drm/amdgpu/sdma_v4_4_2: update VM flush implementation for SDMA

This commit updates the VM flush implementation for the SDMA engine.

- Added a new function `sdma_v4_4_2_get_invalidate_req` to construct the VM_INVALIDATE_ENG0_REQ
  register value for the specified VMID and flush type. This function ensures that all relevant
  page table cache levels (L1 PTEs, L2 PTEs, and L2 PDEs) are invalidated.

- Modified the `sdma_v4_4_2_ring_emit_vm_flush` function to use the new `sdma_v4_4_2_get_invalidate_req`
  function. The updated function emits the necessary register writes and waits to perform a VM flush
  for the specified VMID. It updates the PTB address registers and issues a VM invalidation request
  using the specified VM invalidation engine.

- Included the necessary header file `gc/gc_9_0_sh_mask.h` to provide access to the required register
  definitions.

v2: vm flush by the vm inalidation packet (Lijo)
v3: code stle and define thh macro for the vm invalidation packet (Christian)
v4: Format definition sdma vm invalidate packet (Lijo)

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

drm/amdgpu: Optimize VM invalidation engine allocation and synchronize GPU TLB flush

- Modify the VM invalidation engine allocation logic to handle SDMA page rings.
  SDMA page rings now share the VM invalidation engine with SDMA gfx rings instead of
  allocating a separate engine. This change ensures efficient resource management and
  avoids the issue of insufficient VM invalidation engines.

- Add synchronization for GPU TLB flush operations in gmc_v9_0.c.
  Use spin_lock and spin_unlock to ensure thread safety and prevent race conditions
  during TLB flush operations. This improves the stability and reliability of the driver,
  especially in multi-threaded environments.

 v2: replace the sdma ring check with a function `amdgpu_sdma_is_page_queue`
 to check if a ring is an SDMA page queue.(Lijo)

 v3: Add GC version check, only enabled on GC9.4.3/9.4.4/9.5.0
 v4: Fix code style and add more detailed description (Christian)
 v5: Remove dependency on vm_inv_eng loop order, explicitly lookup shared inv_eng(Christian/Lijo)
 v6: Added search shared ring function amdgpu_sdma_get_shared_ring (Lijo)

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

drm/amd/amdgpu: Increase max rings to enable SDMA page ring

Increase the maximum number of rings supported by the AMDGPU driver from 133 to 149.
This change is necessary to enable support for the SDMA page ring.

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

drm/amdgpu: Decode deferred error type in gfx aca bank parser

In the case of injecting uncorrected error with background workload,
the deferred error among uncorrected errors need to be specified
by checking the deferred and poison bits of status register.

v2: refine checking for deferred error
v2: log possiable DEs among CEs
v2: generate CPER records for DEs among UEs

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

drm/amdgpu/gfx11: Add Cleaner Shader Support for GFX11.5 GPUs

Enable the cleaner shader for GFX11.5.0/11.5.1 GPUs to provide data
isolation between GPU workloads. The cleaner shader is responsible for
clearing the Local Data Store (LDS), Vector General Purpose Registers
(VGPRs), and Scalar General Purpose Registers (SGPRs), which helps
prevent data leakage and ensures accurate computation results.

This update extends cleaner shader support to GFX11.5.0/11.5.1 GPUs,
previously available for GFX11.0.3. It enhances security by clearing GPU
memory between processes and maintains a consistent GPU state across KGD
and KFD workloads.

Cc: Mario Sopena-Novales <mario.novales@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/mes: clean up SDMA HQD loop

Follow the same logic as the other IP types.

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

drm/amdgpu/mes: enable compute pipes across all MEC

Enable pipes on both MECs for MES.

Fixes: 745f46b6a99f ("drm/amdgpu: enable mes v12 self test")
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/mes: drop MES 10.x leftovers

Leftover from MES bring up.  There is no production
MES support for MES 10.x.  The rest of the MES 10.x
code has already been removed so drop this.

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

drm/amdgpu/mes: optimize compute loop handling

Break when we get to the end of the supported pipes
rather than continuing the loop.

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

drm/amdgpu/sdma: guilty tracking is per instance

The gfx and page queues are per instance, so track them
per instance.

v2: drop extra parameter (Lijo)

Fixes: fdbfaaaae06b ("drm/amdgpu: Improve SDMA reset logic with guilty queue tracking")
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/sdma: fix engine reset handling

Move the kfd suspend/resume code into the caller.  That
is where the KFD is likely to detect a reset so on the KFD
side there is no need to call them.  Also add a mutex to
lock the actual reset sequence.

v2: make the locking per instance

Fixes: bac38ca8c475 ("drm/amdkfd: implement per queue sdma reset for gfx 9.4+")
Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: remove invalid usage of sched.ready

I can't count how often I had to remove this nonsense.

