linux-next.git/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c, branch master

drm/amdgpu: GFX12.1 scratch memory limit up to 57-bit

2026-03-04T16:42:26+00:00

The scratch aperture or gmc private aperture in flat memory contains 57 bits of data on gfx v12.1.0 compared to the 32 bits from previous. Add new helper kfd_init_apertures_v12 for gfx version >= v12.1.0 which supports 57-bit VA space. v2: - update pdd->scratch_limit (Yu, Lang) - update fixes tag (Felix Kuehling) - add helper kfd_init_apertures_v12 Fixes: db1882b3ff0c ("drm/amdkfd: Update LDS, Scratch base for 57bit address") Signed-off-by: Philip Yang Reviewed-by: Lang Yu Acked-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: Switch to using GC VERSION to decide LDS/Scratch base

2026-01-14T19:28:58+00:00

Next generation GC IP with 4-level page table needs to use the same LDS/Scratch base with 5-level page table, use GC VERSION to decide is more appropriate. Signed-off-by: Lang Yu Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdkfd: Update LDS, Scratch base for 57bit address

2025-12-16T18:28:03+00:00

For 5-level page tables, update compute vmid sh_mem_base LDS aperture and Scratch aperture base address to above 57-bit, use the same setting from gfx vmid, we can remove the duplicate macro. Update queue pdd lds_base and scratch_base to the same value as sh_mem_base setting. Then application get process apertures return the correct value to access LDS and Scratch memory for 57bit address 5-level page tables. This may pass to MES in future when mapping queue. Signed-off-by: Philip Yang Acked-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amd: Do not include when unused

2025-06-30T15:53:45+00:00

Fix the following compile time warning when building with W=1: warning: EXPORT_SYMBOL() is not used, but #include is present Acked-by: Christian König Signed-off-by: André Almeida Signed-off-by: Alex Deucher

drm/amdkfd: Use device based logging for errors

2024-07-01T20:10:47+00:00

Convert some pr_* to some dev_* APIs to identify the device. Signed-off-by: Lijo Lazar Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole

2024-02-16T20:41:50+00:00

The TBA and TMA, along with an unused IB allocation, reside at low addresses in the VM address space. A stray VM fault which hits these pages must be serviced by making their page table entries invalid. The scheduler depends upon these pages being resident and fails, preventing a debugger from inspecting the failure state. By relocating these pages above 47 bits in the VM address space they can only be reached when bits [63:48] are set to 1. This makes it much less likely for a misbehaving program to generate accesses to them. The current placement at VA (PAGE_SIZE*2) is readily hit by a NULL access with a small offset. v2: - Move it to the reserved space to avoid concflicts with Mesa - Add macros to make reserved space management easier v3: - Move VM max PFN calculation into AMDGPU_VA_RESERVED macros Cc: Arunpravin Paneer Selvam Cc: Christian Koenig Reviewed-by: Christian König Signed-off-by: Jay Cornwall Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher

Revert "drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole"

2024-01-05T21:10:44+00:00

That commit causes NULL pointer dereferences in dmesgs when running applications using ROCm, including clinfo, blender, and PyTorch, since v6.6.1. Revert it to fix blender again. This reverts commit 96c211f1f9ef82183493f4ceed4e347b52849149. Closes: https://github.com/ROCm/ROCm/issues/2596 Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2991 Reviewed-by: Jay Cornwall Signed-off-by: Kaibo Ma Signed-off-by: Alex Deucher

drm/amdkfd: drop IOMMUv2 support

2023-08-11T18:47:25+00:00

Now that we use the dGPU path for all APUs, drop the IOMMUv2 support. v2: drop the now unused queue manager functions for gfx7/8 APUs Reviewed-by: Felix Kuehling Acked-by: Christian König Tested-by: Mike Lothian Signed-off-by: Alex Deucher

drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole

2023-08-07T21:14:06+00:00

The TBA and TMA, along with an unused IB allocation, reside at low addresses in the VM address space. A stray VM fault which hits these pages must be serviced by making their page table entries invalid. The scheduler depends upon these pages being resident and fails, preventing a debugger from inspecting the failure state. By relocating these pages above 47 bits in the VM address space they can only be reached when bits [63:48] are set to 1. This makes it much less likely for a misbehaving program to generate accesses to them. The current placement at VA (PAGE_SIZE*2) is readily hit by a NULL access with a small offset. Signed-off-by: Jay Cornwall Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: Introduce kfd_node struct (v5)

2023-06-09T13:42:27+00:00

Introduce a new structure, kfd_node, which will now represent a compute node. kfd_node is carved out of kfd_dev structure. kfd_dev struct now will become the parent of kfd_node, and will store common resources such as doorbells, GTT sub-alloctor etc. kfd_node struct will store all resources specific to a compute node, such as device queue manager, interrupt handling etc. This is the first step in adding compute partition support in KFD. v2: introduce kfd_node struct to gc v11 (Hawking) v3: make reference to kfd_dev struct through kfd_node (Morris) v4: use kfd_node instead for kfd isr/mqd functions (Morris) v5: rebase (Alex) Signed-off-by: Mukul Joshi Tested-by: Amber Lin Reviewed-by: Felix Kuehling Signed-off-by: Hawking Zhang Signed-off-by: Morris Zhang Signed-off-by: Alex Deucher