On Sat, Aug 2, 2025 at 4:33 AM Ethan Carter Edwards
<et...@ethancedwards.com> wrote:
>
> The repeated checks on grbm_soft_reset are unnecessary. Remove them.
>
Same comment as the gfx10 patch. These are necessary.
Alex
> Signed-off-by: Ethan Carter Edwards <et...@ethancedwards.com>
> ---
> drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 24 +++++++++++-------------
> 1 file changed, 11 insertions(+), 13 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> index
> 6a9cf3587cc6f0a0d00ab1c109fd599dd8aa2579..a6ff9a137a83a93cde0b0c9c9e51db66374bcbee
> 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> @@ -4175,19 +4175,17 @@ static int gfx_v9_0_soft_reset(struct amdgpu_ip_block
> *ip_block)
> /* Disable MEC parsing/prefetching */
> gfx_v9_0_cp_compute_enable(adev, false);
>
> - if (grbm_soft_reset) {
> - tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
> - tmp |= grbm_soft_reset;
> - dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
> - WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
> - tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
> -
> - udelay(50);
> -
> - tmp &= ~grbm_soft_reset;
> - WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
> - tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
> - }
> + tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
> + tmp |= grbm_soft_reset;
> + dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
> + WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
> + tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
> +
> + udelay(50);
> +
> + tmp &= ~grbm_soft_reset;
> + WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
> + tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
>
> /* Wait a little for things to settle down */
> udelay(50);
>
> ---
> base-commit: b9ddaa95fd283bce7041550ddbbe7e764c477110
> change-id: 20250801-amdgfxv9-30357749717e
>
> Best regards,
> --
> Ethan Carter Edwards <et...@ethancedwards.com>
>
