[PATCH 17/29] drm/amdgpu: power vcn 5_0_0 by instance

boyuan.zhang at amd.com boyuan.zhang at amd.com
Fri Oct 25 02:35:33 UTC 2024


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

For vcn 5_0_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.

v2: rename "i"/"j" to "inst" for instance value.

Signed-off-by: Boyuan Zhang <boyuan.zhang at amd.com>
Reviewed-by: Christian König <christian.koenig at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c |   3 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c       | 432 +++++++++---------
 2 files changed, 213 insertions(+), 222 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 48160fa4d8ef..3c85a692a34e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2363,7 +2363,8 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &jpeg_v4_0_5_ip_block);
 			break;
 		case IP_VERSION(5, 0, 0):
-			amdgpu_device_ip_block_add(adev, &vcn_v5_0_0_ip_block);
+			for (i = 0; i < adev->vcn.num_vcn_inst; ++i)
+				amdgpu_device_ip_block_add(adev, &vcn_v5_0_0_ip_block);
 			amdgpu_device_ip_block_add(adev, &jpeg_v5_0_0_ip_block);
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 4ecf0aea156f..15620e111d04 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -116,7 +116,7 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = ip_block->adev;
-	int i, r;
+	int inst = ip_block->instance, r;
 	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_5_0);
 	uint32_t *ptr;
 
@@ -130,46 +130,44 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		volatile struct amdgpu_vcn5_fw_shared *fw_shared;
-
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 
-		atomic_set(&adev->vcn.inst[i].sched_score, 0);
+	if (adev->vcn.harvest_config & (1 << inst))
+		goto done;
 
-		/* VCN UNIFIED TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i],
-				VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[i].irq);
-		if (r)
-			return r;
+	atomic_set(&adev->vcn.inst[inst].sched_score, 0);
 
-		/* VCN POISON TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i],
-				VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].irq);
-		if (r)
-			return r;
+	/* VCN UNIFIED TRAP */
+	r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[inst],
+			VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE, &adev->vcn.inst[inst].irq);
+	if (r)
+		return r;
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		ring->use_doorbell = true;
-		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i;
+	/* VCN POISON TRAP */
+	r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[inst],
+			VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[inst].irq);
+	if (r)
+		return r;
 
-		ring->vm_hub = AMDGPU_MMHUB0(0);
-		sprintf(ring->name, "vcn_unified_%d", i);
+	ring = &adev->vcn.inst[inst].ring_enc[0];
+	ring->use_doorbell = true;
+	ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * inst;
 
-		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0,
-						AMDGPU_RING_PRIO_0, &adev->vcn.inst[i].sched_score);
-		if (r)
-			return r;
+	ring->vm_hub = AMDGPU_MMHUB0(0);
+	sprintf(ring->name, "vcn_unified_%d", inst);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
-		fw_shared->sq.is_enabled = 1;
+	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[inst].irq, 0,
+					AMDGPU_RING_PRIO_0, &adev->vcn.inst[inst].sched_score);
+	if (r)
+		return r;
 
-		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_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
+	fw_shared->sq.is_enabled = 1;
 
+	if (amdgpu_vcnfw_log)
+		amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst]);
+done:
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
 		adev->vcn.pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode;
 
@@ -753,151 +751,147 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, b
  *
  * Start VCN block
  */
-static int vcn_v5_0_0_start(struct amdgpu_device *adev)
+static int vcn_v5_0_0_start(struct amdgpu_device *adev, unsigned int inst)
 {
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 	struct amdgpu_ring *ring;
 	uint32_t 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->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, true, inst);
+
+	if (adev->vcn.harvest_config & (1 << inst))
+		return 0;
+
+	fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		r = vcn_v5_0_0_start_dpg_mode(adev, inst, adev->vcn.indirect_sram);
+		return r;
 	}
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
+	/* disable VCN power gating */
+	vcn_v5_0_0_disable_static_power_gating(adev, inst);
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+	/* set VCN status busy */
+	tmp = RREG32_SOC15(VCN, inst, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
+	WREG32_SOC15(VCN, inst, regUVD_STATUS, tmp);
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			r = vcn_v5_0_0_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
-			continue;
-		}
+	/* enable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_VCPU_CNTL),
+		UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
 
-		/* disable VCN power gating */
-		vcn_v5_0_0_disable_static_power_gating(adev, i);
+	/* disable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_MASTINT_EN), 0,
+		~UVD_MASTINT_EN__VCPU_EN_MASK);
 
-		/* set VCN status busy */
-		tmp = RREG32_SOC15(VCN, i, regUVD_STATUS) | UVD_STATUS__UVD_BUSY;
-		WREG32_SOC15(VCN, i, regUVD_STATUS, tmp);
+	/* enable LMI MC and UMC channels */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_LMI_CTRL2), 0,
+		~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
 
-		/* enable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__CLK_EN_MASK, ~UVD_VCPU_CNTL__CLK_EN_MASK);
+	tmp = RREG32_SOC15(VCN, inst, regUVD_SOFT_RESET);
+	tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, inst, regUVD_SOFT_RESET, tmp);
 
