[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210316081156.GA16595@lst.de>
Date: Tue, 16 Mar 2021 09:11:56 +0100
From: Christoph Hellwig <hch@....de>
To: Logan Gunthorpe <logang@...tatee.com>
Cc: linux-kernel@...r.kernel.org, linux-nvme@...ts.infradead.org,
linux-block@...r.kernel.org, linux-pci@...r.kernel.org,
linux-mm@...ck.org, iommu@...ts.linux-foundation.org,
Stephen Bates <sbates@...thlin.com>,
Christoph Hellwig <hch@....de>,
Dan Williams <dan.j.williams@...el.com>,
Jason Gunthorpe <jgg@...pe.ca>,
Christian König <christian.koenig@....com>,
Ira Weiny <iweiny@...el.com>,
John Hubbard <jhubbard@...dia.com>,
Don Dutile <ddutile@...hat.com>,
Matthew Wilcox <willy@...radead.org>,
Daniel Vetter <daniel.vetter@...ll.ch>,
Jakowski Andrzej <andrzej.jakowski@...el.com>,
Minturn Dave B <dave.b.minturn@...el.com>,
Jason Ekstrand <jason@...kstrand.net>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Xiong Jianxin <jianxin.xiong@...el.com>
Subject: Re: [RFC PATCH v2 06/11] dma-direct: Support PCI P2PDMA pages in
dma-direct map_sg
On Thu, Mar 11, 2021 at 04:31:36PM -0700, Logan Gunthorpe wrote:
> for_each_sg(sgl, sg, nents, i) {
> + if (is_pci_p2pdma_page(sg_page(sg))) {
> + if (sg_page(sg)->pgmap != pgmap) {
> + pgmap = sg_page(sg)->pgmap;
> + map = pci_p2pdma_dma_map_type(dev, pgmap);
> + bus_off = pci_p2pdma_bus_offset(sg_page(sg));
> + }
> +
> + if (map < 0) {
> + sg->dma_address = DMA_MAPPING_ERROR;
> + ret = -EREMOTEIO;
> + goto out_unmap;
> + }
> +
> + if (map) {
> + sg->dma_address = sg_phys(sg) + sg->offset -
> + bus_off;
> + sg_dma_len(sg) = sg->length;
> + sg_mark_pci_p2pdma(sg);
> + continue;
> + }
> + }
This code needs to go into a separate noinline helper to reduce the impact
on the fast path. Also as Robin noted the offset is already
accounted for in sg_phys. We also don't ever set the dma_address in
the scatterlist to DMA_MAPPING_ERROR, that is just a return value
for the single entry mapping routines.
Powered by blists - more mailing lists