Merge tag 'amd-drm-next-6.15-2025-02-21' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.15-2025-02-21:

amdgpu:
- Add OEM i2c support for RGB lights, etc.
- Add support for GC 11.5.3
- Add support for GC 11.5.2
- Add support for SDMA 6.1.3
- Add support for NBIO 7.11.2
- Add support for NBIO 7.9.1
- Add support for MMHUB 3.3.2
- Add support for MMHUB 1.8.1
- Add support for SMU 14.0.5
- Add support for SMUIO 13.0.11
- Add support for PSP 14.0.5
- Add support for UMC 12.5.0
- Add support for DCN 3.6.0
- JPEG 4.0.3 updates
- Add dynamic workload profile switching for GC 10-12
- support larger vbios sizes
- GC 9.5.0 updates
- SMU 13.0.12 updates
- SMU 13.0.6 updates
- IP discovery updates
- GC 10 queue reset updates
- DCN 4.0.1 updates
- UHBR link rate fixes
- Aborted suspend fix
- Mark gttsize parameter as deprecated
- GC 10 cleaner shader updates
- PSR-SU fixes
- Clean up PM4 headers
- Cursor fixes
- Enable devcoredump for JPEG
- Misc cleanups
- Runpm cleanups
- MES updates
- GC 9 gfxoff fixes
- Vbios fetching cleanups
- Documentation updates
- Update secondary plane handling
- DML2 updates
- SDMA fixes for MI
- Cleaner shader fixes for GC 11/12
- ACA updates
- Initial JPEG queue reset support
- RAS updates
- Initial RAS CPER support
- DCN/DCE panic screen handling cleanup
- BT2020 fixes
- SR-IOV fixes

amdkfd:
- synchronize pasid values between KGD and KFD
- Misc cleanups
- Improve GTT/VRAM handling for APUs
- Topology updates
- Fix user queue validation on GC 7/8

UAPI:
- Enable "Broadcast RGB" drm property
- Add INFO IOCTL query for virtualization mode
  Proposed userspace:
  https://github.com/ROCm/amdsmi/commit/e663bed7d6b3df79f5959e73981749b1f22ec698

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221213651.4176031-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 410 insertions, 429 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index b518202955ca..105e59f6132b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -452,64 +452,62 @@ static int vcn_v2_5_resume(struct amdgpu_ip_block *ip_block)
  * vcn_v2_5_mc_resume - memory controller programming
  *
  * @adev: amdgpu_device pointer
+ * @i: instance to resume
  *
  * Let the VCN memory controller know it's offsets
  */
-static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
+static void vcn_v2_5_mc_resume(struct amdgpu_device *adev, int i)
 {
 	uint32_t size;
 	uint32_t offset;
-	int i;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
 
-		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[i].fw->size + 4);
-		/* cache window 0: fw */
-		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo));
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi));
-			WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
-			offset = 0;
-		} else {
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-				lower_32_bits(adev->vcn.inst[i].gpu_addr));
-			WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-				upper_32_bits(adev->vcn.inst[i].gpu_addr));
-			offset = size;
-			WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0,
-				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
-		}
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE0, size);
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
 
-		/* cache window 1: stack */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset));
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET1, 0);
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
-
-		/* cache window 2: context */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET2, 0);
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
-
-		/* non-cache window */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW,
-			lower_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH,
-			upper_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_OFFSET0, 0);
-		WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_SIZE0,
-			AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)));
+	size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.inst[i].fw->size + 4);
+	/* cache window 0: fw */
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+			     (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo));
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+			     (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi));
+		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
+		offset = 0;
+	} else {
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+			     lower_32_bits(adev->vcn.inst[i].gpu_addr));
+		WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+			     upper_32_bits(adev->vcn.inst[i].gpu_addr));
+		offset = size;
+		WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET0,
+			     AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
 	}
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE0, size);
+
+	/* cache window 1: stack */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
+		     lower_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
+		     upper_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET1, 0);
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE);
+
+	/* cache window 2: context */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
+		     lower_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
+		     upper_32_bits(adev->vcn.inst[i].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE));
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_OFFSET2, 0);
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
+
+	/* non-cache window */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW,
+		     lower_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH,
+		     upper_32_bits(adev->vcn.inst[i].fw_shared.gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_OFFSET0, 0);
+	WREG32_SOC15(VCN, i, mmUVD_VCPU_NONCACHE_SIZE0,
+		     AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)));
 }
 
