drm/amd/display: Document set RECOUT operation

During the investigation on how to add visual confirmation on top of the
planes used by DCN, it becomes evident that the lack of information in
the code makes this work unnecessarily complicated. This commit
introduces a set of documentation related to the RECOUT operation in
order to make it easy for developers to navigate this set of functions.

Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Add kernel-doc to some hubp functions

Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Remove legacy comments

To improve the code readability, this commit removes a set of commented
and not used functions for a long time. Notice that now we have the
amdgpu_dm_dtn_log, which prints all the relevant information that we
need.

Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Add documentation for power gate plane

This commit introduces kernel documentation to some essential functions
related to power gate control over planes. It also adds a macro to make
one part of the code easy to understand.

Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Add get_current_time interface to dmub_srv

[Why]
Need to get current DMUB time.

[How]
Add get_current_time interface to dmub_srv.

v2: drop whitespace changes (Alex)

Signed-off-by: Wyatt Wood <wyatt.wood@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: treat memory as a single-channel for asymmetric memory V3

Previous patch caused crash and had been reverted. This patch
addresses the issue without regression.

[Why]
1. Driver use umachannelnumber to calculate watermarks for stutter.
In asymmetric memory config, the actual bandwidth is less than
dual-channel. The bandwidth should be the same as single-channel.
2. We found single rank dimm need additional delay time for stutter.

[How]
Get information from each DIMM. Treat memory config as a single-channel
for asymmetric memory in bandwidth calculating.
Add additional delay time for single rank dimm.

Signed-off-by: Hugo Hu <hugo.hu@amd.com>
Reviewed-by: Sung Lee <Sung.Lee@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Reset max GFX clock after disabling determinism

When determinism mode is disabled on aldebaran, max GFX clock will
be reset to default max frequency value.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Fix showing incorrect frequencies on aldebaran

v1: Use the current and custom pstate frequencies to track the current and
user-set min/max values in manual and determinism mode. Previously, only
actual_* value was used to track the currrent and user requested value.
The value will get reassigned whenever user requests a new value with
pp_od_clk_voltage node. Hence it will show incorrect values when user
requests an invalid value or tries a partial request without committing
the values. Separating out to custom and current variable fixes such
issues.

v2: Remove redundant if-else check

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Add custom/current freq to pstates

Add custom member for user requested custom frequency, level mask
or min/max frequencies. Add curr member to keep track of the current
active values.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Conditionally reset RAS counters on boot

Only clear RAS error counters if perestent EDC harvesting is not supported

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: disable 3DCGCG on picasso/raven1 to avoid compute hang

There is problem with 3DCGCG firmware and it will cause compute test
hang on picasso/raven1. It needs to disable 3DCGCG in driver to avoid
compute hang.

Signed-off-by: Changfeng <Changfeng.Zhu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Refine the error report when flush tlb.

there are 2 hubs to flush in the gmc, to make it easier
to debug when hub flush failed, refine the logs.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Skip the program of GRBM_CAM* in SRIOV

KMD should not the program these registers,
so skip them in the SRIOV environment.

Signed-off-by: Peng Ju Zhou <PengJu.Zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fix GPU TLB update error when PAGE_SIZE > AMDGPU_PAGE_SIZE

When PAGE_SIZE is larger than AMDGPU_PAGE_SIZE, the number of GPU TLB
entries which need to update in amdgpu_map_buffer() should be multiplied
by AMDGPU_GPU_PAGES_IN_CPU_PAGE (PAGE_SIZE / AMDGPU_PAGE_SIZE).

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Yi Li <liyi@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: heavy-weight flush TLB after unmap

Need do a heavy-weight TLB flush to make sure we have no more dirty data
in the cache for the unmapped pages.

Define enum TLB_FLUSH_TYPE, add flush_type parameter to
amdgpu_amdkfd_flush_gpu_tlb_pasid.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Revert "drm/amdkfd: flush TLB after updating GPU page table"

This reverts commit 1704ac8e439e3dcf97431e268bd64fde1874d807.

After "drm/amdgpu: flush TLB if valid PDE turns into PTE" is checked
in, this workaround is not needed.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fill adev->unique_id with data from PF2VF msg

Initialize unique_id from PF2VF under virtualization.