Probably doesn't need an explanation 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>

drm/amdgpu: add cleaner shader trace point

Note when the cleaner shader is executed.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: add isolation trace point

Note when we switch from one isolation owner to another.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: stop reserving VMIDs to enforce isolation

That was quite troublesome for gang submit. Completely drop this
approach and enforce the isolation separately.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: rework how the cleaner shader is emitted v3

Instead of emitting the cleaner shader for every job which has the
enforce_isolation flag set only emit it for the first submission from
every client.

v2: add missing NULL check
v3: fix another NULL pointer deref

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: rework how isolation is enforced v2

Limiting the number of available VMIDs to enforce isolation causes some
issues with gang submit and applying certain HW workarounds which
require multiple VMIDs to work correctly.

So instead start to track all submissions to the relevant engines in a
per partition data structure and use the dma_fences of the submissions
to enforce isolation similar to what a VMID limit does.

v2: use ~0l for jobs without isolation to distinct it from kernel
    submissions which uses NULL for the owner. Add some warning when we
    are OOM.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: overwrite signaled fence in amdgpu_sync

This allows using amdgpu_sync even without peeking into the fences for a
long time.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: use GFP_NOWAIT for memory allocations

In the critical submission path memory allocations can't wait for
reclaim since that can potentially wait for submissions to finish.

Finally clean that up and mark most memory allocations in the critical
path with GFP_NOWAIT. The only exception left is the dma_fence_array()
used when no VMID is available, but that will be cleaned up later on.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/amdgpu: Revert "drm/amd/amdgpu: shorten the gfx idle worker timeout"

This reverts commit 55ff973fe1c053de143969cfc8b34baff084084a.

Reason for revert: this causes some tests fail with call trace.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Acked-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/sdam: Skip SDMA queue reset for SRIOV

For SRIOV, skip the SDMA queue reset and return
error. The engine/queue reset failure will trigger
FLR in the sequence.

v2: do not add queue reset support mask for sriov

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

drm/amdgpu: Add support to load PSP TA v13.0.12 for SRIOV

Add case for 13.0.12.

Signed-off-by: Ahmad Rehman <ahrehman@amd.com>
Reviewed-by: Vignesh.Chander@amd.com
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Enable amdgpu_ras_resume for gfx 9.5.0

This enables ras to be resumed after gpu recovery on mi350 sriov.

Signed-off-by: Ellen Pan <yunru.pan@amd.com>
Reviewed-by: Ahmad Rehman <Ahmad.Rehman@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: set precise mem ops caps to disabled for gfx 11 and 12

Clause instructions with precise memory enabled currently hang the
shader so set capabilities flag to disabled since it's unsafe to use
for debugging.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Tested-by: Lancelot Six <lancelot.six@amd.com>
Reviewed-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Skip pcie_replay_count sysfs creation for VF

VFs cannot read the NAK_COUNTER register. This information is only
available through PMFW metrics.

Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Add active_umc_mask to ras init_flags

Add active_umc_mask to ras init_flags.

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

Documentation/amdgpu: Add debug_mask documentation

Add description for debug_mask bit options.

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

drm/amd/pm: Add debug bit for smu pool allocation

In certain cases, it's desirable to avoid PMFW log transactions to
system memory. Add a mask bit to decide whether to allocate smu pool in
device memory or system memory.

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

drm/amdgpu/vcn: adjust workload profile handling

No need to make the workload profile setup dependent
on the results of cancelling the delayed work thread.
We have all of the necessary checking in place for the
workload profile reference counting, so separate the
two.  As it is now, we can theoretically end up with
the call from begin_use happening while the worker
thread is executing which would result in the profile
not getting set for that submission.  It should not
affect the reference counting.

v2: bail early if the the profile is already active (Lijo)

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

drm/amdgpu/gfx: adjust workload profile handling

No need to make the workload profile setup dependent
on the results of cancelling the delayed work thread.
We have all of the necessary checking in place for the
workload profile reference counting, so separate the
two.  As it is now, we can theoretically end up with
the call from begin_use happening while the worker
thread is executing which would result in the profile
not getting set for that submission.  It should not
affect the reference counting.

v2: bail early if the the profile is already active (Lijo)

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

drm/amdgpu: Add EEPROM I2C address support for smu v13_0_12

Add EEPROM I2C address support for smu v13_0_12.

