[WHY]
amdgpu_dm_plane_fill_blending_from_plane_state added drm_to_adev() but
dm_test_fill_blending_global_alpha did not initialize
plane_state->plane, causing a NULL pointer dereference.
[HOW]
Add an amdgpu_device and drm_plane so the plane->dev
dereference is valid in the test.
Fixes: 829769f1cf ("drm/amd/display: scale plane global alpha to 12 bits on DCN 4.2")
Cc: PingLei.Lin@amd.com
Assisted-by: Copilot:Claude-Opus-4.6
Reviewed-by: Bhawanpreet Lakha <bhawanpreet.lakha@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
On DCN 4.2 the global alpha is reported using 12 bits
(MPCC_GLOBAL_ALPHA spans bits [0:11]), whereas other ASICs such as
DCN 3.1.4 use an 8-bit field (MPCC_GLOBAL_ALPHA spans bits
[16:23]). The DRM plane alpha property is 16-bit and amdgpu_dm
unconditionally scaled it down by >> 8, which only matches the 8-bit
hardware field. On DCN 4.2 this fed a value that was 4 bits too small
into the 12-bit field, so the hardware applied the wrong global alpha
and the resulting blended output did not match the expected hw * alpha
value.
[how]
Detect DCN 4.2 via amdgpu_ip_version(adev, DCE_HWIP, 0) and scale the
16-bit plane alpha by >> 4 to fill the 12-bit MPCC_GLOBAL_ALPHA field.
All other ASICs keep the existing >> 8 behavior for their 8-bit field.
Reviewed-by: ChiaHsuan (Tom) Chung <chiahsuan.chung@amd.com>
Signed-off-by: James Lin <PingLei.Lin@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHAT]
Use an early guard for invalid DMUB notify callback registration inputs.
This keeps the same accepted and rejected cases while removing the
redundant else block.
Assisted-by: Copilot:GPT-5
Reviewed-by: Chen-Yu Chen <chen-yu.chen@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHAT]
Use direct boolean in connector and IRQ code paths. This removes
redundant comparisons around MST state, IRQ validation, handler
removal, and DMUB notification offload without changing behavior.
Assisted-by: Copilot:GPT-5
Reviewed-by: Chen-Yu Chen <chen-yu.chen@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add kunit tests for some functions in amdgpu_dm_plane.
Assisted-by: Copilot:Claude-Opus-4.8
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Bhawanpreet Lakha <bhawanpreet.lakha@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHAT]
Add KUnit coverage for amdgpu_dm_initialize_default_pipeline()
using an amdgpu_device-backed DRM mock so drm_to_adev() and
the DC color capability checks are exercised.
Assisted-by: Copilot:GPT-5.5
Reviewed-by: Bhawanpreet Lakha <bhawanpreet.lakha@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHAT]
Extract shared backlight device index lookup and property
setup into testable helpers. The duplicated bd-to-index
scan in update_status/get_brightness is replaced by
amdgpu_dm_backlight_get_device_index(), and the inline
backlight_properties calculation is replaced by
amdgpu_dm_backlight_fill_props().
Add KUnit coverage for both new helpers. Keep the runtime
power_supply_is_system_supplied() call at the caller so
the helpers remain pure and deterministic under test.
Assisted-by: Copilot:GPT-5.5
Reviewed-by: Bhawanpreet Lakha <bhawanpreet.lakha@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
The compound condition checking dp_connector_no_native_i2c
and no_ddc_pin was duplicated across many files, obscuring
intent at every call site.
[How]
Add bool force_i2c_over_aux to struct dc_link, initialized
once during link creation. Add link_get_ddc_aux_inst()
helper to select the correct aux instance. Wire into
link_service via construct_link_service_ddc(). Replace all
duplicated condition checks and aux instance selection
blocks with the new field and helper. No functional change.
