Add missing operations to commit_planes_for_stream_fast and
hwss_build_fast_sequence to match the legacy commit_planes_for_stream
behavior for UPDATE_TYPE_FAST updates.
- Add stream-level fast update flags (cursor_attr, cursor_pos,
periodic_interrupt, info_frame, dmdata, dither) to dc_stream.h
- Add stream-level fields to dc_fast_update struct for fast/full
update classification in populate_fast_updates/fast_updates_exist
- Add HWSS_SETUP_PERIODIC_INTERRUPT block sequence entry, delegating
to dc->hwss.setup_periodic_interrupt instead of calling dcn10
directly
- Add HUBP_ENABLE_3DLUT_FL block for 3DLUT FL with
should_update_pipe_for_stream/plane guards
- Add DPP_SET_CURSOR_MATRIX block with new cursor_csc_change flag
- Widen DPP_PROGRAM_GAMUT_REMAP to also trigger on stream gamut_remap
- Add info frame, dmdata, dither, and cursor blocks to
hwss_build_fast_sequence
- Reclassify cursor_position/cursor_attributes as UPDATE_TYPE_FAST
- Extract dc_dmdata_types.h to resolve circular include between
hw_sequencer.h and dc_stream.h
- Remove dcn10_hwseq.h include from dc_hw_sequencer.c
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Rafal Ostrowski <rafal.ostrowski@amd.com>
Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why & How]
There will be an unexpected desync error while doing PSR -> Replay transit,
so we want to disable the replay desync error detection by default.
Reviewed-by: Robin Chen <robin.chen@amd.com>
Signed-off-by: Allen Li <allen.li@amd.com>
Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove all references to dml2_project_dcn40 from dml2.
The project is not used.
Signed-off-by: Roman Li <roman.li@amd.com>
Acked-by: Chenyu Chen <chen-yu.chen@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
This aligns dcn42 with:
"drm/amd/display: bypass post csc for additional color spaces in dal"
[How]
Apply the same post csc bypass logic to dcn42 dpp using the
helper function.
Signed-off-by: Roman Li <roman.li@amd.com>
Acked-by: Chenyu Chen <chen-yu.chen@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
The allow_clock_gating function is present in all other DCN versions
and is required to properly migrate DCCG registers access from hwseq
to the dccg component, resolving register conflicts.
[How]
Add the missing .allow_clock_gating function pointer to the
dccg42_funcs struct.
Signed-off-by: Roman Li <roman.li@amd.com>
Acked-by: Chenyu Chen <chen-yu.chen@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add header files for gc v12_1_1 register offsets
and shift masks
v2: Update gc v12_1_1 ip headers
v3: Update gc v12_1_1 ip headers
Signed-off-by: Bing Ma <Bing.Ma@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Update mes_v12_1_suspend and mes_v12_1_resume to line up with mes_v12_0.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Create hung_queue_hqd_info structure and fill in hung queses information
passed by MES, including queue type, pipe id, and queue id.
Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Identify hung queues by comparing doorbells shown in hqd_info from MES
with doorbells stored in the driver to find matching queues.
Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When allocate the hung queues memory, we need to take the number of
queues into account for the worst hang case.
Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The init_mqd_v12_1 function and its sub-call update_mqd_v12_1 both independently
iterate over XCC-specific MQDs. This nested iteration is redundant and can cause
MQDs in different queues to be overwritten. This patch removes the duplicate
loop logic to prevent queue corruption.
Fixes: 01bbc4a4b9 ("drm/amdkfd: Add MQD manager for GFX 12.1.0")
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Limit mc_vram_size to node_segment_size to prevent allocations
to prevent allocations on remote HBM.
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On A+A, psp requires firmware bo be placed on VRAM.
Signed-off-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
After init mes queue, it require some time for mes to execute init
code including setup version info in CP_MES_GP3 register. Put it after
first MES call(set_hw_resource package).
Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
From MES version 0x74 and above, pipe 1(kiq) support use the
shared command buffer to distribute the tasks among the xccs
within the same partition. It's more efficient for tlb invalidation
been done individually on the each XCC at the same time compare
to let master xcc loop all xccs.
This requires the coop_mode been set before kiq set_hw_resource.
Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Michael Chen <michael.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Support for TOC fw load for psp v15_0_8 rev id 0.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add support to load rlc firmware for rev_id 0 of gfx v12_1.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add logging for thermal events in SMUv15.0.8 SOCs
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>
Add mem temp to gpu metrics as maximum hbm stack temperature
for smu_v15_0_8
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add partition metrics support for smu_v15_0_8
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Increase reserved memory to 150 MB.
v2: squash in fixes (Alex)
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Update CP command package for gfx v12.1.
1. Update to common command pkg format for PACKET3_ACQUIRE_MEM.
2. Update to definition PACKET3_PRED_EXEC command pkt.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Same as compute and sdma, gfx_hqd_mask has been initialized properly in
amdgpu_mes_init. set_hw_res should use those initialization accordingly.
Hardcoding it causes the mismatch between driver and MES.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amdgpu_gem_align_pitch() is passed u32 width and cpp from dumb buffer
creation but uses signed int internally. The round-up add and the
aligned * cpp multiplication can overflow, returning zero or a negative
pitch. A zero pitch propagates to a zero-sized GEM object allocation
that reaches userspace via DRM_IOCTL_MODE_CREATE_DUMB.
