[PATCH 13/18] drm/amdgpu: power vcn 3_0 by instance

[<boyuan.zhang@amd.com>]

From: Boyuan Zhang <boyuan.zhang@amd.com>

For vcn 3_0, add ip_block for each vcn instance during discovery stage.

And only powering on/off one of the vcn instance using the
instance value stored in ip_block, instead of powering on/off all
vcn instances. Modify the existing functions to use the instance value
in ip_block, and remove the original for loop for all vcn instances.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c |   3 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c         | 608 +++++++++---------
 2 files changed, 303 insertions(+), 308 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 6b9c974da0c4..78b673b3ec6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2335,7 +2335,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 		case IP_VERSION(3, 1, 1):
 		case IP_VERSION(3, 1, 2):
 		case IP_VERSION(3, 0, 2):
-			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
+			for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+				amdgpu_device_ip_block_add_instance(adev, &vcn_v3_0_ip_block, i);
 			if (!amdgpu_sriov_vf(adev))
 				amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block);
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 65d648429825..7f3275cff240 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -160,7 +160,7 @@ static int vcn_v3_0_early_init(struct amdgpu_ip_block *ip_block)
 static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_ring *ring;
-	int i, j, r;
+	int inst = ip_block->instance, j, r;
 	int vcn_doorbell_index = 0;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_3_0);
 	uint32_t *ptr;
@@ -189,93 +189,91 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 		vcn_doorbell_index = vcn_doorbell_index << 1;
 	}
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		volatile struct amdgpu_fw_shared *fw_shared;
+	volatile struct amdgpu_fw_shared *fw_shared;
 
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->vcn.harvest_config & (1 << inst))
+		goto done;
+
+	adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
+	adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
+	adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
+	adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
+	adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
+	adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
+
+	adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
+	adev->vcn.inst[inst].external.scratch9 = SOC15_REG_OFFSET(VCN, inst, mmUVD_SCRATCH9);
+	adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
+	adev->vcn.inst[inst].external.data0 = SOC15_REG_OFFSET(VCN, inst, mmUVD_GPCOM_VCPU_DATA0);
+	adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
+	adev->vcn.inst[inst].external.data1 = SOC15_REG_OFFSET(VCN, inst, mmUVD_GPCOM_VCPU_DATA1);
+	adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
+	adev->vcn.inst[inst].external.cmd = SOC15_REG_OFFSET(VCN, inst, mmUVD_GPCOM_VCPU_CMD);
+	adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
+	adev->vcn.inst[inst].external.nop = SOC15_REG_OFFSET(VCN, inst, mmUVD_NO_OP);
+
+	/* VCN DEC TRAP */
+	r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[inst],
+			VCN_2_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->vcn.inst[inst].irq);
+	if (r)
+		return r;
 
-		adev->vcn.internal.context_id = mmUVD_CONTEXT_ID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_vmid = mmUVD_LMI_RBC_IB_VMID_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_low = mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_bar_high = mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET;
-		adev->vcn.internal.ib_size = mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET;
-		adev->vcn.internal.gp_scratch8 = mmUVD_GP_SCRATCH8_INTERNAL_OFFSET;
-
-		adev->vcn.internal.scratch9 = mmUVD_SCRATCH9_INTERNAL_OFFSET;
-		adev->vcn.inst[i].external.scratch9 = SOC15_REG_OFFSET(VCN, i, mmUVD_SCRATCH9);
-		adev->vcn.internal.data0 = mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET;
-		adev->vcn.inst[i].external.data0 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA0);
-		adev->vcn.internal.data1 = mmUVD_GPCOM_VCPU_DATA1_INTERNAL_OFFSET;
-		adev->vcn.inst[i].external.data1 = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_DATA1);
-		adev->vcn.internal.cmd = mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET;
-		adev->vcn.inst[i].external.cmd = SOC15_REG_OFFSET(VCN, i, mmUVD_GPCOM_VCPU_CMD);
-		adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
-		adev->vcn.inst[i].external.nop = SOC15_REG_OFFSET(VCN, i, mmUVD_NO_OP);
-
-		/* VCN DEC TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i],
-				VCN_2_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->vcn.inst[i].irq);
+	atomic_set(&adev->vcn.inst[inst].sched_score, 0);
+
+	ring = &adev->vcn.inst[inst].ring_dec;
+	ring->use_doorbell = true;
+	if (amdgpu_sriov_vf(adev)) {
+		ring->doorbell_index = vcn_doorbell_index + inst * (adev->vcn.num_enc_rings + 1);
+	} else {
+		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * inst;
+	}
+	ring->vm_hub = AMDGPU_MMHUB0(0);
+	sprintf(ring->name, "vcn_dec_%d", inst);
+	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[inst].irq, 0,
+				 AMDGPU_RING_PRIO_DEFAULT,
+				 &adev->vcn.inst[inst].sched_score);
+	if (r)
+		return r;
+
+	for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+		enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(j);
+
+		/* VCN ENC TRAP */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[inst],
+			j + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[inst].irq);
 		if (r)
 			return r;
 
