kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h, branch v7.0-rc7

drm/amd: Fix MQD and control stack alignment for non-4K

2026-03-30T20:12:27+00:00

For gfxV9, due to a hardware bug ("based on the comments in the code here [1]"), the control stack of a user-mode compute queue must be allocated immediately after the page boundary of its regular MQD buffer. To handle this, we allocate an enlarged MQD buffer where the first page is used as the MQD and the remaining pages store the control stack. Although these regions share the same BO, they require different memory types: the MQD must be UC (uncached), while the control stack must be NC (non-coherent), matching the behavior when the control stack is allocated in user space. This logic works correctly on systems where the CPU page size matches the GPU page size (4K). However, the current implementation aligns both the MQD and the control stack to the CPU PAGE_SIZE. On systems with a larger CPU page size, the entire first CPU page is marked UC—even though that page may contain multiple GPU pages. The GPU treats the second 4K GPU page inside that CPU page as part of the control stack, but it is incorrectly mapped as UC. This patch fixes the issue by aligning both the MQD and control stack sizes to the GPU page size (4K). The first 4K page is correctly marked as UC for the MQD, and the remaining GPU pages are marked NC for the control stack. This ensures proper memory type assignment on systems with larger CPU page sizes. [1]: https://elixir.bootlin.com/linux/v6.18/source/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c#L118 Acked-by: Felix Kuehling Signed-off-by: Donet Tom Signed-off-by: Alex Deucher (cherry picked from commit 998d6781410de1c4b787fdbf6c56e851ea7fa553)

drm/amdgpu/gart: Add helper to bind VRAM pages (v2)

2025-11-12T02:54:17+00:00

Binds pages that located in VRAM to the GART page table. Useful when a kernel BO is located in VRAM but needs to be accessed from the GART address space, for example to give a kernel BO a 32-bit address when GART is placed in LOW address space. v2: - Refactor function to be more reusable Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amd: Remove unused declarations

2024-08-16T18:23:16+00:00

amdgpu_gart_table_vram_pin() and amdgpu_gart_table_vram_unpin() has been removed since commit 575e55ee4fbc ("drm/amdgpu: recover gart table at resume") remain the declarations untouched in the header files. Besides, amdgpu_dm_display_resume() has also beed removed since commit a80aa93de1a0 ("drm/amd/display: Unify dm resume sequence into a single call"). So, let's remove this unused declarations. Signed-off-by: Zhang Zekun Signed-off-by: Alex Deucher

drm/amdgpu: Allocate GART table in RAM for AMD APU

2023-06-09T13:51:06+00:00

Some AMD APUs may not have a dedicated VRAM. On such platforms the GART table should be allocated on the system memory. When real vram size is zero, place the GART table in system memory and create an SG BO to make it GPU accessible. v2: fix includes Reviewed-by: Felix Kuehling (rajneesh: removed set_memory_wc workaround) Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Harish Kasiviswanathan Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: remove gart.ready flag

2022-01-20T03:32:47+00:00

That's just a leftover from old radeon days and was preventing CS and GART bindings before the hardware was initialized. But nowdays that is perfectly valid. The only thing we need to warn about are GART binding before the table is even allocated. Signed-off-by: Christian König Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher

drm/amdgpu: remove unused parameter in amdgpu_gart_bind

2021-06-18T21:12:47+00:00

Pagelist is no long used in amdgpu_gart_bind. Remove it. Signed-off-by: Yifan Zhang Reviewed-by: Christian König Signed-off-by: Alex Deucher

Merge tag 'amd-drm-next-5.14-2021-06-02' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

2021-06-03T20:13:57+00:00

amd-drm-next-5.14-2021-06-02: amdgpu: - GC/MM register access macro clean up for SR-IOV - Beige Goby updates - W=1 Fixes - Aldebaran fixes - Misc display fixes - ACPI ATCS/ATIF handling rework - SR-IOV fixes - RAS fixes - 16bpc fixed point format support - Initial smartshift support - RV/PCO power tuning fixes for suspend/resume - More buffer object subclassing work - Add new INFO query for additional vbios information - Add new placement for preemptable SG buffers amdkfd: - Misc fixes radeon: - W=1 Fixes - Misc cleanups UAPI: - Add new INFO query for additional vbios information Useful for debugging vbios related issues. Proposed umr patch: https://patchwork.freedesktop.org/patch/433297/ - 16bpc fixed point format support IGT test: https://lists.freedesktop.org/archives/igt-dev/2021-May/031507.html Proposed Vulkan patch: https://github.com/kleinerm/pal/commit/a25d4802074b13a8d5f7edc96ae45469ecbac3c4 - Add a new GEM flag which is only used internally in the kernel driver. Userspace is not allowed to set it. drm: - 16bpc fixed point format fourcc Signed-off-by: Dave Airlie From: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20210602214009.4553-1-alexander.deucher@amd.com

drm/amdgpu: flush gart changes after all BO recovery

2021-06-02T02:55:38+00:00

Don't flush gart changes after recovering each BO instead do it after recovering all the BOs. Flishing gart also needed for amdgpu_ttm_alloc_gart(). v4: use containerof to retrieve adev struct. v3: rename amdgpu_gart_tlb_flush() -> amdgpu_gart_invalidate_tlb(). v2: abstract out gart tlb flushing logic to amdgpu_gart.c Signed-off-by: Nirmoy Das Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: Handle IOMMU enabled case.

2021-05-20T03:50:27+00:00

Problem: Handle all DMA IOMMU group related dependencies before the group is removed. Those manifest themself in that when IOMMU enabled DMA map/unmap is dependent on the presence of IOMMU group the device belongs to but, this group is released once the device is removed from PCI topology. Fix: Expedite all such unmap operations to pci remove driver callback. v5: Drop IOMMU notifier and switch to lockless call to ttm_tt_unpopulate v6: Drop the BO unamp list v7: Drop amdgpu_gart_fini In amdgpu_ih_ring_fini do uncinditional check (!ih->ring) to avoid freeing uniniitalized rings. Call amdgpu_ih_ring_fini unconditionally. v8: Add deatiled explanation Signed-off-by: Andrey Grodzovsky Reviewed-by: Felix Kuehling Link: https://patchwork.freedesktop.org/patch/msgid/20210517143851.475058-1-andrey.grodzovsky@amd.com

drm/amdgpu: remove CONFIG_DRM_AMDGPU_GART_DEBUGFS

2021-02-18T21:43:09+00:00

Removed unused CONFIG_DRM_AMDGPU_GART_DEBUGFS code. We can use umr instead of this gart debugfs. Signed-off-by: Nirmoy Das Reviewed-by: Christian König Signed-off-by: Alex Deucher