dc64 ("drm/amd/powerplay: enforce display related settings only on needed")
Cc: Evan Quan <evan.quan@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Rex Zhu <Rex.Zhu@amd.com>
Cc: Likun Gao <Likun.Gao@amd.com>
Cc: <stable@vger.kernel.org> # v5.1+
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-07-01 09:15:00 -05:00
Evan Quan
f78c581e22 drm/amd/powerplay: use hardware fan control if no powerplay fan table
Otherwise, you may get divided-by-zero error or corrput the SMU fan
control feature.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Slava Abramov <slava.abramov@amd.com>
Acked-by: Slava Abramov <slava.abramov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
2019-07-01 09:14:05 -05:00
Lyude Paul
ee006eb00a drm/amdgpu: Don't skip display settings in hwmgr_resume()
I'm not entirely sure why this is, but for some reason:

921935dc64 ("drm/amd/powerplay: enforce display related settings only on needed")

Breaks runtime PM resume on the Radeon PRO WX 3100 (Lexa) in one the
pre-production laptops I have. The issue manifests as the following
messages in dmesg:

[drm] UVD and UVD ENC initialized successfully.
amdgpu 0000:3b:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring vce1 test failed (-110)
[drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <vce_v3_0> failed -110
[drm:amdgpu_device_resume [amdgpu]] *ERROR* amdgpu_device_ip_resume failed (-110).

And happens after about 6-10 runtime PM suspend/resume cycles (sometimes
sooner, if you're lucky!). Unfortunately I can't seem to pin down
precisely which part in psm_adjust_power_state_dynamic that is causing
the issue, but not skipping the display setting setup seems to fix it.
Hopefully if there is a better fix for this, this patch will spark
discussion around it.

Fixes: 921935dc64 ("drm/amd/powerplay: enforce display related settings only on needed")
Cc: Evan Quan <evan.quan@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Rex Zhu <Rex.Zhu@amd.com>
Cc: Likun Gao <Likun.Gao@amd.com>
Cc: <stable@vger.kernel.org> # v5.1+
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-28 09:08:42 -05:00
tiancyin
39b27ffef7 drm/amd/powerplay: update smu11_driver_if_navi10.h
update the smu11_driver_if_navi10.h since navi10 smu fw
update to 42.28

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: tiancyin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-28 09:08:03 -05:00
Colin Ian King
440e80ce02 drm/amd/display: fix a couple of spelling mistakes
There are a couple of spelling mistakes in dm_error messages and
a comment. Fix these.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 11:22:57 -05:00
Evan Quan
4130ff8027 drm/amd/powerplay: no memory activity support on Vega10
Make mem_busy_percent sysfs interface invisible on Vega10.

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>
2019-06-27 11:22:50 -05:00
shaoyunl
a864e29d94 drm/amdkfd: remove unnecessary warning message on gpu reset
In XGMI configuration, more than one asic can be reset at same time,
kfd is able to handle this and no need to trigger the warning

Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 11:22:41 -05:00
Oak Zeng
f51af4357c drm/amdgpu: Set queue_preemption_timeout_ms default value
Set default value of this kernel parameter to 9000

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 11:22:34 -05:00
Evan Quan
309bce0ca8 drm/amd/powerplay: add missing smu_get_clk_info_from_vbios() call
This seems a merge error.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 11:22:28 -05:00
Evan Quan
505ac3039a drm/amd/powerplay: support runtime ppfeatures setting on Navi10
Implement Navi10 backend for runtime ppfeatures status retrieving
and setting support.

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>
2019-06-27 11:22:21 -05:00
Evan Quan
b213646519 drm/amd/powerplay: check prerequisite for VCN power gating
VCN DPM is a necessary prerequisite for VCN power gating.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 11:22:08 -05:00
Alex Deucher
687ac4a702 drm/amdgpu: drop copy/paste leftover to fix big endian
The buf swap field doesn't exist on RB1.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 09:35:07 -05:00
Alex Deucher
d8dfc3bd46 drm/amdgpu: fix warning on 32 bit
Properly cast pointer to int.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-27 08:56:16 -05:00
Huang Rui
a201b6ac20 drm/amd/powerplay: make athub pg bit configured by pg_flags
The athub pg features enabling should be indicated by pg_flags.

Reported-by: Lijo Lazar <Lijo.Lazar@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:54:32 -05:00
Huang Rui
c12d410ff2 drm/amd/powerplay: make mmhub pg bit configured by pg_flags
The mmhub pg features enabling should be indicated by pg_flags.