-		atomic_set(&adev->vcn.inst[i].sched_score, 0);
-
-		ring = &adev->vcn.inst[i].ring_dec;
+		ring = &adev->vcn.inst[inst].ring_enc[j];
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev)) {
-			ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1);
+			ring->doorbell_index = vcn_doorbell_index + inst * (adev->vcn.num_enc_rings + 1) + 1 + j;
 		} else {
-			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i;
+			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * inst;
 		}
 		ring->vm_hub = AMDGPU_MMHUB0(0);
-		sprintf(ring->name, "vcn_dec_%d", i);
-		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0,
-				     AMDGPU_RING_PRIO_DEFAULT,
-				     &adev->vcn.inst[i].sched_score);
+		sprintf(ring->name, "vcn_enc_%d.%d", inst, j);
+		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[inst].irq, 0,
+					 hw_prio, &adev->vcn.inst[inst].sched_score);
 		if (r)
 			return r;
-
-		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
-			enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(j);
-
-			/* VCN ENC TRAP */
-			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i],
-				j + VCN_2_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[i].irq);
-			if (r)
-				return r;
-
-			ring = &adev->vcn.inst[i].ring_enc[j];
-			ring->use_doorbell = true;
-			if (amdgpu_sriov_vf(adev)) {
-				ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1 + j;
-			} else {
-				ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i;
-			}
-			ring->vm_hub = AMDGPU_MMHUB0(0);
-			sprintf(ring->name, "vcn_enc_%d.%d", i, j);
-			r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0,
-					     hw_prio, &adev->vcn.inst[i].sched_score);
-			if (r)
-				return r;
-		}
-
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SW_RING_FLAG) |
-					     cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) |
-					     cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB);
-		fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED);
-		fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG;
-		if (amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(3, 1, 2))
-			fw_shared->smu_interface_info.smu_interface_type = 2;
-		else if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
-			 IP_VERSION(3, 1, 1))
-			fw_shared->smu_interface_info.smu_interface_type = 1;
-
-		if (amdgpu_vcnfw_log)
-			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 	}
 
+	fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
+	fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SW_RING_FLAG) |
+					 cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) |
+					 cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB);
+	fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED);
+	fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG;
+	if (amdgpu_ip_version(adev, UVD_HWIP, 0) == IP_VERSION(3, 1, 2))
+		fw_shared->smu_interface_info.smu_interface_type = 2;
+	else if (amdgpu_ip_version(adev, UVD_HWIP, 0) ==
+		 IP_VERSION(3, 1, 1))
+		fw_shared->smu_interface_info.smu_interface_type = 1;
+
+	if (amdgpu_vcnfw_log)
+		amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst]);
+done:
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_virt_alloc_mm_table(adev);
 		if (r)
@@ -1137,190 +1135,188 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	return 0;
 }
 
-static int vcn_v3_0_start(struct amdgpu_device *adev)
+static int vcn_v3_0_start(struct amdgpu_device *adev, unsigned int inst)
 {
 	volatile struct amdgpu_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
-	int i, j, k, r;
+	int j, k, r;
 
 	if (adev->pm.dpm_enabled)
-		amdgpu_dpm_enable_uvd(adev, true);
+		amdgpu_dpm_enable_vcn(adev, true, inst);
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->vcn.harvest_config & (1 << inst))
+		return 0;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v3_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		r = vcn_v3_0_start_dpg_mode(adev, inst, adev->vcn.indirect_sram);
+		return r;
+	}
 
-		/* disable VCN power gating */
-		vcn_v3_0_disable_static_power_gating(adev, i);
-
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, tmp);
-
-		/*SW clock gating */
-		vcn_v3_0_disable_clock_gating(adev, i);
-
-		/* 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);
-
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
-
-		/* setup mmUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, mmUVD_LMI_CTRL, tmp |
-			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_v3_0_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, mmUVD_GFX10_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);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_VCPU_CNTL), 0,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
+	/* disable VCN power gating */
+	vcn_v3_0_disable_static_power_gating(adev, inst);
 
