[PATCH] drm/amdgpu: Return -EINVAL when whole gpu reset happened

[Christian König]

Am 09.12.20 um 10:46 schrieb Liu ChengZhe:
> If CS init return -ECANCELED, UMD will free and create new context.
> Job in this new context could conitnue exexcuting. In the case of
> BACO or mode 1, we can't allow this happpen. Because VRAM has lost
> after whole gpu reset, the job can't guarantee to succeed.

NAK, this is intentional.

When ECANCELED is returned UMD should create new context after a GPU 
reset to get back into an usable state and continue to submit jobs.

Regards,
Christian.

>
> Signed-off-by: Liu ChengZhe <ChengZhe.Liu at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 9 +++++++--
>   1 file changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> index 85e48c29a57c..2a98f58134ed 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -120,6 +120,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
>   	uint64_t *chunk_array;
>   	unsigned size, num_ibs = 0;
>   	uint32_t uf_offset = 0;
> +	uint32_t vramlost_count = 0;
>   	int i;
>   	int ret;
>   
> @@ -140,7 +141,11 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
>   
>   	/* skip guilty context job */
>   	if (atomic_read(&p->ctx->guilty) == 1) {
> -		ret = -ECANCELED;
> +		vramlost_count = atomic_read(&p->adev->vram_lost_counter);
> +		if (p->ctx->vram_lost_counter != vramlost_count)
> +			ret = -EINVAL;
> +		else
> +			ret = -ECANCELED;
>   		goto free_chunk;
>   	}
>   
> @@ -246,7 +251,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
>   		goto free_all_kdata;
>   
>   	if (p->ctx->vram_lost_counter != p->job->vram_lost_counter) {
> -		ret = -ECANCELED;
> +		ret = -EINVAL;
>   		goto free_all_kdata;
>   	}
>