Reviewed-by: Nevenko Stupar <nevenko.stupar@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why & How]
- Added link bw to switch case
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Relja Vojvodic <Relja.Vojvodic@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
set_queue_properties_from_criu() divided the checkpointed control stack
size by NUM_XCC(adev->gfx.xcc_mask) (whole GPU), while the checkpoint
size was recorded, the MQD buffer allocated, and the control stack
restored using the per-node mask NUM_XCC(mm->dev->xcc_mask). On spatially
partitioned GFX9.4.3 (CPX/QPX) these differ, so the per-XCC control stack
size used for the restore memcpy could exceed the region sized for the
MQD allocation, writing past the BO into adjacent kernel memory; it also
broke legitimate restore on partitioned parts.
Divide by the per-node XCC count so allocation and copy agree,
leaving kfd_queue_acquire_buffers() to bound the size against
the node's advertised control stack size.
Signed-off-by: Yongqiang Sun <Yongqiang.Sun@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit 36b6c723d8.
It introduced a regression on gfx11: the kfd negative test failed.
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
for GFX9.4.2 and above.
-v2: keep APU with GTT allocation
-v3: use dev->adev->apu_prefer_gtt instead
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Vladimir Indic <vladimir.indic@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This change allows amdgpu_amdkfd_gpuvm_map_bo_to_kernel() to pin buffers
in either GTT or VRAM based on caller specification, providing flexibility
for different memory placement requirements across various kernel buffers.
The domain parameter accepts AMDGPU_GEM_DOMAIN_GTT, AMDGPU_GEM_DOMAIN_VRAM,
or their combination (GTT|VRAM) to let amdgpu_bo_pin() choose the optimal
placement via amdgpu_bo_get_preferred_domain(). This flexible validation
allows callers to specify their preference while delegating final placement
decisions to the driver when appropriate.
CPU visibility is automatically enforced by amdgpu_bo_pin() regardless of
the domain parameter (see amdgpu_bo_pin() line 975-976 which sets
AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED for kernel mappings).
-v3: update amdgpu_amdkfd_gpuvm_map_bo_to_kernel description
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Vladimir Indic <vladimir.indic@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
struct dc has grown large over time (most of it the two inlined
dc_scratch_space copies) and now sits close to the page allocator's 4 MiB
contiguous allocation limit. Its actual size is not fixed by the source
alone, it also depends on the compiler and the .config, so it can easily
cross 4 MiB, e.g. with a newer GCC or a config change.
dc_create() allocates it with kzalloc(). Once struct dc exceeds 4 MiB the
request is rounded up to order 11 (8 MiB), which is above MAX_PAGE_ORDER,
so the page allocator warns and returns NULL. dc_create() then fails, DM
init fails and amdgpu probe aborts with -EINVAL:
WARNING: mm/page_alloc.c:5197 at __alloc_frozen_pages_noprof+0x2f9/0x380
dc_create+0x38/0x660 [amdgpu]
amdgpu_dm_init+0x2d9/0x510 [amdgpu]
dm_hw_init+0x1b/0x90 [amdgpu]
amdgpu_device_init.cold+0x150d/0x1e13 [amdgpu]
amdgpu_driver_load_kms+0x19/0x80 [amdgpu]
amdgpu_pci_probe+0x1e2/0x4c0 [amdgpu]
dc_create() then returns NULL and DM init fails, which aborts the whole
GPU init and makes amdgpu probe fail with -EINVAL ("hw_init of IP block
<dm> failed -22"), leaving the display unusable. The subsequent
amdgpu_irq_put() warnings during teardown are just fallout of unwinding
a half-initialized device.
struct dc is a software-only bookkeeping structure that is never handed
to hardware DMA and is only ever kept as an opaque pointer, so it does
not require physically contiguous memory. Allocate it with kvzalloc()
(and free it with kvfree()) so that the allocator can fall back to
vmalloc() when a contiguous allocation of that size is not available,
which also avoids the MAX_PAGE_ORDER warning entirely.
v2:
- Rebase to amd-staging-drm-next.
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5406
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Honglei Huang <honghuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When creating an user-queue, the user space
provides a doorbell BO handle and an offset within
the bo to obtain a doorbell.