 static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
@@ -612,117 +610,115 @@ static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
  * vcn_v2_5_disable_clock_gating - disable VCN clock gating
  *
  * @adev: amdgpu_device pointer
+ * @i: instance to disable clockgating on
  *
  * Disable clock gating for VCN block
  */
-static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev, int i)
 {
 	uint32_t data;
-	int i;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* UVD disable CGC */
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
-			data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		else
-			data &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
-		data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-		data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_GATE);
-		data &= ~(UVD_CGC_GATE__SYS_MASK
-			| UVD_CGC_GATE__UDEC_MASK
-			| UVD_CGC_GATE__MPEG2_MASK
-			| UVD_CGC_GATE__REGS_MASK
-			| UVD_CGC_GATE__RBC_MASK
-			| UVD_CGC_GATE__LMI_MC_MASK
-			| UVD_CGC_GATE__LMI_UMC_MASK
-			| UVD_CGC_GATE__IDCT_MASK
-			| UVD_CGC_GATE__MPRD_MASK
-			| UVD_CGC_GATE__MPC_MASK
-			| UVD_CGC_GATE__LBSI_MASK
-			| UVD_CGC_GATE__LRBBM_MASK
-			| UVD_CGC_GATE__UDEC_RE_MASK
-			| UVD_CGC_GATE__UDEC_CM_MASK
-			| UVD_CGC_GATE__UDEC_IT_MASK
-			| UVD_CGC_GATE__UDEC_DB_MASK
-			| UVD_CGC_GATE__UDEC_MP_MASK
-			| UVD_CGC_GATE__WCB_MASK
-			| UVD_CGC_GATE__VCPU_MASK
-			| UVD_CGC_GATE__MMSCH_MASK);
-
-		WREG32_SOC15(VCN, i, mmUVD_CGC_GATE, data);
-
-		SOC15_WAIT_ON_RREG(VCN, i, mmUVD_CGC_GATE, 0,  0xFFFFFFFF);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_CM_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_IT_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_DB_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MP_MODE_MASK
-			| UVD_CGC_CTRL__SYS_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MODE_MASK
-			| UVD_CGC_CTRL__MPEG2_MODE_MASK
-			| UVD_CGC_CTRL__REGS_MODE_MASK
-			| UVD_CGC_CTRL__RBC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_MC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_UMC_MODE_MASK
-			| UVD_CGC_CTRL__IDCT_MODE_MASK
-			| UVD_CGC_CTRL__MPRD_MODE_MASK
-			| UVD_CGC_CTRL__MPC_MODE_MASK
-			| UVD_CGC_CTRL__LBSI_MODE_MASK
-			| UVD_CGC_CTRL__LRBBM_MODE_MASK
-			| UVD_CGC_CTRL__WCB_MODE_MASK
-			| UVD_CGC_CTRL__VCPU_MODE_MASK
-			| UVD_CGC_CTRL__MMSCH_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		/* turn on */
-		data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE);
-		data |= (UVD_SUVD_CGC_GATE__SRE_MASK
-			| UVD_SUVD_CGC_GATE__SIT_MASK
-			| UVD_SUVD_CGC_GATE__SMP_MASK
-			| UVD_SUVD_CGC_GATE__SCM_MASK
-			| UVD_SUVD_CGC_GATE__SDB_MASK
-			| UVD_SUVD_CGC_GATE__SRE_H264_MASK
-			| UVD_SUVD_CGC_GATE__SRE_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SIT_H264_MASK
-			| UVD_SUVD_CGC_GATE__SIT_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SCM_H264_MASK
-			| UVD_SUVD_CGC_GATE__SCM_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SDB_H264_MASK
-			| UVD_SUVD_CGC_GATE__SDB_HEVC_MASK
-			| UVD_SUVD_CGC_GATE__SCLR_MASK
-			| UVD_SUVD_CGC_GATE__UVD_SC_MASK
-			| UVD_SUVD_CGC_GATE__ENT_MASK
-			| UVD_SUVD_CGC_GATE__SIT_HEVC_DEC_MASK
-			| UVD_SUVD_CGC_GATE__SIT_HEVC_ENC_MASK
-			| UVD_SUVD_CGC_GATE__SITE_MASK
-			| UVD_SUVD_CGC_GATE__SRE_VP9_MASK
-			| UVD_SUVD_CGC_GATE__SCM_VP9_MASK