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

drm/amdgpu/vcn: fix ref counting for ring based profile handling

We need to make sure the workload profile ref counts are
balanced.  This isn't currently the case because we can
increment the count on submissions, but the decrement may
be delayed as work comes in.  Track when we enable the
workload profile so the references are balanced.

v2: switch to a mutex and active flag
v3: fix mutex init

Fixes: 1443dd3c67f6 ("drm/amd/pm: fix and simplify workload handling")
Cc: Yang Wang <kevinyang.wang@amd.com>
Cc: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/gfx: fix ref counting for ring based profile handling

We need to make sure the workload profile ref counts are
balanced.  This isn't currently the case because we can
increment the count on submissions, but the decrement may
be delayed as work comes in.  Track when we enable the
workload profile so the references are balanced.

v2: switch to a mutex and active flag
v3: fix mutex init

Fixes: 8fdb3958e396 ("drm/amdgpu/gfx: add ring helpers for setting workload profile")
Cc: Yang Wang <kevinyang.wang@amd.com>
Cc: Kenneth Feng <kenneth.feng@amd.com>
Tested-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: Fix bug in config_dequeue_wait_counts

For certain ASICs where dequeue_wait_count don't need to be initialized,
pm_config_dequeue_wait_counts_v9 return without filling in the packet
information. However, the calling function interprets this as a success
and sends the uninitialized packet to firmware causing hang.

Fix the above bug by not calling pm_config_dequeue_wait_counts_v9 for
ASICs that don't need the value to be initialized.

v2: Removed redudant code.
    Tidy up code based on review comments
v3: Don't call pm_config_dequeue_wait_counts_v9 for certain ASICs

Fixes: ed962f8d0603 ("drm/amdkfd: Add pm_config_dequeue_wait_counts API")
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon/uvd: Replace nested max() with single max3()

Use max3() macro instead of nesting max() to simplify the return
statement.

Signed-off-by: FengWei <feng.wei8@zte.com.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: grab an additional reference on the gang fence v2

We keep the gang submission fence around in adev, make sure that it
stays alive.

v2: fix memory leak on retry

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Use wafl version for xgmi

XGMI and WAFL share the same versions. Use WAFL version if XGMI version
is not present in discovery.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fix SDMA engine reset logic

The scheduler should restart only if the reset operation
succeeds  This ensures that new tasks are only submitted
to the queues after a successful reset.

Fixes: 4c02f7301657 ("drm/amdgpu: Introduce conditional user queue suspension for SDMA resets")
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse.Zhang <Jesse.zhang@amd.com>
Reviewed-by: Tim Huang <tim.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: Handle SCLK offset correctly in overdrive for smu 14.0.2

Currently, it seems like the code was carried over from RDNA3 because
it assumes two possible values to set. RDNA4, instead of having:
0: min SCLK
1: max SCLK
only has
0: SCLK offset

This change makes it so it only reports current offset value instead of
showing possible min/max values and their indices. Moreover, it now only
accepts the offset as a value, without the indice index.

Additionally, the lower bound was printed as %u by mistake.

Old:
OD_SCLK_OFFSET:
0: -500Mhz
1: 1000Mhz
OD_MCLK:
0: 97Mhz
1: 1259MHz
OD_VDDGFX_OFFSET:
0mV
OD_RANGE:
SCLK_OFFSET:    -500Mhz       1000Mhz
MCLK:      97Mhz       1500Mhz
VDDGFX_OFFSET:    -200mv          0mv

New:
OD_SCLK_OFFSET:
0Mhz
OD_MCLK:
0: 97Mhz
1: 1259MHz
OD_VDDGFX_OFFSET:
0mV
OD_RANGE:
SCLK_OFFSET:    -500Mhz       1000Mhz
MCLK:      97Mhz       1500Mhz
VDDGFX_OFFSET:    -200mv          0mv

Setting this offset:
Old: "s 1 <offset>"
New: "s <offset>"

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4036
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Tomasz Pakuła <tomasz.pakula.oficjalny@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: release xcp_mgr on exit

Free on driver cleanup.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Flora Cui <flora.cui@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: 3.2.325

This version brings along following fixes:
- Use DPM table clk setting for dml2 soc dscclk
- Update static soc table
- Fix incorrect fw_state address in dmub_srv
- Use HW lock mgr for PSR1 when only one eDP
- Revert "Support for reg inbox0 for host->DMUB CMDs"
- Change notification of link BW allocation
- Fix message for support_edp0_on_dp1
- Guard against setting dispclk low for dcn31x
- Prevent VStartup Overflow
- Check pipe->stream before passing it to a function

Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Use DPM table clk setting for dml2 soc dscclk

[WHY]
Not like dppclk/dispclk, dml2 will calculate the minimum required clocks.
For dscclk, it is used for pure comparision.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Charlene Liu <Charlene.Liu@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Update static soc table

[WHY]
Update the static soc table dcn3_5_soc.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Charlene Liu <Charlene.Liu@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Fix incorrect fw_state address in dmub_srv

[WHY]
The fw_state in dmub_srv was assigned with wrong address.
The address was pointed to the firmware region.