-		for (j = 0; j < 10; ++j) {
-			uint32_t status;
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, inst, mmUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, inst, mmUVD_STATUS, tmp);
 
-			for (k = 0; k < 100; ++k) {
-				status = RREG32_SOC15(VCN, i, mmUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-			}
-			r = 0;
-			if (status & 2)
-				break;
+	/*SW clock gating */
+	vcn_v3_0_disable_clock_gating(adev, inst);
 
-			DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", i);
-			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);
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_VCPU_CNTL),
+		UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_MASTINT_EN), 0,
+		~UVD_MASTINT_EN__VCPU_EN_MASK);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_LMI_CTRL2), 0,
+		~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
+
+	tmp = RREG32_SOC15(VCN, inst, mmUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, inst, mmUVD_SOFT_RESET, tmp);
+
+	/* setup mmUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, inst, mmUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, inst, mmUVD_LMI_CTRL, tmp |
+		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, inst, mmUVD_MPC_CNTL);
+	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
+	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
+	WREG32_SOC15(VCN, inst, mmUVD_MPC_CNTL, tmp);
+
+	/* setup UVD_MPC_SET_MUXA0 */
+	WREG32_SOC15(VCN, inst, 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, inst, 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, inst, 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_v3_0_mc_resume(adev, inst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, inst, mmUVD_GFX10_ADDR_CONFIG,
+		adev->gfx.config.gb_addr_config);
 
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_RB_ARB_CTRL), 0,
+		~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_VCPU_CNTL), 0,
+		~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	for (j = 0; j < 10; ++j) {
+		uint32_t status;
+
+		for (k = 0; k < 100; ++k) {
+			status = RREG32_SOC15(VCN, inst, mmUVD_STATUS);
+			if (status & 2)
+				break;
 			mdelay(10);
-			r = -1;
 		}
+		r = 0;
+		if (status & 2)
+			break;
 
-		if (r) {
-			DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", i);
-			return r;
-		}
+		DRM_ERROR("VCN[%d] decode not responding, trying to reset the VCPU!!!\n", inst);
+		WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_VCPU_CNTL),
+			UVD_VCPU_CNTL__BLK_RST_MASK,
+			~UVD_VCPU_CNTL__BLK_RST_MASK);
+		mdelay(10);
+		WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_VCPU_CNTL), 0,
+			~UVD_VCPU_CNTL__BLK_RST_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);
+		mdelay(10);
+		r = -1;
+	}
 
-		/* clear the busy bit of VCN_STATUS */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	if (r) {
+		DRM_ERROR("VCN[%d] decode not responding, giving up!!!\n", inst);
+		return r;
+	}
 
-		WREG32_SOC15(VCN, i, mmUVD_LMI_RBC_RB_VMID, 0);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_MASTINT_EN),
+		UVD_MASTINT_EN__VCPU_EN_MASK,
+		~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		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);
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, mmUVD_STATUS), 0,
+		~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+
+	WREG32_SOC15(VCN, inst, mmUVD_LMI_RBC_RB_VMID, 0);
+
+	ring = &adev->vcn.inst[inst].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, inst, mmUVD_RBC_RB_CNTL, tmp);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+	fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
+	fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
 
-		/* programm 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));
+	/* programm the RB_BASE for ring buffer */
+	WREG32_SOC15(VCN, inst, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+		lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, inst, 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, inst, mmUVD_RBC_RB_RPTR, 0);
 