-			| UVD_SUVD_CGC_GATE__SIT_VP9_DEC_MASK
-			| UVD_SUVD_CGC_GATE__SDB_VP9_MASK
-			| UVD_SUVD_CGC_GATE__IME_HEVC_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
-		data &= ~(UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
+	/* UVD disable CGC */
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
+		data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
+	data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_GATE);
+	data &= ~(UVD_CGC_GATE__SYS_MASK
+		  | UVD_CGC_GATE__UDEC_MASK
+		  | UVD_CGC_GATE__MPEG2_MASK
+		  | UVD_CGC_GATE__REGS_MASK
+		  | UVD_CGC_GATE__RBC_MASK
+		  | UVD_CGC_GATE__LMI_MC_MASK
+		  | UVD_CGC_GATE__LMI_UMC_MASK
+		  | UVD_CGC_GATE__IDCT_MASK
+		  | UVD_CGC_GATE__MPRD_MASK
+		  | UVD_CGC_GATE__MPC_MASK
+		  | UVD_CGC_GATE__LBSI_MASK
+		  | UVD_CGC_GATE__LRBBM_MASK
+		  | UVD_CGC_GATE__UDEC_RE_MASK
+		  | UVD_CGC_GATE__UDEC_CM_MASK
+		  | UVD_CGC_GATE__UDEC_IT_MASK
+		  | UVD_CGC_GATE__UDEC_DB_MASK
+		  | UVD_CGC_GATE__UDEC_MP_MASK
+		  | UVD_CGC_GATE__WCB_MASK
+		  | UVD_CGC_GATE__VCPU_MASK
+		  | UVD_CGC_GATE__MMSCH_MASK);
+
+	WREG32_SOC15(VCN, i, mmUVD_CGC_GATE, data);
+
+	SOC15_WAIT_ON_RREG(VCN, i, mmUVD_CGC_GATE, 0,  0xFFFFFFFF);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_CM_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_IT_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_DB_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_MP_MODE_MASK
+		  | UVD_CGC_CTRL__SYS_MODE_MASK
+		  | UVD_CGC_CTRL__UDEC_MODE_MASK
+		  | UVD_CGC_CTRL__MPEG2_MODE_MASK
+		  | UVD_CGC_CTRL__REGS_MODE_MASK
+		  | UVD_CGC_CTRL__RBC_MODE_MASK
+		  | UVD_CGC_CTRL__LMI_MC_MODE_MASK
+		  | UVD_CGC_CTRL__LMI_UMC_MODE_MASK
+		  | UVD_CGC_CTRL__IDCT_MODE_MASK
+		  | UVD_CGC_CTRL__MPRD_MODE_MASK
+		  | UVD_CGC_CTRL__MPC_MODE_MASK
+		  | UVD_CGC_CTRL__LBSI_MODE_MASK
+		  | UVD_CGC_CTRL__LRBBM_MODE_MASK
+		  | UVD_CGC_CTRL__WCB_MODE_MASK
+		  | UVD_CGC_CTRL__VCPU_MODE_MASK
+		  | UVD_CGC_CTRL__MMSCH_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	/* turn on */
+	data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE);
+	data |= (UVD_SUVD_CGC_GATE__SRE_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_MASK
+		 | UVD_SUVD_CGC_GATE__SMP_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_MASK
+		 | UVD_SUVD_CGC_GATE__SRE_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SRE_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_H264_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_HEVC_MASK
+		 | UVD_SUVD_CGC_GATE__SCLR_MASK
+		 | UVD_SUVD_CGC_GATE__UVD_SC_MASK
+		 | UVD_SUVD_CGC_GATE__ENT_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_HEVC_DEC_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_HEVC_ENC_MASK
+		 | UVD_SUVD_CGC_GATE__SITE_MASK
+		 | UVD_SUVD_CGC_GATE__SRE_VP9_MASK
+		 | UVD_SUVD_CGC_GATE__SCM_VP9_MASK
+		 | UVD_SUVD_CGC_GATE__SIT_VP9_DEC_MASK
+		 | UVD_SUVD_CGC_GATE__SDB_VP9_MASK
+		 | UVD_SUVD_CGC_GATE__IME_HEVC_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_GATE, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
+	data &= ~(UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
+		  | UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
 			| UVD_SUVD_CGC_CTRL__IME_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
-	}
+		  | UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
 }
 