[HOW]
Fix the firmware state by using DMUB_DEBUG_FW_STATE_OFFSET
in dmub_cmd.h.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Lo-an Chen <lo-an.chen@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Use HW lock mgr for PSR1 when only one eDP

[WHY]
DMUB locking is important to make sure that registers aren't accessed
while in PSR.  Previously it was enabled but caused a deadlock in
situations with multiple eDP panels.

[HOW]
Detect if multiple eDP panels are in use to decide whether to use
lock. Refactor the function so that the first check is for PSR-SU
and then replay is in use to prevent having to look up number
of eDP panels for those configurations.

Fixes: f245b400a223 ("Revert "drm/amd/display: Use HW lock mgr for PSR1"")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3965
Reviewed-by: ChiaHsuan Chung <chiahsuan.chung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Revert "Support for reg inbox0 for host->DMUB CMDs"

This reverts commit 15d1c2e6bf60511ba068d7d735d051911c6c5b92.

Reason: Cursor movement causes system to hang.

Reviewed-by: Aric Cyr <aric.cyr@amd.com>
Signed-off-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Change notification of link BW allocation

[WHY & HOW]
The response of DP BW allocation is handled in Outbox ISR.
When it failed to request the DP BW allocation, it sent another
DPCD request in Outbox ISR immediately. The DP AUX reply also
uses the Outbox ISR. So, no AUX reply happened in this case.
Change to use HPD IRQ for the notification.

Reviewed-by: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Signed-off-by: Cruise Hung <Cruise.Hung@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Fix message for support_edp0_on_dp1

[WHY]
The info message was wrong when support_edp0_on_dp1 is enabled

[HOW]
Use correct info message for support_edp0_on_dp1

Fixes: f6d17270d18a ("drm/amd/display: add a quirk to enable eDP0 on DP1")
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Yilin Chen <Yilin.Chen@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Guard against setting dispclk low for dcn31x

[WHY]
We should never apply a minimum dispclk value while in
prepare_bandwidth or while displays are active. This is
always an optimizaiton for when all displays are disabled.

[HOW]
Defer dispclk optimization until safe_to_lower = true
and display_count reaches 0.

Since 0 has a special value in this logic (ie. no dispclk
required) we also need adjust the logic that clamps it for
the actual request to PMFW.

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Chris Park <chris.park@amd.com>
Reviewed-by: Eric Yang <eric.yang@amd.com>
Signed-off-by: Jing Zhou <Jing.Zhou@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Prevent VStartup Overflow

[WHY & HOW]
Fixed Overflow issue by clamping VStartup to max value of register.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Ryan Seto <ryanseto@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Check pipe->stream before passing it to a function

[WHAT & HOW]
dp_is_128b_132b_signal dereferences pipe->stream so it is necessary to
check it in advance.

Also fix erroneous spaces and move a variable declaration to top.

Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Add debug masks for HDCP LC FW testing

HDCP Locality Check is being moved to FW, add debug flags to control
its behavior in existing hardware for validation purposes.

Signed-off-by: Dominik Kaszewski <dominik.kaszewski@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fix computation for remain size of CPER ring

The mistake of computation for remain size of CPER ring will cause
unbreakable while cycle when CPER ring overflow.

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

drm/amd/amdgpu: shorten the gfx idle worker timeout

Shorten the gfx idle worker timeout. This is to sync with
DAL when there is no activity on the screen. Original 1
second can not sync with DAL, so DAL can not apply MALL
when the workload type is not bootup default.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: format old RAS eeprom data into V3 version

Clear old data and save it in V3 format.

v2: only format eeprom data for new ASICs.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: don't free conflicting apertures for non-display devices

PCI_CLASS_ACCELERATOR_PROCESSING devices won't ever be
the sysfb, so there is no need to free conflicting
apertures.

Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: adjust drm_firmware_drivers_only() handling

Move to probe so we can check the PCI device type and
only apply the drm_firmware_drivers_only() check for
PCI DISPLAY classes.  Also add a module parameter to
override the nomodeset kernel parameter as a workaround
for platforms that have this hardcoded on their kernel
command lines.

Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: drop drm_firmware_drivers_only()

There are a number of systems and cloud providers out there
that have nomodeset hardcoded in their kernel parameters
to block nouveau for the nvidia driver.  This prevents the
amdgpu driver from loading. Unfortunately the end user cannot
easily change this.  The preferred way to block modules from
loading is to use modprobe.blacklist=<driver>.  That is what
providers should be using to block specific drivers.

Drop the check to allow the driver to load even when nomodeset
is specified on the kernel command line.

Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Restore uncached behaviour on GFX12

Always use MTYPE_UC if UNCACHED flag is specified.

