From: Boyuan Zhang <Boyuan.Zhang@amd.com>
To: Alex Deucher <alexander.deucher@amd.com>, amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 01/44] drm/amdgpu/vcn2.5: split code along instances
Date: Tue, 4 Feb 2025 10:35:27 -0500 [thread overview]
Message-ID: <3f03c719-17fd-4d17-9046-1698be10fd36@amd.com> (raw)
In-Reply-To: <20250131165741.1798488-2-alexander.deucher@amd.com>
[-- Attachment #1: Type: text/plain, Size: 37917 bytes --]
On 2025-01-31 11:56, 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@amd.com>
Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
<mailto:Boyuan.Zhang@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 841 +++++++++++++-------------
> 1 file changed, 411 insertions(+), 430 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
> index b518202955cad..b9be304aa294b 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,
> @@ -774,65 +770,63 @@ static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
> }
>
> /**
> - * vcn_v2_5_enable_clock_gating - enable VCN clock gating
> + * vcn_v2_5_enable_clock_gating_inst - 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 */
> + WREG32_P(SOC15_REG_OFFSET(VCN, i, mmUVD_POWER_STATUS),
> + UVD_POWER_STATUS__UVD_POWER_STATUS_MASK,
> + ~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
>
> - 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;
> }
> @@ -1811,16 +1787,19 @@ static int vcn_v2_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
> {
> struct amdgpu_device *adev = ip_block->adev;
> bool enable = (state == AMD_CG_STATE_GATE);
> + int i;
>
> if (amdgpu_sriov_vf(adev))
> return 0;
>
> - if (enable) {
> - if (!vcn_v2_5_is_idle(adev))
> - return -EBUSY;
> - vcn_v2_5_enable_clock_gating(adev);
> - } else {
> - vcn_v2_5_disable_clock_gating(adev);
> + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> + if (enable) {
> + if (!vcn_v2_5_is_idle(adev))
> + return -EBUSY;
> + vcn_v2_5_enable_clock_gating(adev, i);
> + } else {
> + vcn_v2_5_disable_clock_gating(adev, i);
> + }
> }
>
> return 0;
> @@ -1830,20 +1809,22 @@ static int vcn_v2_5_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;
>
> if (amdgpu_sriov_vf(adev))
> return 0;
>
> - if(state == adev->vcn.cur_state)
> + if (state == adev->vcn.cur_state)
> return 0;
>
> - if (state == AMD_PG_STATE_GATE)
> - ret = vcn_v2_5_stop(adev);
> - else
> - ret = vcn_v2_5_start(adev);
> + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
> + if (state == AMD_PG_STATE_GATE)
> + ret |= vcn_v2_5_stop(adev, i);
> + else
> + ret |= vcn_v2_5_start(adev, i);
> + }
>
> - if(!ret)
> + if (!ret)
> adev->vcn.cur_state = state;
>
> return ret;
[-- Attachment #2: Type: text/html, Size: 37827 bytes --]
next prev parent reply other threads:[~2025-02-04 15:35 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-31 16:56 [PATCH V3 00/44] VCN instance rework Alex Deucher
2025-01-31 16:56 ` [PATCH 01/44] drm/amdgpu/vcn2.5: split code along instances Alex Deucher
2025-02-04 15:35 ` Boyuan Zhang [this message]
2025-01-31 16:56 ` [PATCH 02/44] drm/amdgpu/vcn3.0: " Alex Deucher
2025-02-04 15:40 ` Boyuan Zhang
2025-01-31 16:56 ` [PATCH 03/44] drm/amdgpu/vcn4.0: " Alex Deucher
2025-02-04 15:50 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 04/44] drm/amdgpu/vcn4.0.3: " Alex Deucher
2025-02-04 15:50 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 05/44] drm/amdgpu/vcn4.0.5: " Alex Deucher
2025-02-04 15:51 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 06/44] drm/amdgpu/vcn5.0.0: " Alex Deucher
2025-02-04 15:56 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 07/44] drm/amdgpu/vcn5.0.1: " Alex Deucher
2025-02-04 15:57 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 08/44] drm/amdgpu/vcn: switch work handler to be per instance Alex Deucher
2025-02-04 20:59 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 09/44] drm/amdgpu/vcn: make powergating status " Alex Deucher
