[PATCH 04/44] drm/amdgpu/vcn4.0.3: split code along instances

Boyuan Zhang Boyuan.Zhang at amd.com
Tue Feb 4 15:50:58 UTC 2025


On 2025-01-31 11:57, Alex Deucher wrote:
> Split the code on a per instance basis.  This will allow
> us to use the per instance functions in the future to
> handle more things per instance.
>
> Signed-off-by: Alex Deucher<alexander.deucher at amd.com>


Reviewed-by: Boyuan Zhang <Boyuan.Zhang at amd.com> 
<mailto:Boyuan.Zhang at amd.com>


> ---
>   drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 417 ++++++++++++------------
>   1 file changed, 206 insertions(+), 211 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> index f0716c10f23e4..6293d1dc02fec 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
> @@ -1117,177 +1117,172 @@ static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev)
>    * vcn_v4_0_3_start - VCN start
>    *
>    * @adev: amdgpu_device pointer
> + * @i: instance to start
>    *
>    * Start VCN block
>    */
> -static int vcn_v4_0_3_start(struct amdgpu_device *adev)
> +static int vcn_v4_0_3_start(struct amdgpu_device *adev, int i)
>   {
>   	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
>   	struct amdgpu_ring *ring;
> -	int i, j, k, r, vcn_inst;
> +	int j, k, r, vcn_inst;
>   	uint32_t tmp;
>   
> -	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, i);
>   
> -	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> -		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
> -			r = vcn_v4_0_3_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
> -			continue;
> -		}
> +	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
> +		return vcn_v4_0_3_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
>   
> -		vcn_inst = GET_INST(VCN, i);
> -		/* set VCN status busy */
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) |
> -		      UVD_STATUS__UVD_BUSY;
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
> -
> -		/*SW clock gating */
> -		vcn_v4_0_3_disable_clock_gating(adev, i);
> -
> -		/* enable VCPU clock */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
> -			 UVD_VCPU_CNTL__CLK_EN_MASK,
> -			 ~UVD_VCPU_CNTL__CLK_EN_MASK);
> -
> -		/* disable master interrupt */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
> -			 ~UVD_MASTINT_EN__VCPU_EN_MASK);
> -
> -		/* enable LMI MC and UMC channels */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
> -			 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
> -
> -		tmp = RREG32_SOC15(VCN, 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, vcn_inst, regUVD_SOFT_RESET, tmp);
> -
> -		/* setup regUVD_LMI_CTRL */
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
> -		WREG32_SOC15(VCN, 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);
> -
> -		/* setup regUVD_MPC_CNTL */
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL);
> -		tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
> -		tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp);
> -
> -		/* setup UVD_MPC_SET_MUXA0 */
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_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 UVD_MPC_SET_MUX */
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_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_v4_0_3_mc_resume(adev, i);
> -
> -		/* VCN global tiling registers */
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG,
> -			     adev->gfx.config.gb_addr_config);
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
> -			     adev->gfx.config.gb_addr_config);
> -
> -		/* unblock VCPU register access */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, 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, vcn_inst, regUVD_VCPU_CNTL), 0,
> -			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
> +	vcn_inst = GET_INST(VCN, i);
> +	/* set VCN status busy */
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_STATUS) |
> +		UVD_STATUS__UVD_BUSY;
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, tmp);
>   
> -		for (j = 0; j < 10; ++j) {
> -			uint32_t status;
> +	/* SW clock gating */
> +	vcn_v4_0_3_disable_clock_gating(adev, i);
>   
> -			for (k = 0; k < 100; ++k) {
> -				status = RREG32_SOC15(VCN, vcn_inst,
> -						      regUVD_STATUS);
> -				if (status & 2)
> -					break;
> -				mdelay(10);
> -			}
> -			r = 0;
> -			if (status & 2)
> -				break;
> +	/* enable VCPU clock */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
> +		 UVD_VCPU_CNTL__CLK_EN_MASK,
> +		 ~UVD_VCPU_CNTL__CLK_EN_MASK);
>   
> -			DRM_DEV_ERROR(adev->dev,
> -				"VCN decode not responding, trying to reset the VCPU!!!\n");
> -			WREG32_P(SOC15_REG_OFFSET(VCN, 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, vcn_inst,
> -						  regUVD_VCPU_CNTL),
> -				 0, ~UVD_VCPU_CNTL__BLK_RST_MASK);
> +	/* disable master interrupt */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN), 0,
> +		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
> +
> +	/* enable LMI MC and UMC channels */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_LMI_CTRL2), 0,
> +		 ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
> +
> +	tmp = RREG32_SOC15(VCN, 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, vcn_inst, regUVD_SOFT_RESET, tmp);
