Re: [PATCH 2/3 v2] drm/amdgpu: add debug flag to place fw bo on vram for frontdoor loading

[Christian König <ckoenig.leichtzumerken@xxxxxxxxx>]

Am 09.01.24 um 14:00 schrieb Le Ma:
> Use debug_mask=0x8 param to help isolating data path issues
> on new systems in early phase.
>
> v2: rename the flag for explicitness (lijo)
>
> Signed-off-by: Le Ma <le.ma@xxxxxxx>

Reviewed-by: Christian König <christian.koenig@xxxxxxx>

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h       | 1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c   | 6 ++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c   | 2 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 3 ++-
>   4 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 616b6c911767..3d8a48f46b01 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1144,6 +1144,7 @@ struct amdgpu_device {
>   	bool                            debug_vm;
>   	bool                            debug_largebar;
>   	bool                            debug_disable_soft_recovery;
> +	bool                            debug_use_vram_fw_buf;
>   };
>   
>   static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 880137774b4e..0776b0c5e4e4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -128,6 +128,7 @@ enum AMDGPU_DEBUG_MASK {
>   	AMDGPU_DEBUG_VM = BIT(0),
>   	AMDGPU_DEBUG_LARGEBAR = BIT(1),
>   	AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2),
> +	AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3),
>   };
>   
>   unsigned int amdgpu_vram_limit = UINT_MAX;
> @@ -2117,6 +2118,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
>   		pr_info("debug: soft reset for GPU recovery disabled\n");
>   		adev->debug_disable_soft_recovery = true;
>   	}
> +
> +	if (amdgpu_debug_mask & AMDGPU_DEBUG_USE_VRAM_FW_BUF) {
> +		pr_info("debug: place fw in vram for frontdoor loading\n");
> +		adev->debug_use_vram_fw_buf = true;
> +	}
>   }
>   
>   static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
> index 51bfe3757c89..215994409ac1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
> @@ -467,7 +467,7 @@ static int psp_sw_init(void *handle)
>   	}
>   
>   	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
> -				      amdgpu_sriov_vf(adev) ?
> +				      (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
>   				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
>   				      &psp->fw_pri_bo,
>   				      &psp->fw_pri_mc_addr,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
> index 0efb2568cb65..3e12763e477a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
> @@ -1062,7 +1062,8 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
>   {
>   	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT) {
>   		amdgpu_bo_create_kernel(adev, adev->firmware.fw_size, PAGE_SIZE,
> -			amdgpu_sriov_vf(adev) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
> +			(amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
> +			AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
>   			&adev->firmware.fw_buf,
>   			&adev->firmware.fw_buf_mc,
>   			&adev->firmware.fw_buf_ptr);