 static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
@@ -777,62 +773,60 @@ static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
  * vcn_v2_5_enable_clock_gating - enable VCN clock gating
  *
  * @adev: amdgpu_device pointer
+ * @i: instance to enable clockgating on
  *
  * Enable clock gating for VCN block
  */
-static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev)
+static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev, int i)
 {
 	uint32_t data = 0;
-	int i;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* enable UVD CGC */
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
-			data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		else
-			data |= 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-		data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
-		data |= (UVD_CGC_CTRL__UDEC_RE_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_CM_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_IT_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_DB_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MP_MODE_MASK
-			| UVD_CGC_CTRL__SYS_MODE_MASK
-			| UVD_CGC_CTRL__UDEC_MODE_MASK
-			| UVD_CGC_CTRL__MPEG2_MODE_MASK
-			| UVD_CGC_CTRL__REGS_MODE_MASK
-			| UVD_CGC_CTRL__RBC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_MC_MODE_MASK
-			| UVD_CGC_CTRL__LMI_UMC_MODE_MASK
-			| UVD_CGC_CTRL__IDCT_MODE_MASK
-			| UVD_CGC_CTRL__MPRD_MODE_MASK
-			| UVD_CGC_CTRL__MPC_MODE_MASK
-			| UVD_CGC_CTRL__LBSI_MODE_MASK
-			| UVD_CGC_CTRL__LRBBM_MODE_MASK
-			| UVD_CGC_CTRL__WCB_MODE_MASK
-			| UVD_CGC_CTRL__VCPU_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
-
-		data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
-		data |= (UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__IME_MODE_MASK
-			| UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return;
+	/* enable UVD CGC */
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
+		data |= 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data |= 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_CGC_CTRL);
+	data |= (UVD_CGC_CTRL__UDEC_RE_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_CM_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_IT_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_DB_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_MP_MODE_MASK
+		 | UVD_CGC_CTRL__SYS_MODE_MASK
+		 | UVD_CGC_CTRL__UDEC_MODE_MASK
+		 | UVD_CGC_CTRL__MPEG2_MODE_MASK
+		 | UVD_CGC_CTRL__REGS_MODE_MASK
+		 | UVD_CGC_CTRL__RBC_MODE_MASK
+		 | UVD_CGC_CTRL__LMI_MC_MODE_MASK
+		 | UVD_CGC_CTRL__LMI_UMC_MODE_MASK
+		 | UVD_CGC_CTRL__IDCT_MODE_MASK
+		 | UVD_CGC_CTRL__MPRD_MODE_MASK
+		 | UVD_CGC_CTRL__MPC_MODE_MASK
+		 | UVD_CGC_CTRL__LBSI_MODE_MASK
+		 | UVD_CGC_CTRL__LRBBM_MODE_MASK
+		 | UVD_CGC_CTRL__WCB_MODE_MASK
+		 | UVD_CGC_CTRL__VCPU_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_CGC_CTRL, data);
+
+	data = RREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL);
+	data |= (UVD_SUVD_CGC_CTRL__SRE_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SIT_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SMP_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SCM_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SDB_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SCLR_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__UVD_SC_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__ENT_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__IME_MODE_MASK
+		 | UVD_SUVD_CGC_CTRL__SITE_MODE_MASK);
+	WREG32_SOC15(VCN, i, mmUVD_SUVD_CGC_CTRL, data);
 }
 