Reported-by: Lijo Lazar <Lijo.Lazar@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:54:32 -05:00
Kevin Wang
cb2a782eb8 drm/amd/powerplay: add feature check in unforce_dpm_levels function (v2)
if not check dpm feature is enabled, it will cause show smc send message
failed log in dmesg log.
eg:
echo "auto" > power_dpm_force_performance_level

v2: whitespace fix (Alex)

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Rui Teng <rui.teng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:54:32 -05:00
Evan Quan
ac1092b341 drm/amd/powerplay: check gfxclk dpm enablement before proceeding
Support gfxclk dpm disablement.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:26:09 -05:00
Kevin Wang
f3121d3dbb drm/amd/powerplay: print smu versions only if version mismatch
only printf smu version when if version not matched.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:26:03 -05:00
Kevin Wang
ab43c4bf1c drm/amd/powerplay: fix fan speed show error (for hwmon pwm)
the navi asic can't get current rpm by MSG_GetCurrentRpm,
it will cause show fan rpm error, use Metrics_t to replace it.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:25:48 -05:00
Nicholas Kazlauskas
709527c77a drm/amd/display: update infoframe after dig fe is turned on (v2)
[Why]
The AVI infoframe is incorrectly programmed on DCN1/2 when enabling a
stream - causing the wrong pixel encoding to be used for display.

This is because the AVI infoframe is programmed before the DIG BE is
connected to the FE and turned on, so enabling the AFMT block doesn't
actually work and the registers subsequently can't be written to.

[How]
Program the infoframe *after* turning on the DIG FE. This was the
behavior previously used but it was incorrectly reverted
when adding the DCN2 HW sequencer code.

v2: Don't call update_info_frame twice

Fixes: 7ed4e6352c ("drm/amd/display: Add DCN2 HW Sequencer and Resource")

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:24:03 -05:00
Prike Liang
1189413f9c drm/amd/powerplay:clean up the residual mutex for smu_hw_init
The mutex for procting SMU during hw_init was removed as system
will be deadlock when smu_populate_umd_state_clk try get SMU mutex.
Therefore need remove the residual mutex from failed path.

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:51 -05:00
Ernst Sjöstrand
aeaa72e25e drm/amd/amdgpu: sdma_v4_0_start: initialize r
Reported by smatch:
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c:1167 sdma_v4_0_start() error: uninitialized symbol 'r'.

Signed-off-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:48 -05:00
Ernst Sjöstrand
803a1412fe drm/amd/amdgpu: Fix style issues in dcn20_resource.c
Inconsistent indentation and mixed use of brackets.

Signed-off-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:45 -05:00
Ernst Sjöstrand
ed9656fbc8 drm/amd/amdgpu: Check stream in amdgpu_dm_commit_planes
Reported by smatch:
amdgpu_dm.c:5637 amdgpu_dm_commit_planes() error: we previously assumed 'acrtc_state->stream' could be null
This seems to be checked for null pretty consistently elsewhere.

Signed-off-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:43 -05:00
Ernst Sjöstrand
70c5350a87 drm/amd/amdgpu: amdgpu_hwmon_show_temp: initialize temp
Reported by smatch:
drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c:1496 amdgpu_hwmon_show_temp() error: uninitialized symbol 'temp'.

Signed-off-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:39 -05:00
Ernst Sjöstrand
616ae02f6c drm/amd/amdgpu: Fix amdgpu_set_pp_od_clk_voltage error check
Reported by smatch:
drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c:693 amdgpu_set_pp_od_clk_voltage() error: uninitialized symbol 'ret'.

Signed-off-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:34 -05:00
Ernst Sjöstrand
0172591e21 drm/amd/amdgpu: Indent AMD_IS_APU properly
Reported by smatch:
drivers/gpu/drm/amd/amdgpu/soc15.c:715 soc15_get_pcie_usage() warn: inconsistent indenting
And a similar one in si.c.

Signed-off-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:24 -05:00
Alex Deucher
a6bbc3d5ac drm/amdgpu/display: drop ifdefs around comments
No need to protect the comments.  The DCN1_01 config
was dopped anyway.  Got accidently brought back with the
navi merge.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 13:23:17 -05:00
Alex Deucher
3e10f3196b drm/amdgpu/display: switch udelay to msleep
We may need to sleep for up to 80ms
(8ms per each of up to 10 loop iterations):

/* First DPCD read after VDD ON can fail if the particular board
 * does not have HPD pin wired correctly. So if DPCD read fails,
 * which it should never happen, retry a few times. Target worst
 * case scenario of 80 ms.
 */