V2: skip smu_get_unique_id() under virtualization

Signed-off-by: Jiawei Gu <Jiawei.Gu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: flush TLB if valid PDE turns into PTE

Mapping huge page, 2MB aligned address with 2MB size, uses PDE0 as PTE.
If previously valid PDE0, PDE0.V=1 and PDE0.P=0 turns into PTE, this
requires TLB flush, otherwise page table walker will not read updated
PDE0.

Change page table update mapping to return table_freed flag to indicate
the previously valid PDE may have turned into a PTE if page table is
freed.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon: use the dummy page for GART if needed

Imported BOs don't have a pagelist any more.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fixes: 0575ff3d33cd ("drm/radeon: stop using pages with drm_prime_sg_to_page_addr_arrays v2")

drm/amdgpu: move struct amdgpu_vram_reservation into vram mgr

Not used outside of that file.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: check contiguous flags instead of mm_node

Drop the last user of drm_mm_node.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: set the contiguous flag if possible

This avoids reallocating scanout BOs on first pin in a lot of cases.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: use cursor functions in amdgpu_bo_in_cpu_visible_vram

One of the last remaining uses of drm_mm_node.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: re-apply "use the new cursor in the VM code" v2

Now that we found the underlying problem we can re-apply this patch.

This reverts commit 6b44b667e24cf89603ebdaa31b939c034d425162.

v2: rebase on KFD changes

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Nirmoy Das <nirmoy.das@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: query boot config cap before issue psp cmd

Only send boot_config cmd to ASICs that support dynamic
boot config. Otherwise, the boot_config cmd will fail.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: add helper function to query dynamic boot config cap

Check firmware flags to determine whether dynmaic
boot config is supported or not.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: switch to cached fw flags for mem training cap

Check cached firmware_flags to determin whether
two stage mem training is supported or not.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: switch to cached fw flags for sram ecc cap

Check cached firmware_flags to determine whether
sram ecc is supported or not.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: switch to cached fw flags for gpu virt cap

Check cached firmware_flags to determine if gpu
virtualization is supported in vbios

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: add atomfirmware helper function to query fw cap

Fimware capability was changed from 16 bits to 32 bits
for atomfirmware. add helper funciton to query firmware
capability and cache the value at early stage.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Complete multimedia bandwidth interface

- Update SRIOV PF2VF header with latest revision

- Extend existing function in amdgpu_virt.c to read MM bandwidth config
  from PF2VF message

- Add SRIOV Sienna Cichlid codec array and update the bandwidth with
  PF2VF message

v2: squash in removal of unused variable (Alex)

Signed-off-by: Bokun Zhang <bokun.zhang@amd.com>
Reviewed-by: Monk liu <monk.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Albebaran: MTYPE_NC for coarse-grain remote memory

MTYPE UC was used for a specific use case that ended up not being
implemented. Use NC for better performance for coarse-grained memory where
cache coherence during shader execution is not required.

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>

drm/amdgpu: Arcturus: MTYPE_NC for coarse-grain remote memory

MTYPE UC was used for a specific use case that ended up not being
implemented. Use NC for better performance for coarse-grained memory where
cache coherence during shader execution is not required.

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>

drm/amdgpu: Add compile flag for securedisplay

Add compile flag CONFIG_DEBUG_FS to clear the warning:
unused variable 'amdgpu_securedisplay_debugfs_ops'

Signed-off-by: Jinzhou Su <Jinzhou.Su@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: refine the poison data consumption handling

The user applications maybe register the KFD_EVENT_TYPE_HW_EXCEPTION and
KFD_EVENT_TYPE_MEMORY events, driver could notify them when poison data
consumed. Beside that, some applications maybe register SIGBUS signal
hander. These applications will handle poison data by themselves, exit
or re-create context to re-dispatch works.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon/dpm: Disable sclk switching on Oland when two 4K 60Hz monitors are connected

Screen flickers rapidly when two 4K 60Hz monitors are in use. This issue
doesn't happen when one monitor is 4K 60Hz (pixelclock 594MHz) and
another one is 4K 30Hz (pixelclock 297MHz).

The issue is gone after setting "power_dpm_force_performance_level" to
"high". Following the indication, we found that the issue occurs when
sclk is too low.