Switch the helper to unsigned int and use check_add_overflow() /
check_mul_overflow() so wraparound returns zero. Reject a zero pitch
or size in amdgpu_mode_dumb_create() rather than allocating a zero-
byte BO.
Fixes: 8e911ab770 ("drm: amdgpu: Replace drm_fb_get_bpp_depth() with drm_format_plane_cpp()")
Signed-off-by: Werner Kasselman <werner@verivus.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Replace sprintf() with snprintf() to fix the -Werror=format-overflow
warning when building with allmodconfig:
drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c:152:47: error: '%d' directive
writing between 1 and 11 bytes into a region of size 7
[-Werror=format-overflow=]
152 | sprintf(ring->name, "jpeg_dec_%d", i);
The ring->name buffer is 16 bytes. Using snprintf() with sizeof()
ensures the buffer cannot overflow regardless of the integer value.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In dce6_available_bandwidth() and dce8_available_bandwidth(), replace
nested min() calls with min3().
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove Q10 rounding when applying smu_v15_0_8 static metrics
to the driver PPTable as the firmware now provide raw data
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
ttm jobs must have higher priority than any userspace jobs.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Makes a code slightly clearer and reduces indentation.
---
v5: use amdgpu_in_reset in amdgpu_ttm_disable_buffer_funcs
---
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This is the only use case for this function.
---
v2: amdgpu_ttm_clear_buffer instead of amdgpu_clear_buffer
---
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's doing the same thing as amdgpu_fill_buffer(src_data=0), so drop it.
The only caveat is that amdgpu_res_cleared() return value is only valid
right after allocation.
---
v2: introduce new "bool consider_clear_status" arg
v6: dont pass a NULL resv when calling amdgpu_fill_buffer from
amdgpu_bo_create
---
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
With this change we now have as many clear and move entities as we
have sdma engines (limited to TTM_NUM_MOVE_FENCES).
To enable load-balancing this patch gives access to all sdma
schedulers to all entities, except default_entity which has no
use for multiple schedulers.
---
v6: add comment
---
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This enables parallelism of operations.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's possible that some sdma instances aren't working so we shouldn't try
to use them from TTM. To achieve this, delay the call to
amdgpu_sdma_set_buffer_funcs_scheds after the rings have been tested, and
then use the 'ready' property to decide if a sched should be used or not.
Note that currently it's not doing much, because if the ring helper fails
for any ring, the whole sdma block init fails.
---
v5: check buffer_funcs_enabled from amdgpu_ttm_access_memory_sdma
---
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This will allow the use of all of them for clear/fill buffer
operations.
Since drm_sched_entity_init requires a scheduler array, we
store schedulers rather than rings. For the few places that need
access to a ring, we can get it from the sched using container_of.
Since the code is the same for all sdma versions, add a new
helper amdgpu_sdma_set_buffer_funcs_scheds to set buffer_funcs_scheds
based on the number of sdma instances.
Note: the new sched array is identical to the amdgpu_vm_manager one.
These 2 could be merged.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amdgpu_userq_wait_ioctl() takes extra references on waited-on fence
drivers and stores them in waitq->fence_drv_xa. When a new userq fence is
created, those references are transferred into userq_fence->fence_drv_array
so they can be released when the fence completes.
However, those inherited references are currently only dropped from
amdgpu_userq_fence_driver_process(). If a fence never reaches that path,
such as it is already signaled when created, so we need to explicitly release
those fences in that case.
v2: use a list(list_cut_before) for managing the signal userq driver fences.(Christian)
Link: https://patchwork.freedesktop.org/patch/718078/?series=164763&rev=2
v3: Doesn't cache the userq first unsignaled fence and use the cut before list
head directly.(Christian)
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In amdgpu_userq_destroy once unmap_helpder is called within mutex
there is no need to hold mutex.
This helps in avoiding a deadlock between doorbell and wptr ww mutex
and we could unpin and unref these bos outside mutex safely.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use pm_runtime_resume_and_get instead of pm_runtime_get_sync as it
return error but put the reference in the function itself.
In goto statements we need to drop the pm reference too.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We check for return value of amdgpu_userq_unmap_helper and
compare it against the queue->state which is logically
wrong and we should just check for failure and do the needfull.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Unmap the queue after freeing doorbell and wptr memory is completely
wrong. Any operation on the queue needs the doorbell and wptr to be
valid and hence fixing the ordering.
Also since we are using amdgpu_bo_reserve in non interruptrable mode
so there is no need to check for its return values.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Caller should hold the reservation lock for root.bo in func
amdgpu_userq_input_va_validate.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In function amdgpu_userq_buffer_vas_list_cleanup, remove the
reservation lock for vm and caller should make sure it's taken
before locking userq_mutex.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reshuffle the code to run create_mqd outside the mutex.
code here is mostly setting up software structure init
before actually registering the userqueue in the xa and
to the driver.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Do not hold reservation lock for root bo if userq_mutex
is already held in the call flow this cause a lock
issue with ttm_bo_delayed_delete.
Its better to lock the vm->root.bo first and then go ahead
with userq_mutex so userq_mutex threads dont get stuck until
the reservation lock is held.
In this case it helps in the function amdgpu_userq_buffer_vas_mapped
for each queue during restore_all.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move the comment for the caller to the definition for
amdgpu_userq_ensure_ev_fence in kerneldoc format.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