Switch udelay to msleep to avoid limits on arm.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 12:08:46 -05:00
Alex Deucher
44ff0ae6b1 drm/amdgpu/powerplay: FEATURE_MASK is 64 bit so use ULL
ULL is needed for 32 bit arches.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 12:08:19 -05:00
Alex Deucher
d7929c1e13 Merge branch 'drm-next' into drm-next-5.3
Backmerge drm-next and fix up conflicts due to drmP.h removal.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-25 08:42:25 -05:00
tiancyin
8ac875db0f drm/amdgpu: disable gfxoff on navi10
The gfxoff brings unstability, disable it by default

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: tiancyin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-24 09:31:43 -05:00
Hawking Zhang
73c86d628d drm/amdgpu: fix modprobe failure for uvd_4/5/6
For uvd_4/5/6, amdgpu driver will only power on them when
there are jobs assigned to decode/enc rings.uvd_4/5/6 dpm was broken
since amdgpu_dpm_set_powergating_by_smu only covers gfx block.

The change would add more IP block support in amdgpu_dpm_set_powergating_by_smu
For GFX/UVD/VCN/VCE, if the new SMU driver is supported, invoke new
power gate helper function smu_dpm_set_power_gate, otherwise, fallback to
legacy powerplay helper function pp_set_powergating_by_smu. For other IP blocks
always invoke legacy powerplay helper function.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tianci Yin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-24 09:29:59 -05:00
Alex Deucher
f3f48d7331 drm/amdgpu: drop unused df init callback
It was replaced with the sw_init callback so is no longer
needed.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:14 -05:00
Jonathan Kim
8f78f1b03e drm/amdgpu: add sw_init to df_v1_7
change df_init to df_sw_init df 1.7 to prevent regression issues on pre-vega20
products when callback is called in sw_common_sw_init.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:14 -05:00
Oak Zeng
d9848e149d drm/amdkfd: Set gws_mask to 64 bit 1s
Previous kfd doesn't use gws so this mask was set to 0.
Set it to 64 bit 1s because now kfd can use all 64 gws
resources.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:14 -05:00
hersen wu
9cbee6eff8 drm/amd/display/dc: set num-dwb = 1 as navi10 asic cap
during navi10 bring up, dwb causes system hang.
to continue debug major issue, disable dwb by
set num-dwb = 0. the hang issue is not reproduced now
by enable num-dwb =1. dc source is shared by all os.
win needs num-dwb = 1.

Signed-off-by: hersen wu <hersenxs.wu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Roman Li <Roman.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:14 -05:00
Su Sung Chung
170a2398d2 drm/amd/display: make clk_mgr call enable_pme_wa
[why]
Before for raven and navi we are calling pp_smu functions for pme

[how]
refactor a code so we will call clk_mgr's enable_pme_wa function so we
can use pme_wa for future asics. This way we don't need to worry about
different ASIC since clk_mgr already have that information

Signed-off-by: Su Sung Chung <Su.Chung@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>
2019-06-22 09:34:14 -05:00
Charlene Liu
7a5ab155d3 drm/amd/display: expose dentist_get_did_from_divider
for future use

Signed-off-by: Charlene Liu <charlene.liu@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>
2019-06-22 09:34:14 -05:00
Dmytro Laktyushkin
c00d56fede drm/amd/display: add missing mod_vmid destructor
mod_vmid is missing a destructor.

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>
2019-06-22 09:34:14 -05:00
Thomas Lim
1a7d296d16 drm/amd/display: Add Underflow Asserts to dc
[Why]
For debugging underflow issues it can be useful to have asserts when the
underflow initially occurs.

[How]
Read the underflow status registers after actions that have a high risk
of causing underflow and assert that no underflow occurred. If underflow
occurred, clear the bit.

Signed-off-by: Thomas Lim <Thomas.Lim@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>
2019-06-22 09:34:14 -05:00
Dmytro Laktyushkin
bda9afdacf drm/amd/display: move vmid determination logic to a module
Currently vmid is decided internally inside dc. With the introduction
of new asics we are required to coordinate vmid use with external
components.

This change converts vmid logic to a DAL module allowing vmid to be
passed in as a parameter to DC.

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>
2019-06-22 09:34:14 -05:00
Charlene Liu
a6465d1f3b drm/amd/display: dcn2 use fixed clocks.
[Description]
dcn2 use fixed clocks and not program DPP CLK or Disp_CLK.

Signed-off-by: Charlene Liu <charlene.liu@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>
2019-06-22 09:34:14 -05:00
Charlene Liu
971ff2b433 drm/amd/display: add p010 and ayuv plane caps
for future use

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Chris Park <Chris.Park@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Acked-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:14 -05:00
Jun Lei
6e17b5b8a8 drm/amd/display: update DCN2 uclk switch time
[why]
value commited to by HW team is going to be higher
than pre-silicon, and will cause underflow if driver not
updated

[how]
update hardcoded value, update pstate switching logic
to fix case where with long uclk time we won't allow switch
even when we should

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>
2019-06-22 09:34:14 -05:00
Nicholas Kazlauskas
cf020d49b3 drm/amd/display: Rework CRTC color management
[Why]
To prepare for the upcoming DRM plane color management properties
we need to correct a lot of wrong behavior and assumptions made for
CRTC color management.