So resolve the issue by disabling sclk switching when there are two
monitors requires high pixelclock (> 297MHz).

v2:
 - Only apply the fix to Oland.
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: new range accessible by all GPUs

If xnack is on, new range is created to recover retry vm fault or
created by SVM API calls, set all GPUs have access to the range.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Update aldebaran pmfw interface

Update aldebaran driver-PMFW interface to version 0x07

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/amdgpu: Cancel the hrtimer in sw_fini

Move the process of cancelling hrtimer to sw_fini

Signed-off-by: Roy Sun <Roy.Sun@amd.com>
Reviewed-by: Emily Deng <Emily.Deng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: enable ASPM by default

Since ASPM function has been stable, we don't need to add the modprobe
parameter and we can enable ASPM by default.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Jiansong Chen <Jiansong.Chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: update the method for harvest IP for specific SKU

Update the method of disabling VCN IP for specific SKU for navi1x ASIC,
it will judge whether should add the related IP at the function of
amdgpu_device_ip_block_add().

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: add judgement when add ip blocks (v2)

Judgement whether to add an sw ip according to the harvest info.

v2: fix indentation (Alex)

Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: add synchronization among waves in the same threadgroup

It is possible that the previous waves have exited before others are
created, so the other waves maybe reuse pyhsical resouces left by
previous ones. Therefore add barrier instruction to synchronize waves within
the same threadgroup.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/display: fix dal_allocation documentation

Add missing structure elements.

Fixes: 0dd79532340568 ("drm/amdgpu/display: Implement functions to let DC allocate GPU memory")
Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/display: fix build when CONFIG_DRM_AMD_DC_DCN is not defined

Fixes:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c: In function ‘amdgpu_dm_initialize_drm_device’:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:3726:7: error: implicit declaration of function ‘register_outbox_irq_handlers’; did you mean ‘register_hpd_handlers’? [-Werror=implicit-function-declaration]
 3726 |   if (register_outbox_irq_handlers(dm->adev)) {
      |       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
      |       register_hpd_handlers

Fixes: 81927e2808be ("drm/amd/display: Support for DMUB AUX")
Reviewed-by: Jude Shih <shenshih@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Jude Shish <Jude.Shih@amd.com>

drm/amdgpu/display: fix warning when CONFIG_DRM_AMD_DC_DCN is not defined

Fixes:
At top level:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:633:13: warning: ‘dm_dmub_outbox1_low_irq’ defined but not used [-Wunused-function]
  633 | static void dm_dmub_outbox1_low_irq(void *interrupt_params)
      |             ^~~~~~~~~~~~~~~~~~~~~~~

Fixes: 81927e2808be ("drm/amd/display: Support for DMUB AUX")
Reviewed-by: Jude Shih <shenshih@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Jude Shih <Jude.Shih@amd.com>

drm/amdgpu/display: remove an old DCN3 guard

The DCN3 guards were dropped a while ago, this one must have
snuck in in a merge or something.

Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Delete two unneeded bool conversions

The result of an expression consisting of a single relational operator is
already of the bool type and does not need to be evaluated explicitly.

No functional change.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Delete several unneeded bool conversions

The result of an expression consisting of a single relational operator is
already of the bool type and does not need to be evaluated explicitly.

No functional change.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Initialize attribute for hdcp_srm sysfs file

It is stored in dynamically allocated memory, so sysfs_bin_attr_init() must
be called to initialize it. (Note: "initialization" only sets the .attr.key
member in this struct; it does not change the value of any other members.)

Otherwise, when CONFIG_DEBUG_LOCK_ALLOC=y this message appears during boot:

    BUG: key ffff9248900cd148 has not been registered!

Fixes: 9037246bb2da ("drm/amd/display: Add sysfs interface for set/get srm")
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1586
Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: David Ward <david.ward@gatech.edu>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Fix out-of-bounds bug

Create new structure SISLANDS_SMC_SWSTATE_SINGLE, as initialState.levels
and ACPIState.levels are never actually used as flexible arrays. Those
arrays can be used as simple objects of type
SISLANDS_SMC_HW_PERFORMANCE_LEVEL, instead.