This makes kernarg region uncached and it restores
usermode cache disable debug flag functionality.

Do not set MTYPE_UC for COHERENT flag, on GFX12 coherence is handled by
shader code.

Signed-off-by: David Belanger <david.belanger@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/gfx12: correct cleanup of 'me' field with gfx_v12_0_me_fini()

In gfx_v12_0_cp_gfx_load_me_microcode_rs64(), gfx_v12_0_pfp_fini() is
incorrectly used to free 'me' field of 'gfx', since gfx_v12_0_pfp_fini()
can only release 'pfp' field of 'gfx'. The release function of 'me' field
should be gfx_v12_0_me_fini().

Fixes: 52cb80c12e8a ("drm/amdgpu: Add gfx v12_0 ip block support (v6)")
Signed-off-by: Wentao Liang <vulab@iscas.ac.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: avoid NPD when ASIC does not support DMUB

ctx->dmub_srv will de NULL if the ASIC does not support DMUB, which is
tested in dm_dmub_sw_init.

However, it will be dereferenced in dmub_hw_lock_mgr_cmd if
should_use_dmub_lock returns true.

This has been the case since dmub support has been added for PSR1.

Fix this by checking for dmub_srv in should_use_dmub_lock.

[   37.440832] BUG: kernel NULL pointer dereference, address: 0000000000000058
[   37.447808] #PF: supervisor read access in kernel mode
[   37.452959] #PF: error_code(0x0000) - not-present page
[   37.458112] PGD 0 P4D 0
[   37.460662] Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
[   37.465553] CPU: 2 UID: 1000 PID: 1745 Comm: DrmThread Not tainted 6.14.0-rc1-00003-gd62e938120f0 #23 99720e1cb1e0fc4773b8513150932a07de3c6e88
[   37.478324] Hardware name: Google Morphius/Morphius, BIOS Google_Morphius.13434.858.0 10/26/2023
[   37.487103] RIP: 0010:dmub_hw_lock_mgr_cmd+0x77/0xb0
[   37.492074] Code: 44 24 0e 00 00 00 00 48 c7 04 24 45 00 00 0c 40 88 74 24 0d 0f b6 02 88 44 24 0c 8b 01 89 44 24 08 85 f6 75 05 c6 44 24 0e 01 <48> 8b 7f 58 48 89 e6 ba 01 00 00 00 e8 08 3c 2a 00 65 48 8b 04 5
[   37.510822] RSP: 0018:ffff969442853300 EFLAGS: 00010202
[   37.516052] RAX: 0000000000000000 RBX: ffff92db03000000 RCX: ffff969442853358
[   37.523185] RDX: ffff969442853368 RSI: 0000000000000001 RDI: 0000000000000000
[   37.530322] RBP: 0000000000000001 R08: 00000000000004a7 R09: 00000000000004a5
[   37.537453] R10: 0000000000000476 R11: 0000000000000062 R12: ffff92db0ade8000
[   37.544589] R13: ffff92da01180ae0 R14: ffff92da011802a8 R15: ffff92db03000000
[   37.551725] FS:  0000784a9cdfc6c0(0000) GS:ffff92db2af00000(0000) knlGS:0000000000000000
[   37.559814] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   37.565562] CR2: 0000000000000058 CR3: 0000000112b1c000 CR4: 00000000003506f0
[   37.572697] Call Trace:
[   37.575152]  <TASK>
[   37.577258]  ? __die_body+0x66/0xb0
[   37.580756]  ? page_fault_oops+0x3e7/0x4a0
[   37.584861]  ? exc_page_fault+0x3e/0xe0
[   37.588706]  ? exc_page_fault+0x5c/0xe0
[   37.592550]  ? asm_exc_page_fault+0x22/0x30
[   37.596742]  ? dmub_hw_lock_mgr_cmd+0x77/0xb0
[   37.601107]  dcn10_cursor_lock+0x1e1/0x240
[   37.605211]  program_cursor_attributes+0x81/0x190
[   37.609923]  commit_planes_for_stream+0x998/0x1ef0
[   37.614722]  update_planes_and_stream_v2+0x41e/0x5c0
[   37.619703]  dc_update_planes_and_stream+0x78/0x140
[   37.624588]  amdgpu_dm_atomic_commit_tail+0x4362/0x49f0
[   37.629832]  ? srso_return_thunk+0x5/0x5f
[   37.633847]  ? mark_held_locks+0x6d/0xd0
[   37.637774]  ? _raw_spin_unlock_irq+0x24/0x50
[   37.642135]  ? srso_return_thunk+0x5/0x5f
[   37.646148]  ? lockdep_hardirqs_on+0x95/0x150
[   37.650510]  ? srso_return_thunk+0x5/0x5f