However current implementation using xa_store_irq()
to store a doorbell, which allows a later queue created
with the same BO and offset parameters to overwrite an
existing queue and doorbell mapping.
This can cause problems like misrouting fence IRQ
processing to a wrong queue, and mislead the cleanup
process of one queue erasing the mapping of another queue.
This commit fixes this issue by replacing xa_store_irq with
xa_insert_irq, which rejects mapping a reserved
doorbell to a newly created queue
Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amdgpu_xcp_select_scheds() reads the per-XCP scheduler list.
Partition switching rebuilds the same table under xcp_lock.
Take xcp_lock around XCP scheduler selection and release.
This prevents readers from observing partially rebuilt state.
Also revalidate the selected XCP id before indexing the table.
An open file can outlive a switch to another partition mode.
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>
vddInd, vddciInd and mvddInd from VBIOS-parsed tables index into vddc,
vddci and vddmem lookup tables without bounds checks across nine sites.
Return -EINVAL when any index is out of range.
Fixes: f83a999164 ("drm/amd/powerplay: add Vega10 powerplay support (v5)")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
vddInd and vddcInd fields from VBIOS-parsed tables are used to index into
voltage lookup tables without a bounds check. Return -EINVAL when any
index is out of range.
Fixes: c82baa2818 ("drm/amd/powerplay: add Tonga dpm support (v3)")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v1:
Tonga PPTable parsing also relies on VBIOS offsets, revision fields
and entry counts for several subtables. Malformed data can cause
out-of-bounds reads, while voltage lookup tables can overrun their
fixed-size destination arrays.
Add common bounds helpers and validate fixed subtables, dynamic entry
arrays and revision-specific layouts before consuming voltage lookup,
dependency, PCIE, power-tune, hard-limit, thermal, fan, GPIO, PPM and
VCE state data.
v2:
correct to handle get_tonga_ppm_table() return value.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v1:
Vega10 PPTable parsing uses VBIOS-provided offsets, revision fields
and entry counts to locate subtables. Malformed data can otherwise
drive out-of-bounds reads from soft_pp_table_size, and voltage lookup
tables can overrun their fixed-size destination arrays.
Add shared bounds helpers and validate fixed-size subtables, dynamic
entry arrays and revision-specific layouts before consuming thermal,
fan, power-tune, clock dependency, PCIE, hard-limit and voltage lookup
data.
v2:
if ucRevId is not matched, fallback to default table size instead of returning -EINVAL.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
processpptables.c walks several variable-length PPLIB tables by
using offsets from the VBIOS PowerPlay table. Some paths dereference
extended headers, state arrays, clock arrays, non-clock arrays, or VCE
records before checking that the referenced data is inside the table
buffer.
Add local bounds helpers and validate the relevant offsets and entry
sizes before dereferencing them. This prevents truncated or malformed
legacy PowerPlay tables from driving out-of-bounds reads during hwmgr
initialization and table entry lookup.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The Vega hwmgr PowerPlay table parsers read fixed table fields,
state array entries, or SMC PPT fields before validating that the
VBIOS table buffer covers those structures. A truncated table can
therefore lead to out-of-bounds reads during hwmgr initialization.
Reject tables smaller than the fixed PowerPlay table. For Vega10, also
validate the state array offset and entry range before dereferencing
the state array.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
process_pptables_v1_0.c builds the Tonga state array pointer
from usStateArrayOffset before checking that the table buffer covers
the referenced data. A truncated PowerPlay table can therefore lead to
out-of-bounds reads while validating the state array.
Validate the fixed table size first, then check the state array offset
and entry range before dereferencing the state array.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove unnecessary SIGNAL_TYPE_HDMI_TYPE_A check that was performed in the
drm_mode_is_420_only() case, but not in the drm_mode_is_420_also() &&
force_yuv420_output case.
Without further knowledge if YCbCr 4:2:0 is supported outside of HDMI,
there is no reason to use RGB when the display
reports drm_mode_is_420_only() even on a non HDMI connection.