 static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx,
@@ -1006,197 +1000,185 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	return 0;
 }
 
-static int vcn_v2_5_start(struct amdgpu_device *adev)
+static int vcn_v2_5_start(struct amdgpu_device *adev, int i)
 {
+	volatile struct amdgpu_fw_shared *fw_shared =
+		adev->vcn.inst[i].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
-	int i, j, k, r;
+	int j, k, r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, true, i);
-	}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, i);
 
-		/* disable register anti-hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), 0,
-			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
 
-		/* set uvd status busy */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
-	}
+	/* disable register anti-hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS), 0,
+		 ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+
+	/* set uvd status busy */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
 		return 0;
 
-	/*SW clock gating */
-	vcn_v2_5_disable_clock_gating(adev);
+	/* SW clock gating */
+	vcn_v2_5_disable_clock_gating(adev, i);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
-
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
-
-		/* setup mmUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
-		tmp &= ~0xff;
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp | 0x8|
-			UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK	|
-			UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
-			UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
-			UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
-
-		/* setup mmUVD_MPC_CNTL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
-		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
-		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
-		WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
-
-		/* setup UVD_MPC_SET_MUXA0 */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
-			((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
-			(0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
-			(0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
-
-		/* setup UVD_MPC_SET_MUXB0 */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
-			((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
-			(0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
-			(0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
-
-		/* setup mmUVD_MPC_SET_MUX */
-		WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
-			((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
-			(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
-			(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
-	}
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
 
-	vcn_v2_5_mc_resume(adev);
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN), 0,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
+	/* setup mmUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
+	tmp &= ~0xff;
+	WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp | 0x8|
+		     UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK	|
+		     UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		     UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		     UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK);
+
+	/* setup mmUVD_MPC_CNTL */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, i, mmUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXA0,
+		     ((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)));
+
+	/* setup UVD_MPC_SET_MUXB0 */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUXB0,
+		     ((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		      (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		      (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)));
+
+	/* setup mmUVD_MPC_SET_MUX */
+	WREG32_SOC15(VCN, i, mmUVD_MPC_SET_MUX,
+		     ((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		      (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		      (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)));
+
+	vcn_v2_5_mc_resume(adev, i);
 
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
+	WREG32_SOC15(VCN, i, mmUVD_GFX8_ADDR_CONFIG,
+		     adev->gfx.config.gb_addr_config);
 
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
+		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		for (k = 0; k < 10; ++k) {
-			uint32_t status;
-
-			for (j = 0; j < 100; ++j) {
-				status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
-				if (status & 2)
-					break;
-				if (amdgpu_emu_mode == 1)
-					msleep(500);
-				else
-					mdelay(10);
-			}
-			r = 0;
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL), 0,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (k = 0; k < 10; ++k) {
+		uint32_t status;
+
+		for (j = 0; j < 100; ++j) {
+			status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
 			if (status & 2)
 				break;
+			if (amdgpu_emu_mode == 1)
+				msleep(500);
+			else
+				mdelay(10);
+		}
+		r = 0;
+		if (status & 2)
+			break;
 
-			DRM_ERROR("VCN decode not responding, trying to reset the VCPU!!!\n");
-			WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-				UVD_VCPU_CNTL__BLK_RST_MASK,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
-			mdelay(10);
-			WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-				~UVD_VCPU_CNTL__BLK_RST_MASK);
+		DRM_ERROR("VCN decode not responding, trying to reset the VCPU!!!\n");
+		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+			 UVD_VCPU_CNTL__BLK_RST_MASK,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
+		mdelay(10);
+		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-			mdelay(10);
-			r = -1;
-		}
+		mdelay(10);
+		r = -1;
+	}
 