[   37.654522]  ? _raw_spin_unlock_irq+0x2f/0x50
[   37.658883]  ? srso_return_thunk+0x5/0x5f
[   37.662897]  ? wait_for_common+0x186/0x1c0
[   37.666998]  ? srso_return_thunk+0x5/0x5f
[   37.671009]  ? drm_crtc_next_vblank_start+0xc3/0x170
[   37.675983]  commit_tail+0xf5/0x1c0
[   37.679478]  drm_atomic_helper_commit+0x2a2/0x2b0
[   37.684186]  drm_atomic_commit+0xd6/0x100
[   37.688199]  ? __cfi___drm_printfn_info+0x10/0x10
[   37.692911]  drm_atomic_helper_update_plane+0xe5/0x130
[   37.698054]  drm_mode_cursor_common+0x501/0x670
[   37.702600]  ? __cfi_drm_mode_cursor_ioctl+0x10/0x10
[   37.707572]  drm_mode_cursor_ioctl+0x48/0x70
[   37.711851]  drm_ioctl_kernel+0xf2/0x150
[   37.715781]  drm_ioctl+0x363/0x590
[   37.719189]  ? __cfi_drm_mode_cursor_ioctl+0x10/0x10
[   37.724165]  amdgpu_drm_ioctl+0x41/0x80
[   37.728013]  __se_sys_ioctl+0x7f/0xd0
[   37.731685]  do_syscall_64+0x87/0x100
[   37.735355]  ? vma_end_read+0x12/0xe0
[   37.739024]  ? srso_return_thunk+0x5/0x5f
[   37.743041]  ? find_held_lock+0x47/0xf0
[   37.746884]  ? vma_end_read+0x12/0xe0
[   37.750552]  ? srso_return_thunk+0x5/0x5f
[   37.754565]  ? lock_release+0x1c4/0x2e0
[   37.758406]  ? vma_end_read+0x12/0xe0
[   37.762079]  ? exc_page_fault+0x84/0xe0
[   37.765921]  ? srso_return_thunk+0x5/0x5f
[   37.769938]  ? lockdep_hardirqs_on+0x95/0x150
[   37.774303]  ? srso_return_thunk+0x5/0x5f
[   37.778317]  ? exc_page_fault+0x84/0xe0
[   37.782163]  entry_SYSCALL_64_after_hwframe+0x55/0x5d
[   37.787218] RIP: 0033:0x784aa5ec3059
[   37.790803] Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <41> 89 c0 3d 00 f0 ff ff 77 1d 48 8b 45 c8 64 48 2b 04 25 28 00 0
[   37.809553] RSP: 002b:0000784a9cdf90e0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[   37.817121] RAX: ffffffffffffffda RBX: 0000784a9cdf917c RCX: 0000784aa5ec3059
[   37.824256] RDX: 0000784a9cdf917c RSI: 00000000c01c64a3 RDI: 0000000000000020
[   37.831391] RBP: 0000784a9cdf9130 R08: 0000000000000100 R09: 0000000000ff0000
[   37.838525] R10: 0000000000000000 R11: 0000000000000246 R12: 0000025c01606ed0
[   37.845657] R13: 0000025c00030200 R14: 00000000c01c64a3 R15: 0000000000000020
[   37.852799]  </TASK>
[   37.854992] Modules linked in:
[   37.864546] gsmi: Log Shutdown Reason 0x03
[   37.868656] CR2: 0000000000000058
[   37.871979] ---[ end trace 0000000000000000 ]---
[   37.880976] RIP: 0010:dmub_hw_lock_mgr_cmd+0x77/0xb0
[   37.885954] Code: 44 24 0e 00 00 00 00 48 c7 04 24 45 00 00 0c 40 88 74 24 0d 0f b6 02 88 44 24 0c 8b 01 89 44 24 08 85 f6 75 05 c6 44 24 0e 01 <48> 8b 7f 58 48 89 e6 ba 01 00 00 00 e8 08 3c 2a 00 65 48 8b 04 5
[   37.904703] RSP: 0018:ffff969442853300 EFLAGS: 00010202
[   37.909933] RAX: 0000000000000000 RBX: ffff92db03000000 RCX: ffff969442853358
[   37.917068] RDX: ffff969442853368 RSI: 0000000000000001 RDI: 0000000000000000
[   37.924201] RBP: 0000000000000001 R08: 00000000000004a7 R09: 00000000000004a5
[   37.931336] R10: 0000000000000476 R11: 0000000000000062 R12: ffff92db0ade8000
[   37.938469] R13: ffff92da01180ae0 R14: ffff92da011802a8 R15: ffff92db03000000
[   37.945602] FS:  0000784a9cdfc6c0(0000) GS:ffff92db2af00000(0000) knlGS:0000000000000000
[   37.953689] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   37.959435] CR2: 0000000000000058 CR3: 0000000112b1c000 CR4: 00000000003506f0
[   37.966570] Kernel panic - not syncing: Fatal exception
[   37.971901] Kernel Offset: 0x30200000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[   37.982840] gsmi: Log Shutdown Reason 0x02