This patch also moves both checks in the same if-case. This eliminates an
extra else-if-case.
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Signed-off-by: Andri Yngvason <andri@yngvason.is>
Tested-by: Andri Yngvason <andri@yngvason.is>
Reviewed-by: Daniel Stone <daniel@fooishbar.org>
Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The mode-setting pipeline can disabled damage clippings for a commit
by setting ignore_damage_clips in struct drm_plane_state. The commit
will then do a full display update.
Test the flag in DCN code and do a full update in DCN code if it has
been set.
Commit 35ed38d582 ("drm: Allow drivers to indicate the damage helpers
to ignore damage clips") introduced ignore_damage_clips to selectively
ignore damage clipping in certain framebuffer changes. This driver does
not do that, but DRM's damage iterator will soon rely on the flag.
Therefore supporting it here as well make sense for consistency.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 35ed38d582 ("drm: Allow drivers to indicate the damage helpers to ignore damage clips")
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Zack Rusin <zackr@vmware.com>
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Same write-OOB and read-OOB as the Tonga fix, across seven Vega10 sub-table
parsers: get_vddc_lookup_table(), get_mm_clock_voltage_table(),
get_socclk/mclk/gfxclk/pixclk/dcefclk_voltage_dependency_table().
The GFXCLK table selects the correct record size per revision.
Fixes: f83a999164 ("drm/amd/powerplay: add Vega10 powerplay support (v5)")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
ucNumEntries in the Tonga/Polaris PowerPlay sub-tables is used as both the
kzalloc count and loop bound without validation, allowing a crafted VBIOS
to overflow the destination heap object and read past the VBIOS image.
Clamp via pp_entries_max() in get_vddc_lookup_table(),
get_mclk_voltage_dependency_table(), get_sclk_voltage_dependency_table()
and get_mm_clock_voltage_table().
Fixes: c82baa2818 ("drm/amd/powerplay: add Tonga dpm support (v3)")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add a static inline that returns the maximum safe record count for a
PowerPlay sub-table, bounded by the lesser of soft_pp_table_size and
adev->bios_size. Uses adev->bios directly to avoid a dependency on
struct atom_context. Subsequent patches use it to clamp ucNumEntries.
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reject voltage objects whose usSize is smaller than the header or would
advance the cursor past the table end, preventing an infinite loop or
heap OOB read when the VBIOS supplies a malformed VoltageObjectInfo table.
Fixes: c82baa2818 ("drm/amd/powerplay: add Tonga dpm support (v3)")
Fixes: 0d2c7569e1 ("drm/amdgpu: add new atomfirmware based helpers for powerplay")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
CRIU checkpoint copies the MQD control stack using cp_hqd_cntl_stack_size
from hardware without bounding it to the allocated BO region. If the HW
field is larger than the queue's control stack allocation, memcpy reads
past the BO into adjacent GTT memory and can leak kernel data to userspace.
Store the page-aligned control stack BO size in mqd_manager and clamp
checkpoint copies and reported checkpoint sizes to
min(cp_hqd_cntl_stack_size, mm->ctl_stack_size). Apply the same bound
for multi-XCC v9.4.3 checkpoint layout.
Signed-off-by: Yongqiang Sun <Yongqiang.Sun@amd.com>
Reviewed-by: David Francis <David.Francis@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amdgpu_pci_remove() calls drm_dev_unplug() before invoking the driver
fini routines. This causes drm_dev_enter() in amdgpu_ttm_fini() to
always return false, so iounmap(aper_base_kaddr) never runs on normal
driver unload, leaving an orphaned entry in the x86 PAT interval tree.