2025-02-05 1:50 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 10/44] drm/amdgpu/vcn: move more instanced data to vcn_instance Alex Deucher
2025-02-05 3:06 ` Boyuan Zhang
2025-02-05 20:09 ` Alex Deucher
2025-02-06 13:39 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 11/44] drm/amdgpu/vcn: switch vcn helpers to be instance based Alex Deucher
2025-02-05 13:23 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 12/44] drm/amdgpu/vcn3.0: convert internal functions to use vcn_inst Alex Deucher
2025-02-05 15:00 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 13/44] drm/amdgpu/vcn1.0: " Alex Deucher
2025-02-05 15:01 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 14/44] drm/amdgpu/vcn2.0: " Alex Deucher
2025-02-05 15:01 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 15/44] drm/amdgpu/vcn2.5: " Alex Deucher
2025-02-05 15:02 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 16/44] drm/amdgpu/vcn4.0: " Alex Deucher
2025-02-05 15:03 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 17/44] drm/amdgpu/vcn4.0.3: " Alex Deucher
2025-02-05 15:03 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 18/44] drm/amdgpu/vcn4.0.5: " Alex Deucher
2025-02-05 15:04 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 19/44] drm/amdgpu/vcn5.0.0: " Alex Deucher
2025-02-05 15:05 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 20/44] drm/amdgpu/vcn5.0.1: " Alex Deucher
2025-02-05 15:05 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 21/44] drm/amdgpu/vcn: adjust pause_dpg_mode function signature Alex Deucher
2025-02-06 13:40 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 22/44] drm/amdgpu/vcn: add new per instance callback for powergating Alex Deucher
2025-02-06 13:40 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 23/44] drm/amdgpu/vcn1.0: add set_pg_state callback Alex Deucher
2025-02-06 13:46 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 24/44] drm/amdgpu/vcn2.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 25/44] drm/amdgpu/vcn2.5: " Alex Deucher
2025-01-31 16:57 ` [PATCH 26/44] drm/amdgpu/vcn3.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 27/44] drm/amdgpu/vcn4.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 28/44] drm/amdgpu/vcn4.0.3: " Alex Deucher
2025-01-31 16:57 ` [PATCH 29/44] drm/amdgpu/vcn4.0.5: " Alex Deucher
2025-01-31 16:57 ` [PATCH 30/44] drm/amdgpu/vcn5.0.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 31/44] drm/amdgpu/vcn5.0.1: " Alex Deucher
2025-01-31 16:57 ` [PATCH 32/44] drm/amdgpu/vcn: use per instance callbacks for idle work handler Alex Deucher
2025-02-06 13:53 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 33/44] drm/amdgpu/vcn: add a generic helper for set_power_gating_state Alex Deucher
2025-02-06 13:54 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 34/44] drm/amdgpu/vcn1.0: use generic set_power_gating_state helper Alex Deucher
2025-01-31 16:57 ` [PATCH 35/44] drm/amdgpu/vcn2.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 36/44] drm/amdgpu/vcn2.5: " Alex Deucher
2025-01-31 16:57 ` [PATCH 37/44] drm/amdgpu/vcn3.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 38/44] drm/amdgpu/vcn4.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 39/44] drm/amdgpu/vcn4.0.3: " Alex Deucher
2025-01-31 16:57 ` [PATCH 40/44] drm/amdgpu/vcn4.0.5: " Alex Deucher
2025-01-31 16:57 ` [PATCH 41/44] drm/amdgpu/vcn5.0.0: " Alex Deucher
2025-01-31 16:57 ` [PATCH 42/44] drm/amdgpu/vcn5.0.1: " Alex Deucher
2025-01-31 16:57 ` [PATCH 43/44] drm/amdgpu/vcn: optimize firmware storage Alex Deucher
2025-02-06 14:48 ` Boyuan Zhang
2025-01-31 16:57 ` [PATCH 44/44] drm/amdgpu/vcn: use dev_info() for firmware information Alex Deucher
2025-02-06 14:49 ` Boyuan Zhang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3f03c719-17fd-4d17-9046-1698be10fd36@amd.com \
--to=boyuan.zhang@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.