Currently, the code fails because flexible array _levels_ in
struct SISLANDS_SMC_SWSTATE doesn't allow for code that accesses
the first element of initialState.levels and ACPIState.levels
arrays:

drivers/gpu/drm/amd/pm/powerplay/si_dpm.c:
4820: table->initialState.levels[0].mclk.vDLL_CNTL =
4821:         cpu_to_be32(si_pi->clock_registers.dll_cntl);
...
5021: table->ACPIState.levels[0].mclk.vDLL_CNTL =
5022:         cpu_to_be32(dll_cntl);

because such element cannot be accessed without previously allocating
enough dynamic memory for it to exist (which never actually happens).
So, there is an out-of-bounds bug in this case.

That's why struct SISLANDS_SMC_SWSTATE should only be used as type
for object driverState and new struct SISLANDS_SMC_SWSTATE_SINGLE is
created as type for objects initialState, ACPIState and ULVState.

Also, with the change from one-element array to flexible-array member
in commit 0e1aa13ca3ff ("drm/amd/pm: Replace one-element array with
flexible-array in struct SISLANDS_SMC_SWSTATE"), the size of
dpmLevels in struct SISLANDS_SMC_STATETABLE should be fixed to be
SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE instead of
SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1.

Fixes: 0e1aa13ca3ff ("drm/amd/pm: Replace one-element array with flexible-array in struct SISLANDS_SMC_SWSTATE")
Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon/si_dpm: Fix SMU power state load

Create new structure SISLANDS_SMC_SWSTATE_SINGLE, as initialState.levels
and ACPIState.levels are never actually used as flexible arrays. Those
arrays can be used as simple objects of type
SISLANDS_SMC_HW_PERFORMANCE_LEVEL, instead.

Currently, the code fails because flexible array _levels_ in
struct SISLANDS_SMC_SWSTATE doesn't allow for code that access
the first element of initialState.levels and ACPIState.levels
arrays:

4353         table->initialState.levels[0].mclk.vDLL_CNTL =
4354                 cpu_to_be32(si_pi->clock_registers.dll_cntl);
...
4555         table->ACPIState.levels[0].mclk.vDLL_CNTL =
4556                 cpu_to_be32(dll_cntl);

because such element cannot exist without previously allocating
any dynamic memory for it (which never actually happens).

That's why struct SISLANDS_SMC_SWSTATE should only be used as type
for object driverState and new struct SISLANDS_SMC_SWSTATE_SINGLE is
created as type for objects initialState, ACPIState and ULVState.

Also, with the change from one-element array to flexible-array member
in commit 96e27e8d919e ("drm/radeon/si_dpm: Replace one-element array
with flexible-array in struct SISLANDS_SMC_SWSTATE"), the size of
dpmLevels in struct SISLANDS_SMC_STATETABLE should be fixed to be
SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE instead of
SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1583
Fixes: 96e27e8d919e ("drm/radeon/si_dpm: Replace one-element array with flexible-array in struct SISLANDS_SMC_SWSTATE")
Cc: stable@vger.kernel.org
Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon/ni_dpm: Fix booting bug

Create new structure NISLANDS_SMC_SWSTATE_SINGLE, as initialState.levels
and ACPIState.levels are never actually used as flexible arrays. Those
arrays can be used as simple objects of type
NISLANDS_SMC_HW_PERFORMANCE_LEVEL, instead.

Currently, the code fails because flexible array _levels_ in
struct NISLANDS_SMC_SWSTATE doesn't allow for code that access
the first element of initialState.levels and ACPIState.levels
arrays:

drivers/gpu/drm/radeon/ni_dpm.c:
1690         table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL =
1691                 cpu_to_be32(ni_pi->clock_registers.mpll_ad_func_cntl);
...
1903:   table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl);
1904:   table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(mpll_ad_func_cntl_2);

because such element cannot exist without previously allocating
any dynamic memory for it (which never actually happens).

That's why struct NISLANDS_SMC_SWSTATE should only be used as type
for object driverState and new struct SISLANDS_SMC_SWSTATE_SINGLE is
created as type for objects initialState, ACPIState and ULVState.

Also, with the change from one-element array to flexible-array member
in commit 434fb1e7444a ("drm/radeon/nislands_smc.h: Replace one-element
array with flexible-array member in struct NISLANDS_SMC_SWSTATE"), the
size of dpmLevels in struct NISLANDS_SMC_STATETABLE should be fixed to
be NISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE instead of
NISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1.