> +
> +	/* setup regUVD_LMI_CTRL */
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL);
> +	WREG32_SOC15(VCN, 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);
> +
> +	/* setup regUVD_MPC_CNTL */
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL);
> +	tmp &= ~UVD_MPC_CNTL__REPLACEMENT_MODE_MASK;
> +	tmp |= 0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT;
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_MPC_CNTL, tmp);
> +
> +	/* setup UVD_MPC_SET_MUXA0 */
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_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 UVD_MPC_SET_MUX */
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_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_v4_0_3_mc_resume(adev, i);
> +
> +	/* VCN global tiling registers */
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_GFX8_ADDR_CONFIG,
> +		     adev->gfx.config.gb_addr_config);
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_GFX10_ADDR_CONFIG,
> +		     adev->gfx.config.gb_addr_config);
>   
> +	/* unblock VCPU register access */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, 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, 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, vcn_inst,
> +					      regUVD_STATUS);
> +			if (status & 2)
> +				break;
>   			mdelay(10);
> -			r = -1;
>   		}
> +		r = 0;
> +		if (status & 2)
> +			break;
>   
> -		if (r) {
> -			DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n");
> -			return r;
> -		}
> +		DRM_DEV_ERROR(adev->dev,
> +			      "VCN decode not responding, trying to reset the VCPU!!!\n");
> +		WREG32_P(SOC15_REG_OFFSET(VCN, 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, vcn_inst,
> +					  regUVD_VCPU_CNTL),
> +			 0, ~UVD_VCPU_CNTL__BLK_RST_MASK);
>   
> -		/* enable master interrupt */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_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, vcn_inst, regUVD_STATUS), 0,
> -			 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
> +	if (r) {
> +		DRM_DEV_ERROR(adev->dev, "VCN decode not responding, giving up!!!\n");
> +		return r;
> +	}
>   
> -		ring = &adev->vcn.inst[i].ring_enc[0];
> -		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> +	/* enable master interrupt */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_MASTINT_EN),
> +		 UVD_MASTINT_EN__VCPU_EN_MASK,
> +		 ~UVD_MASTINT_EN__VCPU_EN_MASK);
>   
> -		/* program the RB_BASE for ring buffer */
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO,
> -			     lower_32_bits(ring->gpu_addr));
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI,
> -			     upper_32_bits(ring->gpu_addr));
> +	/* clear the busy bit of VCN_STATUS */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_STATUS), 0,
> +		 ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT));
>   
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE,
> -			     ring->ring_size / sizeof(uint32_t));
> +	ring = &adev->vcn.inst[i].ring_enc[0];
> +	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
>   
> -		/* resetting ring, fw should not check RB ring */
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
> -		tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK);
> -		WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
> +	/* program the RB_BASE for ring buffer */
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_LO,
> +		     lower_32_bits(ring->gpu_addr));
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_BASE_HI,
> +		     upper_32_bits(ring->gpu_addr));
> +
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_SIZE,
> +		     ring->ring_size / sizeof(uint32_t));
> +
> +	/* resetting ring, fw should not check RB ring */
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
> +	tmp &= ~(VCN_RB_ENABLE__RB_EN_MASK);
> +	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
>   
> -		/* Initialize the ring buffer's read and write pointers */
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
> +	/* Initialize the ring buffer's read and write pointers */
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
>   
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
> -		tmp |= VCN_RB_ENABLE__RB_EN_MASK;
> -		WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
> +	tmp |= VCN_RB_ENABLE__RB_EN_MASK;
> +	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
>   
> -		ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
> -		fw_shared->sq.queue_mode &=
> -			cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF));
> +	ring->wptr = RREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR);
> +	fw_shared->sq.queue_mode &=
> +		cpu_to_le32(~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF));
>   
> -	}
>   	return 0;
>   }
>   
> @@ -1327,86 +1322,84 @@ static int vcn_v4_0_3_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
>    * vcn_v4_0_3_stop - VCN stop
>    *
>    * @adev: amdgpu_device pointer
> + * @i: instance to stop
>    *
>    * Stop VCN block
>    */
> -static int vcn_v4_0_3_stop(struct amdgpu_device *adev)
> +static int vcn_v4_0_3_stop(struct amdgpu_device *adev, int i)
>   {
