Tonga based asics may experience hangs when an HQD's EOP parameters are modified. Workaround this HW issue by avoiding writes to these registers for tonga asics. Based on the following ROCm commit: 2a0fb8 - drm/amdgpu: Synchronize KFD HQD load protocol with CP scheduler >From the ROCm git repository: https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver.git CC: Jay Cornwall <Jay.Cornwall at amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling at amd.com> Signed-off-by: Andres Rodriguez <andresx7 at gmail.com> --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 0f1b62d..b9e0ded 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -5033,41 +5033,55 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring) /* activate the queue */ mqd->cp_hqd_active = 1; return 0; } int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd) { uint32_t mqd_reg; uint32_t *mqd_data; /* HQD registers extend from mmCP_MQD_BASE_ADDR to mmCP_HQD_ERROR */ mqd_data = &mqd->cp_mqd_base_addr_lo; /* disable wptr polling */ WREG32_FIELD(CP_PQ_WPTR_POLL_CNTL, EN, 0); /* program all HQD registers */ - for (mqd_reg = mmCP_HQD_VMID; mqd_reg <= mmCP_HQD_ERROR; mqd_reg++) + for (mqd_reg = mmCP_HQD_VMID; mqd_reg <= mmCP_HQD_EOP_CONTROL; mqd_reg++) + WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]); + + /* Tonga errata: EOP RPTR/WPTR should be left unmodified. + * This is safe since EOP RPTR==WPTR for any inactive HQD + * on ASICs that do not support context-save. + * EOP writes/reads can start anywhere in the ring. + */ + if (adev->asic_type != CHIP_TONGA) { + WREG32(mmCP_HQD_EOP_RPTR, mqd->cp_hqd_eop_rptr); + WREG32(mmCP_HQD_EOP_WPTR, mqd->cp_hqd_eop_wptr); + WREG32(mmCP_HQD_EOP_WPTR_MEM, mqd->cp_hqd_eop_wptr_mem); + } + + for (mqd_reg = mmCP_HQD_EOP_EVENTS; mqd_reg <= mmCP_HQD_ERROR; mqd_reg++) WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]); /* activate the HQD */ for (mqd_reg = mmCP_MQD_BASE_ADDR; mqd_reg <= mmCP_HQD_ACTIVE; mqd_reg++) WREG32(mqd_reg, mqd_data[mqd_reg - mmCP_MQD_BASE_ADDR]); return 0; } static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring) { int r = 0; struct amdgpu_device *adev = ring->adev; struct vi_mqd *mqd = ring->mqd_ptr; int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS; gfx_v8_0_kiq_setting(ring); if (adev->gfx.in_reset) { /* for GPU_RESET case */ /* reset MQD to a clean status */ -- 2.9.3