On connected_to_cpu hardware, the aperture is mapped write-back (WB) via
ioremap_cache(). On reload, IP discovery calls memremap(..., MEMREMAP_WC)
over the same range. The WC vs WB conflict causes:
ioremap error for 0x..., requested 0x1, got 0x0
amdgpu: discovery failed: -2
Fix by switching to devres-managed mappings so cleanup is guaranteed
regardless of drm_dev_enter() state:
- connected_to_cpu path: devm_memremap(MEMREMAP_WB). For
IORESOURCE_SYSTEM_RAM ranges this takes the try_ram_remap() shortcut,
returning __va(offset) from the existing kernel direct map. No new
ioremap VA or PAT entry is created, so there is nothing to orphan.
- dGPU path: devm_ioremap_wc() registers iounmap() as a devres action,
guaranteeing cleanup at device_del() time.
Also remove iounmap(aper_base_kaddr) from amdgpu_device_unmap_mmio()
since the mapping is now devres-owned.
v2: Remove redundant x86_64 guard (Lijo)
Fixes: 9d0af8b4de ("drm/amdgpu: pre-map device buffer as cached for A+A config")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
check sel_xcp_id before its use
Signed-off-by: Gangliang Xie <ganglxie@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The legacy powerplay path used to allocate hardcode_pp_table from
the original VBIOS PPTable size, copy only the uploaded bytes into it,
and keep soft_pp_table_size unchanged. If a custom PPTable is shorter
than the original table, later code can still treat the stale tail as
valid table data.
Treat the uploaded buffer as the complete custom PPTable: duplicate the
uploaded buffer directly, replace hardcode_pp_table atomically, and set
soft_pp_table_size to the uploaded size.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
smu_sys_set_pp_table() reads usStructureSize from the uploaded
pp_table buffer before validating that the buffer contains a complete
ATOM_COMMON_TABLE_HEADER. A short write can therefore make the driver
read past the supplied sysfs buffer.
Reject empty or header-short uploads before dereferencing the header
pointer.
Keep the existing structure-size check for the full uploaded table.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This adds queue reset support in KFD topology for gfx12.0.0 and
gfx12.0.1 on non-sriov mode.
Signed-off-by: Amber Lin <amber.lin@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Try KQ by ring_id first (KCQ and UQ never share a HW slot); fall back
to amdgpu_userq_process_fence_irq() on miss, since KCQ EOPs were
misrouted into the userq fence path when enable_mes is true.
Require a strict (me,pipe,queue) match in the gfx case, then userq gfx
EOPs fall through to amdgpu_userq_process_fence_irq().
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Try KQ by ring_id first (KCQ and UQ never share a HW slot); fall back
to amdgpu_userq_process_fence_irq() on miss, since KQ EOPs were
misrouted into the userq fence path when enable_mes is true.
Require a strict (me,pipe,queue) match in the gfx case, then userq gfx
EOPs fall through to amdgpu_userq_process_fence_irq().
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Call the new userq reset helper, and dispatch KQs first by ring_id
before falling back to the user-queue lookup.
v2: squash in fixes
Co-developed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Call pm_genpd_remove() to unregister from global list prior to releasing
acp_genpd memory, and clear the pointer after free.
Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When ACP soft reset poll times out, original code returns early without cleanup,
leaking MFD child devices, genpd links and all ACP heap allocations.
Replace direct early return with goto out to force run all cleanup logic
regardless of reset success, preserve timeout error code for caller.
Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When linearizing, the input is an encoded signal bounded to [0,1] and
PQ/sRGB EOTFs are steepest near 1, requiring more precision near the
bright end.
Take the 8-bit sRGB case as a reference: 256 possible inputs and 256 HW
LUT points line up, so the LUT acts as plain indexing. Float
representations don't land perfectly, but LERP-ing between two HW
entries, when input is within a small epsilon of one of them, doesn't
materially change the result.
Replace the uniform 12-region distribution (16 points each,
192 total, range [2^-12, 1]) with a 9-region halving distribution for
the PQ/sRGB pre-defined EOTF: 128 points in the top region [0.5, 1], 64
in the next, 32 in the next, and so on, down to 1 point in each of the
two darkest regions. Total samples grow from 192 to 256, with uniform
1/256 spacing across [0, 1]. The dark tail below 2^-9 is no longer
sampled separately, which is acceptable for PQ/sRGB.