>   	volatile struct amdgpu_vcn4_fw_shared *fw_shared;
> -	int i, r = 0, vcn_inst;
> +	int r = 0, vcn_inst;
>   	uint32_t tmp;
>   
> -	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> -		vcn_inst = GET_INST(VCN, i);
> +	vcn_inst = GET_INST(VCN, i);
>   
> -		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> -		fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
> +	fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
> +	fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
>   
> -		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
> -			vcn_v4_0_3_stop_dpg_mode(adev, i);
> -			continue;
> -		}
> +	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
> +		vcn_v4_0_3_stop_dpg_mode(adev, i);
> +		return 0;
> +	}
>   
> -		/* wait for vcn idle */
> -		r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS,
> -				       UVD_STATUS__IDLE, 0x7);
> -		if (r)
> -			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, vcn_inst, regUVD_LMI_STATUS, tmp,
> -				       tmp);
> -		if (r)
> -			goto Done;
> -
> -		/* stall UMC channel */
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
> -		tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
> -		WREG32_SOC15(VCN, 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, vcn_inst, regUVD_LMI_STATUS, tmp,
> -				       tmp);
> -		if (r)
> -			goto Done;
> +	/* wait for vcn idle */
> +	r = SOC15_WAIT_ON_RREG(VCN, vcn_inst, regUVD_STATUS,
> +			       UVD_STATUS__IDLE, 0x7);
> +	if (r)
> +		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, vcn_inst, regUVD_LMI_STATUS, tmp,
> +			       tmp);
> +	if (r)
> +		goto Done;
> +
> +	/* stall UMC channel */
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_LMI_CTRL2);
> +	tmp |= UVD_LMI_CTRL2__STALL_ARB_UMC_MASK;
> +	WREG32_SOC15(VCN, 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, vcn_inst, regUVD_LMI_STATUS, tmp,
> +			       tmp);
> +	if (r)
> +		goto Done;
>   
> -		/* Unblock VCPU Register access */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
> -			 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
> -			 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
> +	/* Unblock VCPU Register access */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_RB_ARB_CTRL),
> +		 UVD_RB_ARB_CTRL__VCPU_DIS_MASK,
> +		 ~UVD_RB_ARB_CTRL__VCPU_DIS_MASK);
>   
> -		/* release VCPU reset to boot */
> -		WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL),
> -			 UVD_VCPU_CNTL__BLK_RST_MASK,
> -			 ~UVD_VCPU_CNTL__BLK_RST_MASK);
> +	/* release VCPU reset to boot */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, 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, vcn_inst, regUVD_VCPU_CNTL), 0,
> -			 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
> +	/* disable VCPU clock */
> +	WREG32_P(SOC15_REG_OFFSET(VCN, vcn_inst, regUVD_VCPU_CNTL), 0,
> +		 ~(UVD_VCPU_CNTL__CLK_EN_MASK));
>   
> -		/* reset LMI UMC/LMI/VCPU */
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
> -		tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
> +	/* reset LMI UMC/LMI/VCPU */
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
> +	tmp |= UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK;
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
>   
> -		tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
> -		tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
> +	tmp = RREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET);
> +	tmp |= UVD_SOFT_RESET__LMI_SOFT_RESET_MASK;
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_SOFT_RESET, tmp);
>   
> -		/* clear VCN status */
> -		WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
> +	/* clear VCN status */
> +	WREG32_SOC15(VCN, vcn_inst, regUVD_STATUS, 0);
> +
> +	/* apply HW clock gating */
> +	vcn_v4_0_3_enable_clock_gating(adev, i);
>   
> -		/* apply HW clock gating */
> -		vcn_v4_0_3_enable_clock_gating(adev, i);
> -	}
>   Done:
> -	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> -		if (adev->pm.dpm_enabled)
> -			amdgpu_dpm_enable_vcn(adev, false, i);
> -	}
> +	if (adev->pm.dpm_enabled)
> +		amdgpu_dpm_enable_vcn(adev, false, i);
>   
>   	return 0;
>   }
> @@ -1663,7 +1656,7 @@ static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block,
>   					  enum amd_powergating_state state)
>   {
>   	struct amdgpu_device *adev = ip_block->adev;
> -	int ret;
> +	int ret = 0, i;
>   
>   	/* for SRIOV, guest should not control VCN Power-gating
>   	 * MMSCH FW should control Power-gating and clock-gating
> @@ -1677,10 +1670,12 @@ static int vcn_v4_0_3_set_powergating_state(struct amdgpu_ip_block *ip_block,
>   	if (state == adev->vcn.cur_state)
>   		return 0;
>   
> -	if (state == AMD_PG_STATE_GATE)
> -		ret = vcn_v4_0_3_stop(adev);
> -	else
> -		ret = vcn_v4_0_3_start(adev);
> +	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> +		if (state == AMD_PG_STATE_GATE)
> +			ret |= vcn_v4_0_3_stop(adev, i);
> +		else
> +			ret |= vcn_v4_0_3_start(adev, i);
> +	}
>   
>   	if (!ret)
>   		adev->vcn.cur_state = state;
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20250204/bacae6b4/attachment-0001.htm>


More information about the amd-gfx mailing list