Fixes: b5c764d6ed55 ("drm/amd/display: Use HW lock mgr for PSR1")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Cc: Sun peng Li <sunpeng.li@amd.com>
Cc: Tom Chung <chiahsuan.chung@amd.com>
Cc: Daniel Wheeler <daniel.wheeler@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/amdgpu: Fix MES init sequence

When MES is been used , the set_hw_resource_1 API is required to
initialize MES internal context correctly

Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Enable ACA by default for psp v13_0_6/v13_0_14

Enable ACA by default for psp v13_0_6/v13_0_14.

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

drm/amdkfd: Correct F8_MODE for gfx950

Correct F8_MODE setting for gfx950 that was removed

Fixes: 61972cd93af7 ("drm/amdkfd: Set per-process flags only once for gfx9/10/11/12")
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviwanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Save PA of bad pages for old asics

for old asics that do not support mca translating, we
just save PA for them

Signed-off-by: ganglxie <ganglxie@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: set CP_HQD_PQ_DOORBELL_CONTROL.DOORBELL_MODE to 1 for sriov multiple vf.

In sriov multiple vf, Set CP_HQD_PQ_DOORBELL_CONTROL.DOORBELL_MODE to 1 to read WPTR from MQD.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Add amdgpu_sriov_multi_vf_mode function

Use amdgpu_sriov_multi_vf_mode to replace amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev).

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

drm/amdgpu/pm: enable vcn busy sysfs for GC 9.3.0

Make it visible for the all GC 9.3.0 chips that support it.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: enable vcn busy sysfs for GC 12.x

Make it visible for the all GC 12.x chips that support it.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: Fix instruction hazard in gfx12 trap handler

VALU instructions with SGPR source need wait states to avoid hazard
with SALU using different SGPR.

v2: Eliminate some hazards to reduce code explosion

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Lancelot Six <lancelot.six@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: enable vcn busy sysfs for additional GC 11.x

Make it visible for the all GC 11.x chips that support it.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: add VCN activity for SMU 14.0.2

Wire up the query.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: add VCN activity for SMU 13.0.0/7

Wire up the query.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: Remove incorrect macro guard

This macro guard "__cplusplus" is unnecessary and should not be there.

Signed-off-by: Alex Hung <alex.hung@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Calculate IP specific xgmi bandwidth

Use IP version specific xgmi speed/width for bandwidth calculation.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: add VCN activity for renoir

Wire up the query.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/pm: wire up hwmon fan speed for smu 14.0.2

Add callbacks for fan speed fetching.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4034
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Reduce dequeue retry timeout for gfx9 family

Dequeue retry timeout controls the interval between checks for unmet
conditions. On MI series, reduce this from 0x40 to 0x1 (~ 1 uS). The
cost of additional bandwidth consumed by CP when polling memory
shouldn't be substantial.

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/pm: Update feature list for smu_v13_0_12

Update feature list for smu_v13_0_12 to show vcn & smu deep
sleep feature enable status.

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

drm/amdgpu/gfx12: don't read registers in mqd init

Just use the default values.  There's not need to
get the value from hardware and it could cause problems
if we do that at runtime and gfxoff is active.

Reviewed-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/gfx11: don't read registers in mqd init

Just use the default values.  There's not need to
get the value from hardware and it could cause problems
if we do that at runtime and gfxoff is active.

Reviewed-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fix the race condition for draining retry fault

Issue:
In the scenario where svm_range_restore_pages is called, but
svm->checkpoint_ts has not been set and the retry fault has not been
drained, svm_range_unmap_from_cpu is triggered and calls svm_range_free.
Meanwhile, svm_range_restore_pages continues execution and reaches
svm_range_from_addr. This results in a "failed to find prange..." error,
 causing the page recovery to fail.

How to fix:
Move the timestamp check code under the protection of svm->lock.

v2:
Make sure all right locks are released before go out.

v3:
Directly goto out_unlock_svms, and return -EAGAIN.

v4:
Refine code.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Remove unsupported xgmi versions

XGMI v4.8.0 is not used in any SOCs. Remove the associated functions.
Also, ensure get_xgmi_info callback pointer is not NULL before calling
the function.

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/pm: add unique_id for gfx12

Expose unique_id for gfx12

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

drm/amdgpu: Update SRIOV video codec caps

There have been multiple fixes to the video caps that are missing for
SRIOV. Update the SRIOV caps with correct values.