-		WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 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->rb.wptr = lower_32_bits(ring->wptr);
-		fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
-		if (amdgpu_ip_version(adev, UVD_HWIP, 0) !=
-		    IP_VERSION(3, 0, 33)) {
-			fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(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 &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
-			fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(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 &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-		}
+	WREG32_SOC15(VCN, inst, mmUVD_SCRATCH2, 0);
+	ring->wptr = RREG32_SOC15(VCN, inst, mmUVD_RBC_RB_RPTR);
+	WREG32_SOC15(VCN, inst, mmUVD_RBC_RB_WPTR,
+		lower_32_bits(ring->wptr));
+	fw_shared->rb.wptr = lower_32_bits(ring->wptr);
+	fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+	if (amdgpu_ip_version(adev, UVD_HWIP, 0) !=
+		IP_VERSION(3, 0, 33)) {
+		fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+		ring = &adev->vcn.inst[inst].ring_enc[0];
+		WREG32_SOC15(VCN, inst, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, inst, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, inst, mmUVD_RB_BASE_LO, ring->gpu_addr);
+		WREG32_SOC15(VCN, inst, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(VCN, inst, mmUVD_RB_SIZE, ring->ring_size / 4);
+		fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+		fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+		ring = &adev->vcn.inst[inst].ring_enc[1];
+		WREG32_SOC15(VCN, inst, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, inst, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+		WREG32_SOC15(VCN, inst, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+		WREG32_SOC15(VCN, inst, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(VCN, inst, mmUVD_RB_SIZE2, ring->ring_size / 4);
+		fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
 	}
 
 	return 0;
@@ -1566,77 +1562,76 @@ static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 	return 0;
 }
 
-static int vcn_v3_0_stop(struct amdgpu_device *adev)
+static int vcn_v3_0_stop(struct amdgpu_device *adev, unsigned int inst)
 {
 	uint32_t tmp;
-	int i, r = 0;
+	int r = 0;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	if (adev->vcn.harvest_config & (1 << inst))
+		goto done;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v3_0_stop_dpg_mode(adev, i);
-			continue;
-		}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		r = vcn_v3_0_stop_dpg_mode(adev, inst);
+		goto done;
+	}
 
-		/* 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, inst, 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, inst, mmUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-		/* disable 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;
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, inst, mmUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, inst, 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, inst, 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, inst, 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, inst, 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, inst, mmUVD_VCPU_CNTL), 0,
+		~(UVD_VCPU_CNTL__CLK_EN_MASK));
 
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, mmUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, mmUVD_SOFT_RESET, tmp);
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, inst, mmUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, inst, mmUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, inst, mmUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, inst, mmUVD_SOFT_RESET, tmp);
 
-		/* clear status */
-		WREG32_SOC15(VCN, i, mmUVD_STATUS, 0);
+	/* clear status */
+	WREG32_SOC15(VCN, inst, mmUVD_STATUS, 0);
 
-		/* apply HW clock gating */
-		vcn_v3_0_enable_clock_gating(adev, i);
+	/* apply HW clock gating */
+	vcn_v3_0_enable_clock_gating(adev, inst);
 
-		/* enable VCN power gating */
-		vcn_v3_0_enable_static_power_gating(adev, i);
-	}
+	/* enable VCN power gating */
+	vcn_v3_0_enable_static_power_gating(adev, inst);
 
+done:
 	if (adev->pm.dpm_enabled)
-		amdgpu_dpm_enable_uvd(adev, false);
+		amdgpu_dpm_enable_vcn(adev, false, inst);
 
 	return 0;
 }
@@ -2162,29 +2157,28 @@ static int vcn_v3_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 					  enum amd_powergating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
+	int i = ip_block->instance;
 	int ret;
 
-	for (int i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		/* for SRIOV, guest should not control VCN Power-gating
-		* MMSCH FW should control Power-gating and clock-gating
-		* guest should avoid touching CGC and PG
-		*/
-		if (amdgpu_sriov_vf(adev)) {
-			adev->vcn.cur_state[i] = AMD_PG_STATE_UNGATE;
-			return 0;
-		}
+	/* for SRIOV, guest should not control VCN Power-gating
+	* MMSCH FW should control Power-gating and clock-gating
+	* guest should avoid touching CGC and PG
+	*/
+	if (amdgpu_sriov_vf(adev)) {
+		adev->vcn.cur_state[i] = AMD_PG_STATE_UNGATE;
+		return 0;
+	}
 
-		if (state == adev->vcn.cur_state[i])
-			return 0;
+	if (state == adev->vcn.cur_state[i])
+		return 0;
 
-		if (state == AMD_PG_STATE_GATE)
-			ret = vcn_v3_0_stop(adev);
-		else
-			ret = vcn_v3_0_start(adev);
+	if (state == AMD_PG_STATE_GATE)
+		ret = vcn_v3_0_stop(adev, i);
+	else
+		ret = vcn_v3_0_start(adev, i);
 
-		if (!ret)
-			adev->vcn.cur_state[i] = state;
-	}
+	if (!ret)
+		adev->vcn.cur_state[i] = state;
 
 	return ret;
 }
-- 
2.34.1