The documentation added by this commit in amdgpu_dm_color explains
how the HW color pipeline works and its limitations with the DRM
interface.

The current implementation does the following wrong:
- Implicit sRGB DGM when no CRTC DGM is set
- Implicit sRGB RGM when no CRTC RGM is set
- No way to specify a non-linear DGM matrix that produces correct output
- No way to specify a correct RGM when a linear DGM is used

We had workarounds for passing kms_color tests but not all of the
behavior we had wrong was covered by these tests (especially when
it comes to non-linear DGM). Testing both DGM and RGM at the same time
isn't something kms_color tests well either.

[How]
The specifics for how color management works in AMDGPU and the new
behavior can be found by reading the documentation added to
amdgpu_dm_color.c from this patch.

All of the incorrect cases from the old implementation have been
addressed for the atomic interface, but there still a few TODOs for
the legacy one.

Note: this does cause regressions for kms_color@pipe-a-ctm-* over HDMI.

The result looks correct from visual inspection but the CRC no longer
matches. For reference, the test was previously doing the following:

linear degamma -> CTM -> sRGB regamma -> RGB to YUV (709) -> ...

Now the test is doing:

linear degamma -> CTM -> linear regamma -> RGB to YUV (709) -> ...

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Wesley Chalmers
043f5bb630 drm/amd/display: Use macro for invalid OPP ID
[WHY]
This is meant to make it clearer that 0xf is not a valid OPP ID, and
that code making use of OPP IDs should not accept this value.

Signed-off-by: Wesley Chalmers <Wesley.Chalmers@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>
2019-06-22 09:34:13 -05:00
Eric Bernstein
c5509aadcf drm/amd/display: expose enable dp output functions
expose this function for future use

Implementation of DCN3 DIO Link Encoder including
dpcs register headers.

Signed-off-by: Eric Bernstein <eric.bernstein@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>
2019-06-22 09:34:13 -05:00
Charlene Liu
a6132cb102 drm/amd/display: add dwb stere caps and version
add dwb stereo caps and ver for future use

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Eric Bernstein
779451a736 drm/amd/display: Alpha plane type
Add Alpha surface type for future use

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>
2019-06-22 09:34:13 -05:00
Jun Lei
5d36f78311 drm/amd/display: making DCN20 WM table non-overlapping
[why]
Existing behavior has overlapping ranges resulting in path
dependent SMU selection

[how]
Make ranges non-overlapping, resulting in non-path dependent
selection

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>
2019-06-22 09:34:13 -05:00
Wenjing Liu
e710fdb134 drm/amd/display: update dsc max_target_bpp to 16 bpp
[why]
According to the latest specs, the max_target bpp sink
can support is 16 bpp.

[how]
update dsc max_target_bpp to 16

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Charlene Liu
f82c916c41 drm/amd/display: add some parameters to validate bandwidth functions
required for new checks.

Signed-off-by: Charlene Liu <charlene.liu@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>
2019-06-22 09:34:13 -05:00
Wenjing Liu
39a4eb853f drm/amd/display: update DSC MST DP virtual DPCD peer device enumeration policy
[why]
Current policy assumes virtual DPCD peer device as
an individual MST branch device with 1 input and 1 output.
However this is only true for virtual DP-to-DP peer device.
In general there are three types of virtual DP peer devices.
1. Sink peer device with virtual DPCD.
2. Virtual DP-to-DP Peer device with virtual DPCD.
3. Virtual DP-to-HDMI Protocol Converter Peer Device with
Virtual DPCD.
So we should break the assumption and handle all three types.

[how]
DP-to-DP peer device will have virtual DPCD cap upstream.
Sink peer device will have virtual DPCD on the logical port.
Dp to HDMI protocol converter peer device will have virtual DPCD
on its converter port.
For DSC capable Synaptics non VGA port we workaround by enumerating
a virutal DPCD peer device on its upstream
even if it doesn't have one.

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Jun Lei
2131f65581 drm/amd/display: add support for forcing DCFCLK without affecting watermarks
[why]
useful for debugging

[how]
plumb a debug option in dc

Signed-off-by: Jun Lei <Jun.Lei@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>
2019-06-22 09:34:13 -05:00
Nicholas Kazlauskas
6f4992b0e2 drm/amd/display: Copy stream updates onto streams
[Why]
Almost every function in DC that works with stream state expects that
the current state on the stream is the one that it should be writing
out. These functions are typically triggered by specifying a particular
stream update - but the actual contents of the stream update itself
are ignored, leaving it to the DM to actually update the stream state
itself.

