From: Mukul Joshi <[email protected]> GFX12.1 doesn't follow the pair-wise CU mask requirement as is the case for GFX 10,GFX 11 and GFX 12. Currently, the ioctl call is returning error because of this incorrect condition of checking for a pair of CUs to be enabled in the CU mask. Fix the issue by removing this check for GFX 12.1.
Signed-off-by: Mukul Joshi <[email protected]> Reviewed-by: Harish Kasiviswanathan <[email protected]> Signed-off-by: Alex Deucher <[email protected]> --- drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index ef1d1cb46152d..9e607098c3a09 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -663,7 +663,8 @@ int pqm_update_mqd(struct process_queue_manager *pqm, /* ASICs that have WGPs must enforce pairwise enabled mask checks. */ if (minfo && minfo->cu_mask.ptr && - KFD_GC_VERSION(pqn->q->device) >= IP_VERSION(10, 0, 0)) { + KFD_GC_VERSION(pqn->q->device) >= IP_VERSION(10, 0, 0) && + KFD_GC_VERSION(pqn->q->device) < IP_VERSION(12, 1, 0)) { int i; for (i = 0; i < minfo->cu_mask.count; i += 2) { -- 2.55.0