Bug: https://lore.kernel.org/dri-devel/3eedbe78-1fbd-4763-a7f3-ac5665e76a4a@xenosoft.de/
Fixes: 434fb1e7444a ("drm/radeon/nislands_smc.h: Replace one-element array with flexible-array member in struct NISLANDS_SMC_SWSTATE")
Cc: stable@vger.kernel.org
Reported-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Link: https://lore.kernel.org/dri-devel/9bb5fcbd-daf5-1669-b3e7-b8624b3c36f9@xenosoft.de/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/amdgpu: Fix errors in function documentation

Fix a couple of syntax errors and removed one excess
parameter in the function documentations which lead
to kernel docs build warning.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dwaipayan Ray <dwaipayanray1@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: remove unused function dc_link_perform_link_training

This function is not used anywhere, remove it. It was added in
40dd6bd376a4 ("drm/amd/display: Linux Set/Read link rate and lane count
through debugfs") and moved in fe798de53a7a ("drm/amd/display: Move link
functions from dc to dc_link"), but a user is missing.

Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Rouven Czerwinski <r.czerwinski@pengutronix.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: add function to clear MMEA error status for aldebaran

For aldebaran, hardware will not clear error status automatically when
reading error status register, insteadly driver should set clear bit of
the error status register explicitly to clear error status.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: correct the funtion to clear GCEA error status

The bit 11 of GCEA_ERR_STATUS register is used to clear GCEA error
status.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: 3.2.135.1

- adding missed FW promotion

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: [FW Promotion] Release 0.0.65

- Implement INBOX0 messaging for HW lock

Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: 3.2.135

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: fix use_max_lb flag for 420 pixel formats

Right now the flag simply selects memory config 0 when flag is true
however 420 modes benefit more from memory config 3.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Handle potential dpp_inst mismatch with pipe_idx

[Why]
In some pipe harvesting configs, we will select the incorrect
dpp_inst when programming DTO. This is because when any intermediate
pipe is fused, resource instances are no longer in 1:1
correspondence with pipe index.

[How]
When looping through pipes to program DTO, get the dpp_inst
associated with each pipe from res_pool.

Signed-off-by: Anthony Wang <anthony1.wang@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Handle pixel format test request

[Why]
Some DSC tests fail because stream pixel encoding does not change
its value according to the type requested in the DPCD test params.

[How]
Set stream pixel encoding before updating DSC config and configuring
the test pattern.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Hanghong Ma <Hanghong.Ma@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Fix clock table filling logic

[Why]
Currently, the code that fills the clock table can miss filling
information about some of the higher voltage states advertised
by the SMU. This, in turn, may cause some of the higher pixel clock
modes (e.g. 8k60) to fail validation.

[How]
Fill the table with one entry per DCFCLK level instead of one entry
per FCLK level. This is needed because the maximum FCLK does not
necessarily need maximum voltage, whereas DCFCLK values from SMU
cover the full voltage range.

Signed-off-by: Ilya Bakoulin <Ilya.Bakoulin@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: minor dp link training refactor

[how]
The change includes some dp link training refactors:
1. break down is_ch_eq_done to checking individual conditions in
its own function.
2. update dpcd_set_training_pattern to take in dc_dp_training_pattern
as input.
3. moving lttpr mode struct definition into link_service_types.h

Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Reviewed-by: George Shen <George.Shen@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: DETBufferSizeInKbyte variable type modifications

[Why]
DETBufferSizeInKByte is not expected to be sub-dividable, hence
unsigned int is a better suited data-type. Change it to an array
as well to satisfy current requirements.

[How]
Change the data-type of DETBufferSizeInKByte to an unsigned int
array. Modify the all the variables like DETBufferSizeY,
DETBufferSizeC that are involved in DETBufferSizeInKByte calculations
to unsigned int in all the display_mode_vba_xx files.

Signed-off-by: Chaitanya Dhere <chaitanya.dhere@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Add dc log for DP SST DSC enable/disable

Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Reviewed-by: Mikita Lipski <Mikita.Lipski@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Expand DP module training API.

[Why & How]
Add functionality useful for DP link training to public interface.

Signed-off-by: Jimmy Kizito <Jimmy.Kizito@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Add fallback and abort paths for DP link training.

[Why]
When enabling a DisplayPort stream:
- Optionally reducing link bandwidth between failed link training
attempts should progressively relax training requirements.
- Abandoning link training altogether if a sink is unplugged should
avoid unnecessary training attempts.