The problem with doing this in DM is a matter of timing. On Linux
most of this is incorrectly done in atomic check, when we actually want
it to be done during atomic commit tail while access to DC is locked.

To give an example, a commit requesting to modify color management
state for DM could come in, be rejected, but still have modified
the actual system state for the stream since it's shared memory. The
next time color management gets programmed it'll use the rejected
color management info - which might not even still be around if it's
a custom transfer function.

So a reasonable place to perform this is within DC itself and this is
the model that's currently in use for surface updates. DC can even
compare the current system state to the incoming surface update to
determine update level, something that can't currnetly be done with the
framework for stream updates.

[How]
Duplicate the framework used for surface updates for stream updates
as well. Copy all the updates after checking the update type.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@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>
2019-06-22 09:34:13 -05:00
Ilya Bakoulin
4f008d931b drm/amd/display: Fix incorrect vba type
SwathWidthCThisState is expected to be an unsigned int array.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Martin Leung
d8cd587d2b drm/amd/display: removing MODULO change for dcn2
[why]
when resetting pipes from 480p to dual-pipe 8k, modulo reg write for
video optimized rate updated one pipe without changing the other, causing
sync error

[how]
removed code from dcn2

Signed-off-by: Martin Leung <martin.leung@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Ilya Bakoulin
03fd87db6d drm/amd/display: Fix incorrect DML output_bpp value
[Why]
The output_bpp pipe parameter was assigned an incorrect value
(color depth enum), and subsequently used to overwrite
the OutputBpp parameter calculated by DML. Seems like this had no
effect except with DSC enabled, which would make DML produce
bad outputs.

[How]
Removed assignment to OutputBpp, fixed output_bpp assignment,
and properly set ForcedOutputLinkBPP instead of OutputBpp.
Also removed condition in DML that prevented forcing of
Output BPP with DSC enabled.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Jun Lei
3979efcec6 drm/amd/display: Add missing VM conversion from hw values
[why]
VM implemenation is missing conversion from HW values in hubbub
DM not passing actual PTB during flip

[how]
add proper HW conversion from logical values
fix cases where we programmed VA even though we are in PA
plumb in PTB from DM

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Ilya Bakoulin
a746a25855 drm/amd/display: Drive-by fixes for display_mode_vba
Fixes for the following:
- Incorrect pointer type (unsigned int instead of double)
- Incorrect DSC number of slices setting

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:13 -05:00
Nikola Cornij
98ce8cc1b4 drm/amd/display: Enable DSC power-gating for DSC streams
[why]
Currently DSC power gating is disabled by default because the power
transition doesn't happen, causing a crash on some systems

[how]
Fix the lack of power state transition and enable DSC power gating
by default.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Martin Leung <Martin.Leung@amd.com>
Reviewed-by: Nevenko Stupar <Nevenko.Stupar@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Charlene Liu
c3ec8ba537 drm/amd/display: Return UPDATE_TYPE_FULL on writeback update
Should do full update when display writeback is updated.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Duke Du <Duke.Du@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Wenjing Liu
ba32c50f04 drm/amd/display: decouple dsc adjustment out of enablement
[why]
dsc adjustment is allowed via stream update sequence.
dsc enablement is only allowed via commit stream sequence.
with the current unified dsc set function, it is hard
to determine which sequence it is called by.
The solution is to decouple dsc adjustment out of enablement
sequence so we can handle them separately.

[how]
decouple dsc adjustment out of enablement.

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Jun Lei
1621f4c417 drm/amd/display: always use 4 dp lanes for dml
[why]
current DML logic uses currently trained setting for number
of dp lanes in DML calculations.  this is obviously flawed since
just because 1 lane is in use doesn't mean only 1 lane can be used

this causes mode validation to fail depending on current state,
which is incorrect

[how]
DML should always assume 4 lanes are available.  validation of
bandwidth is not supposed to be handled by DML, since we do
link validation without DML already

also, DML is expecting there to be a copy of the max state, this
state is removed when update_bounding_box is called to update
actual SKU clocks.  fix this as well by duping last state.

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Acked-by: Eric Yang <eric.yang2@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Wesley Chalmers
278141f58e drm/amd/display: Use DCN2 functions instead of DCE
[WHY]
DCN code should make as few references to DCE as possible

[HOW]
Copy DCE110 implementation of find_first_free_match_stream_enc_for_link
into DCN10

Signed-off-by: Wesley Chalmers <Wesley.Chalmers@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>
2019-06-22 09:34:12 -05:00
Wesley Chalmers
6936c8b1d4 drm/amd/display: DCN2 Engine-specifc encoder allocation
[WHY]
From DCE110 onward, we have the ability to assign DIG BE and FE
separately for any display connector type; before, we could only do this
for DP.

