drm/amdkfd: Use dedicated kernel memory for compute MQDs on GFX12.1

To avoid allocation failures in high-density queue scenarios, move user
mode compute MQD allocations for GFX12.1 from GTT sub-allocator to
dedicated kernel memory via amdgpu_amdkfd_alloc_kernel_mem.
This ensures that compute queue creation is not bottlenecked by the
fixed size of the sub-allocator pool.

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>
This commit is contained in:
Alex Sierra 2026-04-14 20:59:14 -05:00 • committed by Alex Deucher
commit b4e7f41c4b