To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
References: <cce00131-1f28-27b3-40ab-04f8783f1e5a@deltatee.com>
 <20170418190138.GH7181@obsidianresearch.com>
 <df1351d8-b86c-2e21-1948-4688ece5dc2b@deltatee.com>
 <CAPcyv4gScx6A7vG9VEHpNF41GOy1Nxst7QQ3QC3uZ54bWoxbMg@mail.gmail.com>
 <20170418210339.GA24257@obsidianresearch.com>
 <1492564806.25766.124.camel@kernel.crashing.org>
 <20170419155557.GA8497@obsidianresearch.com>
 <4899b011-bdfb-18d8-ef00-33a1516216a6@deltatee.com>
 <20170419171451.GA10020@obsidianresearch.com>
 <b0234176-e86b-6e7c-686d-b4fef719aad7@deltatee.com>
 <20170419183247.GA13716@obsidianresearch.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Dan Williams <dan.j.williams@intel.com>,
        Bjorn Helgaas <helgaas@kernel.org>, Christoph Hellwig <hch@lst.de>,
        Sagi Grimberg <sagi@grimberg.me>,
        "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>,
        "Martin K. Petersen" <martin.petersen@oracle.com>,
        Jens Axboe <axboe@kernel.dk>, Steve Wise <swise@opengridcomputing.com>,
        Stephen Bates <sbates@raithlin.com>, Max Gurtovoy <maxg@mellanox.com>,
        Keith Busch <keith.busch@intel.com>, linux-pci@vger.kernel.org,
        linux-scsi <linux-scsi@vger.kernel.org>,
        linux-nvme@lists.infradead.org, linux-rdma@vger.kernel.org,
        linux-nvdimm <linux-nvdimm@ml01.01.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Jerome Glisse <jglisse@redhat.com>
From: Logan Gunthorpe <logang@deltatee.com>
Message-ID: <21e8099a-d19d-7df0-682d-627d8b81dfde@deltatee.com>
Date: Wed, 19 Apr 2017 13:02:49 -0600
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
 Icedove/45.6.0
MIME-Version: 1.0
In-Reply-To: <20170419183247.GA13716@obsidianresearch.com>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Subject: Re: [RFC 0/8] Copy Offload with Peer-to-Peer PCI Memory
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1607
Lines: 38


On 19/04/17 12:32 PM, Jason Gunthorpe wrote:
> On Wed, Apr 19, 2017 at 12:01:39PM -0600, Logan Gunthorpe wrote:
> Not entirely, it would have to call through the whole process
> including the arch_p2p_cross_segment()..

Hmm, yes. Though it's still not clear what, if anything,
arch_p2p_cross_segment would be doing. In my experience, if you are
going between host bridges, the CPU address (or PCI address -- I'm not
sure which seeing they are the same on my system) would still work fine
-- it just _may_ be a bad idea because of performance.

Similarly if you are crossing via a QPI bus or similar, I'd expect the
CPU address to work fine. But here the performance is even less likely
to be any good.


>          // Try the arch specific helper
> 	 const struct dma_map_ops *comp_ops = get_dma_ops(completer);
> 	 const struct dma_map_ops *init_ops = get_dma_ops(initiator);

So, in this case, what device does the completer point to? The PCI
device or a more specific GPU device? If it's the former, who's
responsible for setting the new dma_ops? Typically the dma_ops are arch
specific but now you'd be adding ones that are tied to hmm or the gpu.

>> I'm not sure I like the name pci_p2p_same_segment. It reads as though
>> it's only checking if the devices are not the same segment.
> 
> Well, that is exactly what it is doing. If it succeeds then the caller
> knows the DMA will not flow outside the segment and no iommu setup/etc
> is required.

It appears to me like it's calculating the DMA address, and the check is
just a side requirement. It reads as though it's only doing the check.

Logan