drm/amdgpu/gmc9: remove dummy read workaround for newer chips

Aldebaran has a hw fix so no longer requires the workaround.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

+4 -2
+4 -2
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
··· 574 574 * be updated to avoid reading an incorrect value due to 575 575 * the new fast GRBM interface. 576 576 */ 577 - if (entry->vmid_src == AMDGPU_GFXHUB_0) 577 + if ((entry->vmid_src == AMDGPU_GFXHUB_0) && 578 + (adev->asic_type < CHIP_ALDEBARAN)) 578 579 RREG32(hub->vm_l2_pro_fault_status); 579 580 580 581 status = RREG32(hub->vm_l2_pro_fault_status); ··· 803 802 * be cleared to avoid a false ACK due to the new fast 804 803 * GRBM interface. 805 804 */ 806 - if (vmhub == AMDGPU_GFXHUB_0) 805 + if ((vmhub == AMDGPU_GFXHUB_0) && 806 + (adev->asic_type < CHIP_ALDEBARAN)) 807 807 RREG32_NO_KIQ(hub->vm_inv_eng0_req + 808 808 hub->eng_distance * eng); 809 809