-		if (r) {
-			DRM_ERROR("VCN decode not responding, giving up!!!\n");
-			return r;
-		}
+	if (r) {
+		DRM_ERROR("VCN decode not responding, giving up!!!\n");
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
-			UVD_MASTINT_EN__VCPU_EN_MASK,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_MASTINT_EN),
+		 UVD_MASTINT_EN__VCPU_EN_MASK,
+		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
+		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
 
-		ring = &adev->vcn.inst[i].ring_dec;
-		/* force RBC into idle state */
-		rb_bufsz = order_base_2(ring->ring_size);
-		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
-		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
+	ring = &adev->vcn.inst[i].ring_dec;
+	/* force RBC into idle state */
+	rb_bufsz = order_base_2(ring->ring_size);
+	tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
 
-		fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET;
-		/* program the RB_BASE for ring buffer */
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
+	fw_shared->multi_queue.decode_queue_mode |= FW_QUEUE_RING_RESET;
+	/* program the RB_BASE for ring buffer */
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+		     lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
+		     upper_32_bits(ring->gpu_addr));
 
-		/* Initialize the ring buffer's read and write pointers */
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
 
-		ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
-		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
-				lower_32_bits(ring->wptr));
-		fw_shared->multi_queue.decode_queue_mode &= ~FW_QUEUE_RING_RESET;
+	ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
+	WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
+		     lower_32_bits(ring->wptr));
+	fw_shared->multi_queue.decode_queue_mode &= ~FW_QUEUE_RING_RESET;
 
-		fw_shared->multi_queue.encode_generalpurpose_queue_mode |= FW_QUEUE_RING_RESET;
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
-		fw_shared->multi_queue.encode_generalpurpose_queue_mode &= ~FW_QUEUE_RING_RESET;
-
-		fw_shared->multi_queue.encode_lowlatency_queue_mode |= FW_QUEUE_RING_RESET;
-		ring = &adev->vcn.inst[i].ring_enc[1];
-		WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
-		fw_shared->multi_queue.encode_lowlatency_queue_mode &= ~FW_QUEUE_RING_RESET;
-	}
+	fw_shared->multi_queue.encode_generalpurpose_queue_mode |= FW_QUEUE_RING_RESET;
+	ring = &adev->vcn.inst[i].ring_enc[0];
+	WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
+	fw_shared->multi_queue.encode_generalpurpose_queue_mode &= ~FW_QUEUE_RING_RESET;
+
+	fw_shared->multi_queue.encode_lowlatency_queue_mode |= FW_QUEUE_RING_RESET;
+	ring = &adev->vcn.inst[i].ring_enc[1];
+	WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+	WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
+	fw_shared->multi_queue.encode_lowlatency_queue_mode &= ~FW_QUEUE_RING_RESET;
 
 	return 0;
 }
@@ -1425,72 +1407,66 @@ static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	return 0;
 }
 
-static int vcn_v2_5_stop(struct amdgpu_device *adev)
+static int vcn_v2_5_stop(struct amdgpu_device *adev, int i)
 {
 	uint32_t tmp;
-	int i, r = 0;
+	int r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v2_5_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->vcn.harvest_config & (1 << i))
+		return 0;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v2_5_stop_dpg_mode(adev, i);
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		return r;
 
-		tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__READ_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_MASK |
-			UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__READ_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_MASK |
+		UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-		/* block LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
+	/* block LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL2, tmp);
 
-		tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
-			UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
-		r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK|
+		UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
+	r = SOC15_WAIT_ON_RREG(VCN, i, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
-			UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_RB_ARB_CTRL),
+		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
+		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
 
-		/* reset VCPU */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__BLK_RST_MASK,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* reset VCPU */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL),
+		 UVD_VCPU_CNTL__BLK_RST_MASK,
+		 ~UVD_VCPU_CNTL__BLK_RST_MASK);
 
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~(UVD_VCPU_CNTL__CLK_EN_MASK));
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
+		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
+	/* clear status */
+	WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
 
-		vcn_v2_5_enable_clock_gating(adev);
+	vcn_v2_5_enable_clock_gating(adev, i);
 
-		/* enable register anti-hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS),
-			UVD_POWER_STATUS__UVD_POWER_STATUS_MASK,
-			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
-	}
+	/* enable register anti-hang mechanism */