Re: [PATCH 1/3] Revert "drm/amdgpu: add debugfs amdgpu_reset_level"

["Lazar, Lijo" <lijo.lazar@amd.com>]

On 10/13/2022 1:57 PM, Victor Zhao wrote:
> This reverts commit 3ae992d5e1194a16e3d977076eb5722fa6e410d8.
> 
> This commit breaks the reset logic for aldebaran, revert it for now.
> Will move the mask inside the reset handler.

Thanks for reverting. Please cc me also for refactored patches for SMU 
11.0.7.

Series is
	Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>

Thanks,
Lijo

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h         | 4 ----
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 2 --
>   drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c   | 8 --------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c    | 3 ---
>   4 files changed, 17 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 3ce91f660c3f..0e6ddf05c23c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -274,9 +274,6 @@ extern int amdgpu_vcnfw_log;
>   #define AMDGPU_RESET_VCE			(1 << 13)
>   #define AMDGPU_RESET_VCE1			(1 << 14)
>   
> -#define AMDGPU_RESET_LEVEL_SOFT_RECOVERY (1 << 0)
> -#define AMDGPU_RESET_LEVEL_MODE2 (1 << 1)
> -
>   /* max cursor sizes (in pixels) */
>   #define CIK_CURSOR_WIDTH 128
>   #define CIK_CURSOR_HEIGHT 128
> @@ -1065,7 +1062,6 @@ struct amdgpu_device {
>   
>   	struct work_struct		reset_work;
>   
> -	uint32_t						amdgpu_reset_level_mask;
>   	bool                            job_hang;
>   };
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> index 6066aebf491c..de61a85c4b02 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> @@ -1954,8 +1954,6 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
>   		return PTR_ERR(ent);
>   	}
>   
> -	debugfs_create_u32("amdgpu_reset_level", 0600, root, &adev->amdgpu_reset_level_mask);
> -
>   	/* Register debugfs entries for amdgpu_ttm */
>   	amdgpu_ttm_debugfs_init(adev);
>   	amdgpu_debugfs_pm_init(adev);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> index 9da5ead50c90..831fb222139c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
> @@ -37,8 +37,6 @@ int amdgpu_reset_init(struct amdgpu_device *adev)
>   {
>   	int ret = 0;
>   
> -	adev->amdgpu_reset_level_mask = 0x1;
> -
>   	switch (adev->ip_versions[MP1_HWIP][0]) {
>   	case IP_VERSION(13, 0, 2):
>   		ret = aldebaran_reset_init(adev);
> @@ -76,9 +74,6 @@ int amdgpu_reset_prepare_hwcontext(struct amdgpu_device *adev,
>   {
>   	struct amdgpu_reset_handler *reset_handler = NULL;
>   
> -	if (!(adev->amdgpu_reset_level_mask & AMDGPU_RESET_LEVEL_MODE2))
> -		return -ENOSYS;
> -
>   	if (test_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags))
>   		return -ENOSYS;
>   
> @@ -98,9 +93,6 @@ int amdgpu_reset_perform_reset(struct amdgpu_device *adev,
>   	int ret;
>   	struct amdgpu_reset_handler *reset_handler = NULL;
>   
> -	if (!(adev->amdgpu_reset_level_mask & AMDGPU_RESET_LEVEL_MODE2))
> -		return -ENOSYS;
> -
>   	if (test_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags))
>   		return -ENOSYS;
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> index 3e316b013fd9..d3558c34d406 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> @@ -405,9 +405,6 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
>   {
>   	ktime_t deadline = ktime_add_us(ktime_get(), 10000);
>   
> -	if (!(ring->adev->amdgpu_reset_level_mask & AMDGPU_RESET_LEVEL_SOFT_RECOVERY))
> -		return false;
> -
>   	if (amdgpu_sriov_vf(ring->adev) || !ring->funcs->soft_recovery || !fence)
>   		return false;
>