[How]
- Add fallback parameter to DP link training function and reduce link
bandwidth between failed training attempts as long as stream bandwidth
requirements are met.
- Add training status for sink unplug and abort training when this
status is reported.

Signed-off-by: Jimmy Kizito <Jimmy.Kizito@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Update setting of DP training parameters.

[Why]
Some links are dynamically assigned link encoders on stream enablement.

[How]
Update DisplayPort training parameter determination stage that assumes
link encoder statically assigned to link.

Signed-off-by: Jimmy Kizito <Jimmy.Kizito@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Update DPRX detection.

[Why]
Some extra provisions are required during DPRX detection for links which
lack physical HPD and AUX/DDC pins.

[How]
Avoid attempting to access nonexistent physical pins during DPRX
detection.

Signed-off-by: Jimmy Kizito <Jimmy.Kizito@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Stylon Wang <stylon.wang@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: covert ras status to kernel errno

The original codes use ras status and kernl errno together in the same
function, which is a wrong code style.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Avoid HPD IRQ in GPU reset state

[Why]
If GPU is in reset state, force enabling link will cause
unexpected behaviour.

[How]
Avoid handling HPD IRQ when GPU is in reset state.

Signed-off-by: Zhan Liu <zhan.liu@amd.com>
Reviewed-by: Nikola Cornij <nikola.cornij@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Quit RAS initialization earlier if RAS is disabled

If RAS is disabled through amdgpu_ras_enable kernel parameter,
we should quit the RAS initialization eariler to avoid initialization
of some RAS data structure such as sysfs etc.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: handle errors returned by svm_migrate_copy_to_vram/ram

If migration copy failed because process is killed, or out of VRAM or
system memory, pass error code back to caller to handle error
gracefully.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Export ras_*_enabled to debugfs

Export the runtime-set "ras_hw_enabled" and
"ras_enabled" to debugfs, for debugging.

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: John Clements <John.Clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Rename to ras_*_enabled

Rename,
  ras_hw_supported --> ras_hw_enabled, and
  ras_features     --> ras_enabled,
to show that ras_enabled is a subset of
ras_hw_enabled, which itself is a subset
of the ASIC capability.

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: John Clements <John.Clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Move up ras_hw_supported

Move ras_hw_supported into struct amdgpu_dev.
The dependency is:
struct amdgpu_ras <== struct amdgpu_dev <== ASIC,
read as "struct amdgpu_ras depends on struct
amdgpu_dev, which depends on the hardware."

This can be loosely understood as, "if RAS is
supported, which is property of the ASIC (struct
amdgpu_dev), then we can access struct
amdgpu_ras."

v2: Fix a typo: must binary AND in ternary cond
    in amdgpu_ras.c

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: John Clements <John.Clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Remove redundant ras->supported

Remove redundant ras->supported, as this value
is also stored in adev->ras_features.

Use adev->ras_features, as that supercedes "ras",
since the latter is its member.

The dependency goes like this:
ras <== adev->ras_features <== hw_supported,
and is read as "ras depends on ras_features, which
depends on hw_supported." The arrows show the flow
of information, i.e. the dependency update.

"hw_supported" should also live in "adev".

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: John Clements <John.Clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: update vcn1.0 Non-DPG suspend sequence

update suspend register settings in Non-DPG mode.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: update the shader to clear specific SGPRs

Add shader codes to explicitly clear specific SGPRs, such as
flat_scratch_lo, flat_scratch_hi and so on. And also correct the
allocation size of SGPRs in PGM_RSRC1.

Signed-off-by: Dennis Li <Dennis.Li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Enable TCP channel hashing for Aldebaran

Enable TCP channel hashing to match DF hash settings for Aldebaran.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: add ACPI SRAT parsing for topology

In NPS4 BIOS we need to find the closest numa node when creating
topology io link between cpu and gpu, if PCI driver doesn't set
it.

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>

drm/amdgpu/pm: add documentation for pp_od_clock_voltage for vangogh

Vangogh follows other APUs, but also allows core clock adjustments.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: add documentation for pp_od_clock_voltage for APUs

APUs only support adjusting the SCLK domain.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: expose pmfw attached timestamp on Aldebaran

Available with 68.18.0 and later PMFWs.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: new gpu_metrics structure for pmfw attached timestamp

Supported by some latest ASICs.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Use device specific BO size & stride check.

