[PATCH 2/2] drm/amdgpu/dma_buf: fix page_link check

[Matthew Auld]

On 07/04/2025 15:32, Christian König wrote:
> Am 07.04.25 um 16:18 schrieb Matthew Auld:
>> The page_link lower bits of the first sg could contain something like
>> SG_END, if we are mapping a single VRAM page or contiguous blob which
>> fits into one sg entry. Rather pull out the struct page, and use that in
>> our check to know if we mapped struct pages vs VRAM.
>>
>> Fixes: f44ffd677fb3 ("drm/amdgpu: add support for exporting VRAM using DMA-buf v3")
>> Signed-off-by: Matthew Auld <matthew.auld at intel.com>
>> Cc: Christian König <christian.koenig at amd.com>
>> Cc: amd-gfx at lists.freedesktop.org
>> Cc: <stable at vger.kernel.org> # v5.8+
> 
> Good point, haven't thought about that at all since we only abuse the sg table as DMA addr container.
> 
> Reviewed-by: Christian König <christian.koenig at amd.com>
> 
> Were is patch #1 from this series?

That one is xe specific:
https://lore.kernel.org/intel-xe/20250407141823.44504-3-matthew.auld@intel.com/T/#m4ef16e478cfc8853d4518448dd345a66d5a7f6d9

I copied your approach with using page_link here, but with added sg_page().

> 
> Thanks,
> Christian.
> 
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 2 +-
>>   1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
>> index 9f627caedc3f..c9842a0e2a1c 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
>> @@ -184,7 +184,7 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
>>   				 struct sg_table *sgt,
>>   				 enum dma_data_direction dir)
>>   {
>> -	if (sgt->sgl->page_link) {
>> +	if (sg_page(sgt->sgl)) {
>>   		dma_unmap_sgtable(attach->dev, sgt, dir, 0);
>>   		sg_free_table(sgt);
>>   		kfree(sgt);
>