[PATCH 2/8] powerpc/dma: properly wire up the unmap_page and unmap_sg methods

[Christophe Leroy]

Le 16/12/2018 à 18:19, Christoph Hellwig a écrit :
> The unmap methods need to transfer memory ownership back from the device
> to the cpu by identical means as dma_sync_*_to_cpu.  I'm not sure powerpc
> needs to do any work in this transfer direction, but given that it does
> invalidate the caches in dma_sync_*_to_cpu already we should make sure
> we also do so on unmapping.

Why do we have to do that on unmapping ? If we are unmapping it means we 
are retiring the area, so why would we need to use CPU for syncing an 
area than won't be used anymore ?

Christophe


> 
> Signed-off-by: Christoph Hellwig <hch at lst.de>
> ---
>   arch/powerpc/kernel/dma.c | 9 ++++++++-
>   1 file changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
> index dbfc7056d7df..d442d23e182b 100644
> --- a/arch/powerpc/kernel/dma.c
> +++ b/arch/powerpc/kernel/dma.c
> @@ -210,10 +210,15 @@ static int dma_nommu_map_sg(struct device *dev, struct scatterlist *sgl,
>   	return nents;
>   }
>   
> -static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sg,
> +static void dma_nommu_unmap_sg(struct device *dev, struct scatterlist *sgl,
>   				int nents, enum dma_data_direction direction,
>   				unsigned long attrs)
>   {
> +	struct scatterlist *sg;
> +	int i;
> +
> +	for_each_sg(sgl, sg, nents, i)
> +		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
>   }
>   
>   static u64 dma_nommu_get_required_mask(struct device *dev)
> @@ -247,6 +252,8 @@ static inline void dma_nommu_unmap_page(struct device *dev,
>   					 enum dma_data_direction direction,
>   					 unsigned long attrs)
>   {
> +	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> +		__dma_sync(bus_to_virt(dma_address), size, dir);
>   }
>   
>   #ifdef CONFIG_NOT_COHERENT_CACHE
>