The builtin size check isn't really the right thing for AMD
modifiers due to a couple of reasons:

1) In the format structs we don't do set any of the tilesize / blocks
etc. to avoid having format arrays per modifier/GPU
2) The pitch on the main plane is pixel_pitch * bytes_per_pixel even
for tiled ...
3) The pitch for the DCC planes is really the pixel pitch of the main
surface that would be covered by it ...

Note that we only handle GFX9+ case but we do this after converting
the implicit modifier to an explicit modifier, so on GFX9+ all
framebuffers should be checked here.

There is a TODO about DCC alignment, but it isn't worse than before
and I'd need to dig a bunch into the specifics. Getting this out in
a reasonable timeframe to make sure it gets the appropriate testing
seemed more important.

Finally as I've found that debugging addfb2 failures is a pita I was
generous adding explicit error messages to every failure case.

Fixes: f258907fdd83 ("drm/amdgpu: Verify bo size can fit framebuffer size on init.")
Tested-by: Simon Ser <contact@emersion.fr>
Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Init GFX10_ADDR_CONFIG for VCN v3 in DPG mode.

Otherwise tiling modes that require the values form this field
(In particular _*_X) would be corrupted upon video decode.

Copied from the VCN v2 code.

Fixes: 99541f392b4d ("drm/amdgpu: add mc resume DPG mode for VCN3.0")
Reviewed-and-Tested by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: change the default timeout for kernel compute queues

Change to 60s.  This matches what we already do in virtualization.
Infinite timeout can lead to deadlocks in the kernel.

Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: set vcn mgcg flag for picasso

enable vcn mgcg flag for picasso.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: Update L1 and add L2/3 cache information

The L1 cache information has been updated and the L2/L3
information has been added. The changes have been made
for Vega10 and newer ASICs. There are no changes
for the older ASICs before Vega10.

Signed-off-by: Mike Li <Tianxinmike.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/amdgpu/amdgpu_drv.c: Replace drm_modeset_lock_all with drm_modeset_lock

drm_modeset_lock_all() is not needed here, so it is replaced with
drm_modeset_lock(). The crtc list around which we are looping never
changes, therefore the only lock we need is to protect access to
crtc->state.

Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: initialize variable

Static analysis reports this problem

amdgpu_pm.c:478:16: warning: The right operand of '<' is a garbage value
  for (i = 0; i < data.nums; i++) {
                ^ ~~~~~~~~~

In some cases data is not set.  Initialize to 0 and flag not setting
data as an error with the existing check.

Signed-off-by: Tom Rix <trix@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon: Avoid power table parsing memory leaks

Avoid leaving a hanging pre-allocated clock_info if last mode is
invalid, and avoid heap corruption if no valid modes are found.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211537
Fixes: 6991b8f2a319 ("drm/radeon/kms: fix segfault in pm rework")
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon: Fix off-by-one power_state index heap overwrite

An out of bounds write happens when setting the default power state.
KASAN sees this as:

[drm] radeon: 512M of GTT memory ready.
[drm] GART: num cpu pages 131072, num gpu pages 131072
==================================================================
BUG: KASAN: slab-out-of-bounds in
radeon_atombios_parse_power_table_1_3+0x1837/0x1998 [radeon]
Write of size 4 at addr ffff88810178d858 by task systemd-udevd/157

CPU: 0 PID: 157 Comm: systemd-udevd Not tainted 5.12.0-E620 #50
Hardware name: eMachines        eMachines E620  /Nile       , BIOS V1.03 09/30/2008
Call Trace:
 dump_stack+0xa5/0xe6
 print_address_description.constprop.0+0x18/0x239
 kasan_report+0x170/0x1a8
 radeon_atombios_parse_power_table_1_3+0x1837/0x1998 [radeon]
 radeon_atombios_get_power_modes+0x144/0x1888 [radeon]
 radeon_pm_init+0x1019/0x1904 [radeon]
 rs690_init+0x76e/0x84a [radeon]
 radeon_device_init+0x1c1a/0x21e5 [radeon]
 radeon_driver_load_kms+0xf5/0x30b [radeon]
 drm_dev_register+0x255/0x4a0 [drm]
 radeon_pci_probe+0x246/0x2f6 [radeon]
 pci_device_probe+0x1aa/0x294
 really_probe+0x30e/0x850
 driver_probe_device+0xe6/0x135
 device_driver_attach+0xc1/0xf8
 __driver_attach+0x13f/0x146
 bus_for_each_dev+0xfa/0x146
 bus_add_driver+0x2b3/0x447
 driver_register+0x242/0x2c1
 do_one_initcall+0x149/0x2fd
 do_init_module+0x1ae/0x573
 load_module+0x4dee/0x5cca
 __do_sys_finit_module+0xf1/0x140
 do_syscall_64+0x33/0x40
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Without KASAN, this will manifest later when the kernel attempts to
allocate memory that was stomped, since it collides with the inline slab
freelist pointer:

invalid opcode: 0000 [#1] SMP NOPTI
CPU: 0 PID: 781 Comm: openrc-run.sh Tainted: G        W 5.10.12-gentoo-E620 #2
Hardware name: eMachines        eMachines E620  /Nile , BIOS V1.03       09/30/2008
RIP: 0010:kfree+0x115/0x230
Code: 89 c5 e8 75 ea ff ff 48 8b 00 0f ba e0 09 72 63 e8 1f f4 ff ff 41 89 c4 48 8b 45 00 0f ba e0 10 72 0a 48 8b 45 08 a8 01 75 02 <0f> 0b 44 89 e1 48 c7 c2 00 f0 ff ff be 06 00 00 00 48 d3 e2 48 c7
RSP: 0018:ffffb42f40267e10 EFLAGS: 00010246
RAX: ffffd61280ee8d88 RBX: 0000000000000004 RCX: 000000008010000d
RDX: 4000000000000000 RSI: ffffffffba1360b0 RDI: ffffd61280ee8d80
RBP: ffffd61280ee8d80 R08: ffffffffb91bebdf R09: 0000000000000000
R10: ffff8fe2c1047ac8 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000100
FS:  00007fe80eff6b68(0000) GS:ffff8fe339c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe80eec7bc0 CR3: 0000000038012000 CR4: 00000000000006f0
Call Trace:
 __free_fdtable+0x16/0x1f
 put_files_struct+0x81/0x9b
 do_exit+0x433/0x94d
 do_group_exit+0xa6/0xa6
 __x64_sys_exit_group+0xf/0xf
 do_syscall_64+0x33/0x40
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fe80ef64bea
Code: Unable to access opcode bytes at RIP 0x7fe80ef64bc0.
RSP: 002b:00007ffdb1c47528 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007fe80ef64bea
RDX: 00007fe80ef64f60 RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
R10: 00007fe80ee2c620 R11: 0000000000000246 R12: 00007fe80eff41e0
R13: 00000000ffffffff R14: 0000000000000024 R15: 00007fe80edf9cd0
Modules linked in: radeon(+) ath5k(+) snd_hda_codec_realtek ...

Use a valid power_state index when initializing the "flags" and "misc"
and "misc2" fields.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211537
Reported-by: Erhard F. <erhard_f@mailbox.org>
Fixes: a48b9b4edb8b ("drm/radeon/kms/pm: add asic specific callbacks for getting power state (v2)")
Fixes: 79daedc94281 ("drm/radeon/kms: minor pm cleanups")
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: drop the GCR packet from the emit_ib frame for sdma5.0

It's not needed here and has been added to the proper place
in the previous patch.  This aligns with what we do for sdma 5.2.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Add graphics cache rinse packet for sdma 5.0

Add emit mem sync callback for sdma_v5_0

In amdgpu sync object test, three threads created jobs
to send GFX IB and SDMA IB in sequence. After the first
GFX thread joined, sometimes the third thread will reuse
the same physical page to store the SDMA IB. There will
be a risk that SDMA will read GFX IB in the previous physical
page. So it's better to flush the cache before commit sdma IB.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

MAINTAINERS: fix a few more amdgpu tree links

Switch to gitlab.

Fixes: 101c2fae5108d7 ("MAINTAINERS: update radeon/amdgpu/amdkfd git trees")
Cc: David Ward <david.ward@gatech.edu>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Add debugfs node to read private buffer

Add debugfs interface to read region allocated for FW private buffer

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>