On Fri, Sep 20, 2024 at 2:43 AM <jiadong.zhu@xxxxxxx> wrote:
>
> From: Jiadong Zhu <Jiadong.Zhu@xxxxxxx>
>
> Implement sdma queue reset callback via MMIO.
>
> Signed-off-by: Jiadong Zhu <Jiadong.Zhu@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 81 ++++++++++++++++++++++++++
> 1 file changed, 81 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> index e813da1e48aa..7fd7ef22d571 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> @@ -1555,6 +1555,86 @@ static int sdma_v5_0_soft_reset(void *handle)
> return 0;
> }
>
> +static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
> +{
> + struct amdgpu_device *adev = ring->adev;
> + int i, j;
> + u32 rb_cntl, ib_cntl, f32_cntl, freeze, cntl, preempt, soft_reset, stat1_reg;
> +
> + if (amdgpu_sriov_vf(adev))
> + return -EINVAL;
> +
> + for (i = 0; i < adev->sdma.num_instances; i++) {
> + if (ring == &adev->sdma.instance[i].ring)
> + break;
> + }
> +
> + if (i == adev->sdma.num_instances) {
> + DRM_ERROR("sdma instance not found\n");
> + return -EINVAL;
> + }
Do we need to enter safe mode here?
> +
> + /* stop queue */
> + ib_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
> + ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
> +
> + rb_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
> + rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
> +
> + /* engine stop SDMA1_F32_CNTL.HALT to 1 and SDMAx_FREEZE freeze bit to 1 */
> + freeze = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE));
> + freeze = REG_SET_FIELD(freeze, SDMA0_FREEZE, FREEZE, 1);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE), freeze);
> +
> + for (j = 0; j < adev->usec_timeout; j++) {
> + freeze = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE));
> + if (REG_GET_FIELD(freeze, SDMA0_FREEZE, FROZEN) & 1)
> + break;
> + udelay(1);
> + }
> +
> + /* check sdma copy engine all idle if frozen not received*/
> + if (j == adev->usec_timeout) {
> + stat1_reg = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_STATUS1_REG));
> + if ((stat1_reg & 0x3FF) != 0x3FF) {
> + DRM_ERROR("cannot soft reset as sdma not idle\n");
> + return -ETIMEDOUT;
> + }
> + }
> +
> + f32_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL));
> + f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 1);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_F32_CNTL), f32_cntl);
> +
> + cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_CNTL));
> + cntl = REG_SET_FIELD(cntl, SDMA0_CNTL, UTC_L1_ENABLE, 0);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_CNTL), cntl);
> +
> + /* soft reset SDMA_GFX_PREEMPT.IB_PREEMPT = 0 mmGRBM_SOFT_RESET.SOFT_RESET_SDMA0/1 = 1 */
> + preempt = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_PREEMPT));
> + preempt = REG_SET_FIELD(preempt, SDMA0_GFX_PREEMPT, IB_PREEMPT, 0);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_PREEMPT), preempt);
> +
> + soft_reset = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
> + soft_reset |= 1 << GRBM_SOFT_RESET__SOFT_RESET_SDMA0__SHIFT << i;
> +
> + WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, soft_reset);
> +
> + udelay(50);
> +
> + soft_reset &= ~(1 << GRBM_SOFT_RESET__SOFT_RESET_SDMA0__SHIFT << i);
> + WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, soft_reset);
> +
> + /* unfreeze*/
> + freeze = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE));
> + freeze = REG_SET_FIELD(freeze, SDMA0_FREEZE, FREEZE, 0);
> + WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE), freeze);
> +
> + return sdma_v5_0_gfx_resume_instance(adev, i, true);
And exit safe mode here?
Alex
> +}
> +
> static int sdma_v5_0_ring_preempt_ib(struct amdgpu_ring *ring)
> {
> int i, r = 0;
> @@ -1897,6 +1977,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
> .emit_reg_write_reg_wait = sdma_v5_0_ring_emit_reg_write_reg_wait,
> .init_cond_exec = sdma_v5_0_ring_init_cond_exec,
> .preempt_ib = sdma_v5_0_ring_preempt_ib,
> + .reset = sdma_v5_0_reset_queue,
> };
>
> static void sdma_v5_0_set_ring_funcs(struct amdgpu_device *adev)
> --
> 2.25.1
>