Suggested-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
cm3_helper_translate_curve_to_degamma_hw_format() reads one tf_pts entry
per HW LUT point, limiting the number of samples per region to
NUMBER_SW_SEGMENTS (16, at seg_distr[k] = 4) - higher seg_distr[k]
underflows the increment to 0. But the next patch introduces a halving
distribution for PQ/sRGB EOTFs that requires up to 128 samples in its
upper region (seg_distr[k] = 7).
As preparation, extend the loop index by 4 bits and linearly interpolate
adjacent tf_pts entries with the new interp_tf_pts() helper, where the 4
least significant bits are weight in 1/16 increments. This raises the
cap to 256 samples per region (seg_distr[k] = 8). seg_distr[k] <= 4
paths remain unchanged: the 4 least significant bits remain zero and
interp_tf_pts() reduces to a direct lookup.
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Co-developed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In newer DCN families, there is no hw predefined curves for shaper,
blend and regamma. When userspace sets pre-defined curves for these
blocks, the driver uses AMD color module to program predefined curve as
LUT. However, it was using the same LUT segmentation for EOTF and
inverse EOTF by using the same color management helper. This is causing
banding on blend when PQ predefined curve is set. Besides that, degamma
predefined HW curve cannot be used with subsampled 4:2:0/4:2:2 formats
as it affects the linearity of color space in which HW scaler operates.
To mitigate banding when using the blend block and better support
subsampled format on degamma, use different translation helpers when
linearizing and delinearizing.
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit 8b89acc0b2.
So that we can detach NL->L LUT programming from L->NL one, i.e., we can
use cm3_helper_translate_curve_to_degamma_hw_format for plane degamma and
blend (post-3DLUT curve) and cm3_helper_translate_curve_to_hw_format for
plane shaper (pre-3DLUT curve) and stream regamma.
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When setting plane degamma TF via AMD driver-specific color properties,
the driver uses PRE_DEGAM color block (ROM). However, this block cannot
be used with subsampled formats as it affects the linearity of color
space in which HW scaler operates. For subsampled format, use the AMD
color module to map plane degamma predefined curve to LUT and use GAMCOR
block instead (RAM).
This is based on Harry's implementation for Fixed Matrix Colorop.
Link: https://lore.kernel.org/dri-devel/20260330153451.99472-1-harry.wentland@amd.com/
Co-developed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The standalone_mode ip_discovery sysfs hierarchy is tied to the PCI
device lifetime and tracked in early_ip_discovery_list. It is torn down
only by amdgpu_discovery_sysfs_early_fini() on driver unbind, which is
why amdgpu_discovery_fini() already guards its teardown with
!standalone_mode.
Commit 7de02fe953 ("drm/amdgpu: clean up discovery and preempt sysfs
entries on shutdown") added an unconditional amdgpu_discovery_sysfs_fini()
call in amdgpu_device_sys_interface_fini(), which runs during
amdgpu_device_fini_hw() on every unbind/reload. On reload this freed the
PCI-device-owned ip_top via kobject_put()->ip_disc_release()->kfree(),
leaving a dangling pointer in early_ip_discovery_list. The subsequent
amdgpu_discovery_sysfs_early_fini() then dereferenced and put the freed
object, causing a use-after-free and double-free, and prematurely
destroyed the sysfs that was meant to persist across reloads.
Make amdgpu_discovery_sysfs_fini() skip standalone_mode objects so the
invariant is centralized at the teardown site and the new call site
cannot free the PCI-device-owned ip_top. Teardown of standalone sysfs
remains the sole responsibility of amdgpu_discovery_sysfs_early_fini().
Fixes: 7de02fe953 ("drm/amdgpu: clean up discovery and preempt sysfs entries on shutdown")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
MQD used outside of dpm_lock is unsafe because the queue could be
destroyed during the window of dqm_unlock, moving into dqm_lock
range is the best practice.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
