kernel/linux.git/drivers/gpu/drm/amd/amdkfd/kfd_queue.c, branch v6.18.34

drm/amdkfd: Fix queue preemption/eviction failures by aligning control stack size to GPU page size

2026-04-22T11:22:14+00:00

[ Upstream commit 78746a474e92fc7aaed12219bec7c78ae1bd6156 ] The control stack size is calculated based on the number of CUs and waves, and is then aligned to PAGE_SIZE. When the resulting control stack size is aligned to 64 KB, GPU hangs and queue preemption failures are observed while running RCCL unit tests on systems with more than two GPUs. amdgpu 0048:0f:00.0: amdgpu: Queue preemption failed for queue with doorbell_id: 80030008 amdgpu 0048:0f:00.0: amdgpu: Failed to evict process queues amdgpu 0048:0f:00.0: amdgpu: GPU reset begin!. Source: 4 amdgpu 0048:0f:00.0: amdgpu: Queue preemption failed for queue with doorbell_id: 80030008 amdgpu 0048:0f:00.0: amdgpu: Failed to evict process queues amdgpu 0048:0f:00.0: amdgpu: Failed to restore process queues This issue is observed on both 4 KB and 64 KB system page-size configurations. This patch fixes the issue by aligning the control stack size to AMDGPU_GPU_PAGE_SIZE instead of PAGE_SIZE, so the control stack size will not be 64 KB on systems with a 64 KB page size and queue preemption works correctly. Additionally, In the current code, wg_data_size is aligned to PAGE_SIZE, which can waste memory if the system page size is large. In this patch, wg_data_size is aligned to AMDGPU_GPU_PAGE_SIZE. The cwsr_size, calculated from wg_data_size and the control stack size, is aligned to PAGE_SIZE. Reviewed-by: Felix Kuehling Signed-off-by: Donet Tom Signed-off-by: Alex Deucher (cherry picked from commit a3e14436304392fbada359edd0f1d1659850c9b7) Signed-off-by: Sasha Levin

drm/amdkfd: Relax size checking during queue buffer get

2026-03-04T12:19:59+00:00

[ Upstream commit 42ea9cf2f16b7131cb7302acb3dac510968f8bdc ] HW-supported EOP buffer sizes are 4K and 32K. On systems that do not use 4K pages, the minimum buffer object (BO) allocation size is PAGE_SIZE (for example, 64K). During queue buffer acquisition, the driver currently checks the allocated BO size against the supported EOP buffer size. Since the allocated BO is larger than the expected size, this check fails, preventing queue creation. Relax the strict size validation and allow PAGE_SIZE-sized BOs to be used. Only the required 4K region of the buffer will be used as the EOP buffer and avoids queue creation failures on non-4K page systems. Acked-by: Christian König Suggested-by: Philip Yang Signed-off-by: Donet Tom Signed-off-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: bump minimum vgpr size for gfx1151

2026-01-08T09:17:18+00:00

commit cf326449637a566ba98fb82c47d46cd479608c88 upstream. GFX1151 has 1.5x the number of available physical VGPRs per SIMD. Bump total memory availability for acquire checks on queue creation. Signed-off-by: Jonathan Kim Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit b42f3bf9536c9b710fd1d4deb7d1b0dc819dc72d) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: relax checks for over allocation of save area

2025-11-12T03:52:27+00:00

Over allocation of save area is not fatal, only under allocation is. ROCm has various components that independently claim authority over save area size. Unless KFD decides to claim single authority, relax size checks. Signed-off-by: Jonathan Kim Reviewed-by: Philip Yang Signed-off-by: Alex Deucher (cherry picked from commit 15bd4958fe38e763bc17b607ba55155254a01f55) Cc: stable@vger.kernel.org

drm/amdkfd: Drop workaround for GC v9.4.3 revID 0

2025-04-07T19:18:59+00:00

Remove workaround code for the early engineering samples GC v9.4.3 SOCs with revID 0 Reviewed-by: Amber Lin Signed-off-by: Apurv Mishra Signed-off-by: Alex Deucher

drm/amdkfd: Fix NULL Pointer Dereference in KFD queue

2025-03-05T15:45:35+00:00

Through KFD IOCTL Fuzzing we encountered a NULL pointer derefrence when calling kfd_queue_acquire_buffers. Fixes: 629568d25fea ("drm/amdkfd: Validate queue cwsr area and eop buffer size") Signed-off-by: Andrew Martin Reviewed-by: Philip Yang Signed-off-by: Andrew Martin Signed-off-by: Alex Deucher

drm/amdkfd: Fix user queue validation on Gfx7/8

2025-02-17T19:09:29+00:00

To workaround queue full h/w issue on Gfx7/8, when application create AQL queue, the ring buffer bo allocate size is queue_size/2 and map queue_size ring buffer to GPU in 2 pieces using 2 attachments, each attachment map size is queue_size/2, with same ring_bo backing memory. For Gfx7/8, user queue buffer validation should use queue_size/2 to verify ring_bo allocation and mapping size. Fixes: 68e599db7a54 ("drm/amdkfd: Validate user queue buffers") Suggested-by: Tomáš Trnka Signed-off-by: Philip Yang Acked-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdkfd: update the cwsr area size for gfx950

2024-12-10T15:26:51+00:00

Update cwsr area size for gfx950 to fit the new user queue buffer validation. The size of LDS calculation is referred from gfx950 thunk implementation. Signed-off-by: Le Ma Acked-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdkfd: Handle queue destroy buffer access race

2024-08-13T14:43:16+00:00

Add helper function kfd_queue_unreference_buffers to reduce queue buffer refcount, separate it from release queue buffers. Because it is circular locking to hold dqm_lock to take vm lock, kfd_ioctl_destroy_queue should take vm lock, unreference queue buffers first, but not release queue buffers, to handle error in case failed to hold vm lock. Then hold dqm_lock to remove queue from queue list and then release queue buffers. Restore process worker restore queue hold dqm_lock, will always find the queue with valid queue buffers. v2 (Felix): - renamed kfd_queue_unreference_buffer(s) to kfd_queue_unref_bo_va(s) - added two FIXME comments for follow up Signed-off-by: Philip Yang Signed-off-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: Fix compile error if HMM support not enabled

2024-08-06T14:40:30+00:00

Fixes the below if kernel config not enable HMM support >> drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_queue.c:107:26: error: implicit declaration of function 'svm_range_from_addr' >> drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_queue.c:107:24: error: assignment to 'struct svm_range *' from 'int' makes pointer from integer without a cast [-Wint-conversion] >> drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_queue.c:111:28: error: invalid use of undefined type 'struct svm_range' Fixes: b049504e211e ("drm/amdkfd: Validate user queue svm memory residency") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202407252127.zvnxaKRA-lkp@intel.com/ Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher