drm/amdgpu: change how we update mmRLC_SPM_MC_CNTL

In pp_one_vf mode avoid the extra overhead and read/write the
registers without the KIQ.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Acked-by: Yintian Tao <yintian.tao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -7030,14 +7030,21 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 
 static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
-	u32 data;
+	u32 reg, data;
 
-	data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
+	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
+	if (amdgpu_sriov_is_pp_one_vf(adev))
+		data = RREG32_NO_KIQ(reg);
+	else
+		data = RREG32(reg);
 
 	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
 
-	WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+	if (amdgpu_sriov_is_pp_one_vf(adev))
+		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
+	else
+		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
 }
 
 static bool gfx_v10_0_check_rlcg_range(struct amdgpu_device *adev,

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -5615,12 +5615,18 @@ static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
 	u32 data;
 
-	data = RREG32(mmRLC_SPM_VMID);
+	if (amdgpu_sriov_is_pp_one_vf(adev))
+		data = RREG32_NO_KIQ(mmRLC_SPM_VMID);
+	else
+		data = RREG32(mmRLC_SPM_VMID);
 
 	data &= ~RLC_SPM_VMID__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_VMID__RLC_SPM_VMID_MASK) << RLC_SPM_VMID__RLC_SPM_VMID__SHIFT;
 
-	WREG32(mmRLC_SPM_VMID, data);
+	if (amdgpu_sriov_is_pp_one_vf(adev))
+		WREG32_NO_KIQ(mmRLC_SPM_VMID, data);
+	else
+		WREG32(mmRLC_SPM_VMID, data);
 }
 
 static const struct amdgpu_rlc_funcs iceland_rlc_funcs = {

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -4950,14 +4950,21 @@ static int gfx_v9_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 
 static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
 {
-	u32 data;
+	u32 reg, data;
 
-	data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
+	reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL);
+	if (amdgpu_sriov_is_pp_one_vf(adev))
+		data = RREG32_NO_KIQ(reg);
+	else
+		data = RREG32(reg);
 
 	data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
 	data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
 
-	WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+	if (amdgpu_sriov_is_pp_one_vf(adev))
+		WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data);
+	else
+		WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
 }
 
 static bool gfx_v9_0_check_rlcg_range(struct amdgpu_device *adev,