Signed-off-by: David Rosca <david.rosca@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Remove JPEG from vega and carrizo video caps

JPEG is only supported for VCN1+.

Signed-off-by: David Rosca <david.rosca@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fix JPEG video caps max size for navi1x and raven

8192x8192 is the maximum supported resolution.

Signed-off-by: David Rosca <david.rosca@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Fix MPEG2, MPEG4 and VC1 video caps max size

1920x1088 is the maximum supported resolution.

Signed-off-by: David Rosca <david.rosca@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/radeon: fix uninitialized size issue in radeon_vce_cs_parse()

On the off chance that command stream passed from userspace via
ioctl() call to radeon_vce_cs_parse() is weirdly crafted and
first command to execute is to encode (case 0x03000001), the function
in question will attempt to call radeon_vce_cs_reloc() with size
argument that has not been properly initialized. Specifically, 'size'
will point to 'tmp' variable before the latter had a chance to be
assigned any value.

Play it safe and init 'tmp' with 0, thus ensuring that
radeon_vce_cs_reloc() will catch an early error in cases like these.

Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.

Fixes: 2fc5703abda2 ("drm/radeon: check VCE relocation buffer range v3")
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: NULL-check BO's backing store when determining GFX12 PTE flags

PRT BOs may not have any backing store, so bo->tbo.resource will be
NULL. Check for that before dereferencing.

Fixes: 0cce5f285d9a ("drm/amdkfd: Check correct memory types for is_system variable")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Natalie Vock <natalie.vock@gmx.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: finish wiring up sid.h in DCE6

For coherence with DCE8 et DCE10, add or move some values under sid.h
and remove duplicated from si_enums.h.

Signed-off-by: Alexandre Demers <alexandre.f.demers@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/amdkfd: Evict all queues even HWS remove queue failed

[Why]
If reset is detected and kfd need to evict working queues, HWS moving queue will be failed.
Then remaining queues are not evicted and in active state.

After reset done, kfd uses HWS to termination remaining activated queues but HWS is resetted.
So remove queue will be failed again.

[How]
Keep removing all queues even if HWS returns failed.
It will not affect cpsch as it checks reset_domain->sem.

v2: If any queue failed, evict queue returns error.
v3: Declare err inside the if-block.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Yifan Zha <Yifan.Zha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: fix SI's GB_ADDR_CONFIG_GOLDEN values and wire up sid.h in GFX6

By wiring up sid.h in GFX6, we end up with a few duplicated defines such as
the golden registers. Let's clean this up.

[TAHITI,VERDE, HAINAN]_GB_ADDR_CONFIG_GOLDEN were defined both in sid.h
and under si_enums.h, with different values. Keep the values used under radeon
and move them under gfx_v6_0.c where they are used (as it is done under cik)

Signed-off-by: Alexandre Demers <alexandre.f.demers@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: prepare DCE6 uniformisation with DCE8 and DCE10

Let's begin the cleanup in sid.h to prevent warnings and errors when wiring
sid.h into dce_v6_0.c.

This is a bigger cleanup.
Many defines found under sid.h have already been properly moved
into the different "_d.h" and "_sh_mask.h", so they should have been
already removed from sid.h and properly linked in where needed.

Signed-off-by: Alexandre Demers <alexandre.f.demers@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdkfd: delete stray tab in kfd_dbg_set_mes_debug_mode()

These lines are indented one tab more than they should be.  Delete
the stray tabs.

Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/gfx: delete stray tabs

These lines are indented one tab too far.  Delete the extra tabs.

Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu: Trigger a wedged event for ring reset

Instead of only triggering a wedged event for complete GPU resets,
trigger for ring resets. Regardless of the reset, it's useful for
userspace to know that it happened because the kernel will reject
further submissions from that app.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: André Almeida <andrealmeid@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amdgpu/vce2: fix ip block reference

Need to use the correct IP block type.  VCE vs VCN.
Fixes mclk issues on Hawaii.

Suggested by selendym.

Fixes: 82ae6619a450 ("drm/amdgpu: update the handle ptr in wait_for_idle")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3997
Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Cc: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: change kzalloc to kcalloc in dml1_validate()

We are trying to get rid of all multiplications from allocation
functions to prevent integer overflows. Here the multiplication is
probably safe, but using kcalloc() is more appropriate and improves
readability. This patch has no effect on runtime behavior.

Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drm/amd/display: change kzalloc to kcalloc in dcn314_validate_bandwidth()

We are trying to get rid of all multiplications from allocation
functions to prevent integer overflows. Here the multiplication is
probably safe, but using kcalloc() is more appropriate and improves
readability. This patch has no effect on runtime behavior.

Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>