-		/* disable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN), 0,
-			~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* setup regUVD_LMI_CTRL */
+	tmp = RREG32_SOC15(VCN, inst, regUVD_LMI_CTRL);
+	WREG32_SOC15(VCN, inst, regUVD_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);
 
-		/* enable LMI MC and UMC channels */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_LMI_CTRL2), 0,
-			~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp &= ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		tmp &= ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* setup regUVD_LMI_CTRL */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL);
-		WREG32_SOC15(VCN, i, regUVD_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);
-
-		vcn_v5_0_0_mc_resume(adev, i);
-
-		/* VCN global tiling registers */
-		WREG32_SOC15(VCN, i, regUVD_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* unblock VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_RB_ARB_CTRL), 0,
-			~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
-
-		/* release VCPU reset to boot */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_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, i, regUVD_STATUS);
-				if (status & 2)
-					break;
-				mdelay(10);
-				if (amdgpu_emu_mode == 1)
-					msleep(1);
-			}
+	vcn_v5_0_0_mc_resume(adev, inst);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15(VCN, inst, regUVD_GFX10_ADDR_CONFIG,
+		adev->gfx.config.gb_addr_config);
+
+	/* unblock VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_RB_ARB_CTRL), 0,
+		~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
+
+	/* release VCPU reset to boot */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_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, regUVD_STATUS);
+			if (status & 2)
+				break;
+			mdelay(10);
+			if (amdgpu_emu_mode == 1)
+				msleep(1);
+		}
 
-			if (amdgpu_emu_mode == 1) {
-				r = -1;
-				if (status & 2) {
-					r = 0;
-					break;
-				}
-			} else {
+		if (amdgpu_emu_mode == 1) {
+			r = -1;
+			if (status & 2) {
 				r = 0;
-				if (status & 2)
-					break;
-
-				dev_err(adev->dev,
-					"VCN[%d] is not responding, trying to reset the VCPU!!!\n", i);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL),
-							UVD_VCPU_CNTL__BLK_RST_MASK,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-				mdelay(10);
-				WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-							~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-				mdelay(10);
-				r = -1;
+				break;
 			}
+		} else {
+			r = 0;
+			if (status & 2)
+				break;
+
+			dev_err(adev->dev,
+				"VCN[%d] is not responding, trying to reset the VCPU!!!\n", inst);
+			WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_VCPU_CNTL),
+						UVD_VCPU_CNTL__BLK_RST_MASK,
+						~UVD_VCPU_CNTL__BLK_RST_MASK);
+			mdelay(10);
+			WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_VCPU_CNTL), 0,
+						~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+			mdelay(10);
+			r = -1;
 		}
+	}
 
-		if (r) {
-			dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", i);
-			return r;
-		}
+	if (r) {
+		dev_err(adev->dev, "VCN[%d] is not responding, giving up!!!\n", inst);
+		return r;
+	}
 
-		/* enable master interrupt */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_MASTINT_EN),
-				UVD_MASTINT_EN__VCPU_EN_MASK,
-				~UVD_MASTINT_EN__VCPU_EN_MASK);
+	/* enable master interrupt */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_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, regUVD_STATUS), 0,
-			~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
+	/* clear the busy bit of VCN_STATUS */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_STATUS), 0,
+		~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
 
-		ring = &adev->vcn.inst[i].ring_enc[0];
-		WREG32_SOC15(VCN, i, regVCN_RB1_DB_CTRL,
-			ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
-			VCN_RB1_DB_CTRL__EN_MASK);
-
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_LO, ring->gpu_addr);
-		WREG32_SOC15(VCN, i, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(VCN, i, regUVD_RB_SIZE, ring->ring_size / 4);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
-		WREG32_SOC15(VCN, i, regUVD_RB_RPTR, 0);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, 0);
-
-		tmp = RREG32_SOC15(VCN, i, regUVD_RB_RPTR);
-		WREG32_SOC15(VCN, i, regUVD_RB_WPTR, tmp);
-		ring->wptr = RREG32_SOC15(VCN, i, regUVD_RB_WPTR);
-
-		tmp = RREG32_SOC15(VCN, i, regVCN_RB_ENABLE);
-		tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
-		WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp);
-		fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
-	}
+	ring = &adev->vcn.inst[inst].ring_enc[0];
+	WREG32_SOC15(VCN, inst, regVCN_RB1_DB_CTRL,
+		ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT |
+		VCN_RB1_DB_CTRL__EN_MASK);
+
+	WREG32_SOC15(VCN, inst, regUVD_RB_BASE_LO, ring->gpu_addr);
+	WREG32_SOC15(VCN, inst, regUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(VCN, inst, regUVD_RB_SIZE, ring->ring_size / 4);
+
+	tmp = RREG32_SOC15(VCN, inst, regVCN_RB_ENABLE);
+	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
+	WREG32_SOC15(VCN, inst, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+	WREG32_SOC15(VCN, inst, regUVD_RB_RPTR, 0);
+	WREG32_SOC15(VCN, inst, regUVD_RB_WPTR, 0);
+
+	tmp = RREG32_SOC15(VCN, inst, regUVD_RB_RPTR);
+	WREG32_SOC15(VCN, inst, regUVD_RB_WPTR, tmp);
+	ring->wptr = RREG32_SOC15(VCN, inst, regUVD_RB_WPTR);
+
+	tmp = RREG32_SOC15(VCN, inst, regVCN_RB_ENABLE);
+	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
+	WREG32_SOC15(VCN, inst, regVCN_RB_ENABLE, tmp);
+	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	return 0;
 }
@@ -939,80 +933,76 @@ static void vcn_v5_0_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
  *
  * Stop VCN block
  */
-static int vcn_v5_0_0_stop(struct amdgpu_device *adev)
+static int vcn_v5_0_0_stop(struct amdgpu_device *adev, unsigned int inst)
 {
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared;
 	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;
-
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+	if (adev->vcn.harvest_config & (1 << inst))
+		goto done;
 