Signed-off-by: Wesley Chalmers <Wesley.Chalmers@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>
2019-06-22 09:34:12 -05:00
Nikola Cornij
b5d71c9396 drm/amd/display: Disable DSC power gating in Diags
[why]
With DSC power gating enabled, one of the register reads times out occasionally,
causing a DSC test to fail.

[how]
Disable DSC power gating in Diags.
NOTE: This has to be reverted once the problems with DSC power gating are
resolved.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Nevenko Stupar <Nevenko.Stupar@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Joshua Aberback
324707fdf8 drm/amd/display: Set test pattern on blank when using Visual Confirm
[Why]
We want a test pattern to show up on screen when we're blanked and have
visual confirm enabled, for debugging. Raven does this, it's a mistake that
Navi does not.

[How]
 - in "blank_pixel_data", set appropriate DPG pattern for visual confirm
 - refactor DPG calls out of "enable_stream_timing"

Signed-off-by: Joshua Aberback <joshua.aberback@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>
2019-06-22 09:34:12 -05:00
Dmytro Laktyushkin
ad141db915 drm/amd/display: add null checks and set update flags for DCN2
* add plane state null checks
* add and set update surface flags

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Tyler DiBattista
9796b71318 drm/amd/display: move DWB structs and enums to dc_hw_types
[Why]
these enums/structs will be used more generically in the future
so moving it to dc_hw_types and dc_types

Signed-off-by: Tyler DiBattista <tyler.dibattista@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>
2019-06-22 09:34:12 -05:00
Vitaly Prosyak
f99b6f4f21 drm/amd/display: Integrate color transform3x4 with 3dlut tm
[Why & How]
Reuse existent code path (dcn1+) and in order to do that apply de gamma
in 1D blender LUT and re use MPC OGAM.
Follow up is required.

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Acked-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Vitaly Prosyak <Vitaly.Prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Charlene Liu
8bb3d7e7b5 drm/amd/display: used optimum VSTARTUP instead of MaxVStartup
[Description]
Features that are desirable for minimizing the Global Sync Period:
DRR and lateflip

Signed-off-by: Charlene Liu <charlene.liu@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>
2019-06-22 09:34:12 -05:00
Wenjing Liu
09104d151a drm/amd/display: add dsc_passthrough_support bit in dpcd struct
Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@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>
2019-06-22 09:34:12 -05:00
Wenjing Liu
cba4d59c93 drm/amd/display: fix a potential issue in DSC logic
[why]
In compute dsc bandwidth range there is an uninitialized variable

[how]
Initialize the variable to the correct value.

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Leo (Hanghong) Ma
e34fe1bba6 drm/amd/display: Expose send immediate sdp message interface
[Why]
To send sdp message immediately from a single slot.

[How]
Modify the generic SDP message interface, and use GSP4 to send immediate
sdp message.

Signed-off-by: Leo (Hanghong) Ma <hanghong.ma@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>
2019-06-22 09:34:12 -05:00
Ilya Bakoulin
ed07237c0c drm/amd/display: Fix LB BPP and Cursor width
DCN2.0 LB BPP should be 48 or 16BPC and max cursor width should be 256.

Also use populate_dml_pipes as functions pointer instead of using it directly

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:12 -05:00
Dmytro Laktyushkin
b964e79064 drm/amd/display: fix macro_tile_size for tiling
A regression was introduced when we set correct tile size
for the gfx9 swizzle mode. This resulted in incorrect
macro tile size.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@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>
2019-06-22 09:34:12 -05:00
Joshua Aberback
97ae9b9675 drm/amd/display: Remove OPP clock programming on plane disable
[Why]
Plane disable gets calls when we enable blank. On DCN2, we blank by using
DPG to display a black colour instead of using OTG blank. DPG runs off the
OPP clock, therefore we shouldn't disable the OPP clock when disabling the
plane. We do need to disable the OPP clock when disabling the entire pipe,
that will be addressed in a separate commit.

Signed-off-by: Joshua Aberback <joshua.aberback@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>
2019-06-22 09:34:11 -05:00
Dmytro Laktyushkin
02ce5a799a drm/amd/display: fix odm mpo disable
It looks like mpo isn't properly disabled during odm, this change is
meant to fix that.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Charlene Liu
72c6473a6a drm/amd/display: [backport] dwb dm + efc support
dwb fixes.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Duke Du <Duke.Du@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Charlene Liu
bb21290ff6 drm/amd/display: Create DWB resource for DCN2
[Description]
dcn20 has num_dwb =1 in the res cap, but not created.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Duke Du <Duke.Du@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Aric Cyr
6bd8d7d3f7 drm/amd/display: Intermittent DCN2 pipe hang on mode change
[Why]
GSL is being used to synchronize pipes when vsync is off but
on transition to vsync on during a mode change GSL is not
being reset correctly.

[How]
Disable GSL on any plane that is disabled.

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Nikola Cornij
f446489adc drm/amd/display: Add support for extended DSC DPCD caps
[why]
A few of the new DSC DPCD caps were introduced by a DP 1.4a SCR in order
to give DSC branch decoders a chance to expose their maximum throughput
and maximum line width limitations.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Nikola Cornij
ce76898527 drm/amd/display: Do a reg update instead of set when writing ODM color format
[why]
If a set is done, DSC settings are zeroed out, leading to no DSC for the modes
that require ODM, such as 8k60.

This was a regression introduced by 5a4f26295176bbfc776c75aaf0f6dd8ccf806958.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Vitaly Prosyak
97516065a0 drm/amd/display: add flags for gamut map library
[Why & How]
Gamut map lib provides a wider gamut mapping options
vs BT2390

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Acked-by: Vitaly Prosyak <Vitaly.Prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Samson Tam
796c9ece2e drm/amd/display: block passive dongle EDID Emulation for USB-C ports
[Why]
Emulating passive dongle on USB-C port causes issue on some asics.

[How]
Check for DP_IS_USB_C flag in bios parser and propagate it to
encoder features flags. If DP_IS_USB_C flag is set and it is trying to
emulate passive dongle, then return fail.

Signed-off-by: Samson Tam <Samson.Tam@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>
2019-06-22 09:34:11 -05:00
Yongqiang Sun
040a4d63bd drm/amd/display: DCHUB requestors numbers for Navi.
[Why]
The DCHub arbiter has a mechanism to dynamically rate limit the DCHub
request stream to the fabric. If the memory controller is fully utilized
and the DCHub requestors are well ahead of their amortized schedule,
then it is safe to prevent the next winner from being committed and sent
to the fabric. The utilization of the memory controller is approximated
by ensuring that the number of outstanding requests is greater than a
threshold specified by the ARB_MIN_REQ_OUTSTANDING. To determine that
the DCHub requestors are well ahead of the amortized schedule, the slack
of the next winner is compared with the ARB_SAT_LEVEL in DLG RefClk
cycles.

[How]
The recommended settings to enable thise dynamic limiting for Navi is
180 requests.

Signed-off-by: Yongqiang Sun <yongqiang.sun@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>
2019-06-22 09:34:11 -05:00
Nikola Cornij
d7cd0e053b drm/amd/display: Add 170Mpix/sec DSC throughput support
[why]
It was missing, although defined in DP spec

[how]
- Add handling of this value to DSC code
- Also remove unused file dsc_helpers.c

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Joshua Aberback <Joshua.Aberback@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Charlene Liu
c703e753c8 drm/amd/display: add SW_USE_I2C_REG request.
[Description]
This is for DC_I2c arbitration use between HW use/SW use and DMCU use.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@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>
2019-06-22 09:34:11 -05:00
Nikola Cornij
b01473e919 drm/amd/display: Make sure line size is not zero in DCN2 line buffer size calculations
[why]
'Divide by zero' error happens when line size happens to be zero.

[how]
The code that makes sure line size minimum value can be 1 was already
present in DCN1 part of the driver, this is mearly a port to DCN2.

Signed-off-by: Nikola Cornij <nikola.cornij@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>
2019-06-22 09:34:11 -05:00
Eryk Brol
7fad39ca4a drm/amd/display: Change DCN2 vupdate start programming
[Why]
In order to ensure that incoming flips are latched and
complete immediately, we need to program the vupdate
interrupt to come during the back porch of each frame.

[How]
Program the vupdate start_line to be in the back porch
like it's done for DCN1.

Signed-off-by: Eryk Brol <eryk.brol@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:11 -05:00
Yongqiang Sun
78b674573a drm/amd/display: Refactor program watermark.
Refactor programming watermark function:
Divided into urgent watermark, stutter watermark and pstate watermark.

Signed-off-by: Yongqiang Sun <yongqiang.sun@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>
2019-06-22 09:34:10 -05:00
Dmytro Laktyushkin
be67de3561 drm/amd/display: fix dcn2 mpc split decision
The split condition is broken and will always activate
at the moment.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Charlene Liu
4850ce697f drm/amd/display: Add hubp_init entry to hubp vtable
Different HW will need to init HUBP differently. For now, add a vtable
entry, and hook a NO-OP for DCN1 and DCN2.

