[PATCH 01/15] drm/amdgpu: Add interface to reserve bad page

[Christian König]

Am 18.04.24 um 04:58 schrieb YiPeng Chai:
> Add interface to reserve bad page.
>
> Signed-off-by: YiPeng Chai <YiPeng.Chai at amd.com>

Yeah, that approach looks valid to me. Just keep in mind that 
amdgpu_vram_mgr_query_page_status() is not the fastest function cause it 
does a linear search.

Apart from that Reviewed-by: Christian König <christian.koenig at amd.com> 
for this patch, but can't really judge the rest of the patch set.

Regards,
Christian.

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 19 +++++++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h |  4 ++++
>   2 files changed, 23 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> index 2c97cb80d79a..05782d68f073 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
> @@ -2782,6 +2782,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
>   		}
>   	}
>   
> +	mutex_init(&con->page_rsv_lock);
>   	mutex_init(&con->page_retirement_lock);
>   	init_waitqueue_head(&con->page_retirement_wq);
>   	atomic_set(&con->page_retirement_req_cnt, 0);
> @@ -2835,6 +2836,8 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev)
>   
>   	atomic_set(&con->page_retirement_req_cnt, 0);
>   
> +	mutex_destroy(&con->page_rsv_lock);
> +
>   	cancel_work_sync(&con->recovery_work);
>   
>   	mutex_lock(&con->recovery_lock);
> @@ -4278,3 +4281,19 @@ void amdgpu_ras_query_boot_status(struct amdgpu_device *adev, u32 num_instances)
>   			amdgpu_ras_boot_time_error_reporting(adev, i, boot_error);
>   	}
>   }
> +
> +int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn)
> +{
> +	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
> +	struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
> +	uint64_t start = pfn << AMDGPU_GPU_PAGE_SHIFT;
> +	int ret = 0;
> +
> +	mutex_lock(&con->page_rsv_lock);
> +	ret = amdgpu_vram_mgr_query_page_status(mgr, start);
> +	if (ret == -ENOENT)
> +		ret = amdgpu_vram_mgr_reserve_range(mgr, start, AMDGPU_GPU_PAGE_SIZE);
> +	mutex_unlock(&con->page_rsv_lock);
> +
> +	return ret;
> +}
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> index 8d26989c75c8..ab5bf573378e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
> @@ -500,6 +500,7 @@ struct amdgpu_ras {
>   	wait_queue_head_t page_retirement_wq;
>   	struct mutex page_retirement_lock;
>   	atomic_t page_retirement_req_cnt;
> +	struct mutex page_rsv_lock;
>   	/* Fatal error detected flag */
>   	atomic_t fed;
>   
> @@ -909,4 +910,7 @@ bool amdgpu_ras_get_fed_status(struct amdgpu_device *adev);
>   
>   bool amdgpu_ras_event_id_is_valid(struct amdgpu_device *adev, u64 id);
>   u64 amdgpu_ras_acquire_event_id(struct amdgpu_device *adev, enum ras_event_type type);
> +
> +int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn);
> +
>   #endif