-		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-			vcn_v5_0_0_stop_dpg_mode(adev, i);
-			continue;
-		}
+	fw_shared = adev->vcn.inst[inst].fw_shared.cpu_addr;
+	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
 
-		/* wait for vcn idle */
-		r = SOC15_WAIT_ON_RREG(VCN, i, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
-		if (r)
-			return r;
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		vcn_v5_0_0_stop_dpg_mode(adev, inst);
+		goto done;
+	}
 
-		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, regUVD_LMI_STATUS, tmp, tmp);
-		if (r)
-			return r;
+	/* wait for vcn idle */
+	r = SOC15_WAIT_ON_RREG(VCN, inst, regUVD_STATUS, UVD_STATUS__IDLE, 0x7);
+	if (r)
+		return r;
 
-		/* disable LMI UMC channel */
-		tmp = RREG32_SOC15(VCN, i, regUVD_LMI_CTRL2);
-		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
-		WREG32_SOC15(VCN, i, regUVD_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, regUVD_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, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-		/* block VCPU register access */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_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, regUVD_VCPU_CNTL),
-			UVD_VCPU_CNTL__BLK_RST_MASK,
-			~UVD_VCPU_CNTL__BLK_RST_MASK);
-
-		/* disable VCPU clock */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, regUVD_VCPU_CNTL), 0,
-			~(UVD_VCPU_CNTL__CLK_EN_MASK));
-
-		/* apply soft reset */
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-		tmp = RREG32_SOC15(VCN, i, regUVD_SOFT_RESET);
-		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
-		WREG32_SOC15(VCN, i, regUVD_SOFT_RESET, tmp);
-
-		/* clear status */
-		WREG32_SOC15(VCN, i, regUVD_STATUS, 0);
-
-		/* enable VCN power gating */
-		vcn_v5_0_0_enable_static_power_gating(adev, i);
-	}
+	/* disable LMI UMC channel */
+	tmp = RREG32_SOC15(VCN, inst, regUVD_LMI_CTRL2);
+	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
+	WREG32_SOC15(VCN, inst, regUVD_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, regUVD_LMI_STATUS, tmp, tmp);
+	if (r)
+		return r;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_vcn(adev, false, i);
-	}
+	/* block VCPU register access */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_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, inst, regUVD_VCPU_CNTL),
+		UVD_VCPU_CNTL__BLK_RST_MASK,
+		~UVD_VCPU_CNTL__BLK_RST_MASK);
+
+	/* disable VCPU clock */
+	WREG32_P(SOC15_REG_OFFSET(VCN, inst, regUVD_VCPU_CNTL), 0,
+		~(UVD_VCPU_CNTL__CLK_EN_MASK));
+
+	/* apply soft reset */
+	tmp = RREG32_SOC15(VCN, inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, inst, regUVD_SOFT_RESET, tmp);
+	tmp = RREG32_SOC15(VCN, inst, regUVD_SOFT_RESET);
+	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
+	WREG32_SOC15(VCN, inst, regUVD_SOFT_RESET, tmp);
+
+	/* clear status */
+	WREG32_SOC15(VCN, inst, regUVD_STATUS, 0);
+
+	/* enable VCN power gating */
+	vcn_v5_0_0_enable_static_power_gating(adev, inst);
+done:
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_vcn(adev, false, inst);
 
 	return 0;
 }
@@ -1269,9 +1259,9 @@ static int vcn_v5_0_0_set_powergating_state(struct amdgpu_ip_block *ip_block,
 		return 0;
 
 	if (state == AMD_PG_STATE_GATE)
-		ret = vcn_v5_0_0_stop(adev);
+		ret = vcn_v5_0_0_stop(adev, inst);
 	else
-		ret = vcn_v5_0_0_start(adev);
+		ret = vcn_v5_0_0_start(adev, inst);
 
 	if (!ret)
 		adev->vcn.inst[inst].cur_state = state;
-- 
2.34.1



More information about the amd-gfx mailing list