In addition, future HW will need to access the HUBPREQ_DEBUG and
CUR_TTU_CNTL0 register for hubp_init. Add that here.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Ilya Bakoulin
fbc9ca671f drm/amd/display: Fix ODM combine data format
[Why]
OPTC data format was left at its default value (444) when enabling
ODM combine. This caused issues with FPGA capture.

[How]
Write the OPTC_DATA_FORMAT field when enabling ODM combine.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Yongqiang Sun
2a874fa025 drm/amd/display: Remove duplicate define of TO_DCN20_HUBBUB
Signed-off-by: Yongqiang Sun <yongqiang.sun@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Thomas Lim
78ad75f8d7 drm/amd/display: Add power down display on boot flag
[Why]
Due to the generic introduction of seamless boot, the display is no
longer blanked upon boot. However, this causes corruption on some
systems that does not lock the memory in the non-secure boot case,
resulting in brief corruption on boot due to garbage being written into
the frame buffer.

[How]
Add a flag, read during DC init, to determine whether display should be
blanked on boot. Default to true.

Signed-off-by: Thomas Lim <Thomas.Lim@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Nikola Cornij
9c0ab2dd07 drm/amd/display: Consider DSC target bpp precision when calculating DSC target bpp
[why]
DSC target bpp precision is a decoder DPCD and an AMD encoder capability.
It must be taken into account when calculating target bitrate.

[how]
Add a DC DSC function that does this calculation.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Acked-by: Tony Cheng <Tony.Cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Josip Pavic
d7c29549e3 drm/amd/display: enable abm on dcn2
[Why]
ABM is currently not enabled on DCN2.

[How]
Update the register name list for DCN2 and un-comment the code that
creates the abm object.

Signed-off-by: Josip Pavic <Josip.Pavic@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Wenjing Liu
c2209d1544 drm/amd/display: Implement DSC MST fair share algorithm
[why]
The current policy will always enable DSC to 12 bpp
regardless of if the current bandwidth is enough for MST displays.
This logic is not optimal because user will get lower quality output
if DSC compression is enabled.
This change to is to implement a DSC MST bandwidth fair share
algorithm so we will dynamically decide if DSC is needed and what
quality (target bpp) is needed to fairly destribute the MST bandwidth
in one MST topology. This will allow user to see the most optimal
image quality with the given bandwidth.

[how]
We will start with lowest bandwidth possible and run a
Max-Min fairness algorithm to fairly distribute the available
bandwidth. If there is still remaining bandwidth, we will try to fit
the timing without DSC compression.

Signed-off-by: Wenjing Liu <Wenjing.Liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Nikola Cornij
c9ae6e1691 drm/amd/display: Acquire DSC HW resource only if required by stream
[why]
There are ASICs that have fewer DSC engines than pipes, which makes
DSC a resource that should be used only if required.

[how]
Acquire DSC HW resource if required by stream and release when not
required anymore.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
hersen wu
0d7bd17c6e drm/amd/display: Disable display writeback on Linux for NV10
[WHY] system crash when initialize dwb
current linux driver does not support dwb.
 disable this feature for now.

[HOW] set num_dwb = 0 to disable dwb for now

Signed-off-by: hersen wu <hersenxs.wu@amd.com>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
hersen wu
b37727fb14 drm/amd/display: Add vupdate interrupt sources to NV10
[WHY] linux upstream already has interrupt vupdate for freesync
in dcn10. dcn20 interrupt shares the same source code as dcn10.
but dcn20 interrupt translator does not add vupdate interrupt.
this cause index of vupdate aarray be negative which causes
crash.

[HOW] add vupdate into dc interrupt transltor

Signed-off-by: hersen wu <hersenxs.wu@amd.com>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00
Nikola Cornij
c92b4c46c1 drm/amd/display: Mark DSC resource as unused after copying to the secondary ODM pipe
[why]
DSC resource has to be acquired before it can be used and simply copying
a reference to it is very likely to cause problems when accessing DSC.

[how]
Set DSC resource pointer to NULL to mark it as unused after primary pipe
resources were copied to the secondary ODM pipe.

Signed-off-by: Nikola Cornij <nikola.cornij@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>
2019-06-22 09:34:10 -05:00
Tyler DiBattista
5940ff3941 drm/amd/display: Change Min fclk to 1.2Ghz
[Why]
Some nightly tests are failing since the new value for fclk is a
bit too low. Also, a new test for the maximum downscale case was
needed.

[How]
Updated the default value for fclk to be 1.2GHz.

Signed-off-by: Tyler DiBattista <tyler.dibattista@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Acked-by: Tony Cheng <Tony.Cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2019-06-22 09:34:10 -05:00