Hi, Christoph I think we cannot modify dma_get_cache_alignment(), because existing callers may want to unconditionally return ARCH_DMA_MINALIGN. Huacai ------------------ Original ------------------ From: "Christoph Hellwig"<hch@xxxxxxxxxxxxx>; Date: Mon, Sep 11, 2017 03:39 PM To: "Huacai Chen"<chenhc@xxxxxxxxxx>; Cc: "James E . J . Bottomley"<jejb@xxxxxxxxxxxxxxxxxx>; "Martin K . Petersen"<martin.petersen@xxxxxxxxxx>; "Fuxin Zhang"<zhangfx@xxxxxxxxxx>; "linux-scsi"<linux-scsi@xxxxxxxxxxxxxxx>; "linux-kernel"<linux-kernel@xxxxxxxxxxxxxxx>; "stable"<stable@xxxxxxxxxxxxxxx>; Subject: Re: [PATCH 2/2] scsi: Align queue to ARCH_DMA_MINALIGN innon-coherent DMA mode > + if (plat_device_is_coherent(dev)) We can't just call platform device code. We'll need a proper DMA API call for this. > + blk_queue_dma_alignment(q, 0x04 - 1); > + else > + blk_queue_dma_alignment(q, dma_get_cache_alignment() - 1); Which we already have with dma_get_cache_alignment, except that it doesn't take a struct device pointer and doesn't call into dma_map ops. So please add a struct device argument to dma_get_cache_alignment, and let it call into dma_map_ops where needed. With that you can replace the above with: blk_queue_dma_alignment(q, max(0x04U, dma_get_cache_alignment(dev)) - 1);