On 2019-07-25 12:10 a.m., Christoph Hellwig wrote:
> On Wed, Jul 24, 2019 at 09:58:59AM -0600, Logan Gunthorpe wrote:
>>
>>
>> On 2019-07-24 12:32 a.m., Christoph Hellwig wrote:
>>>> struct dev_pagemap *pgmap = sg_page(sg)->pgmap;
>>>> + struct pci_dev *client;
>>>> + int dist;
>>>> +
>>>> + client = find_parent_pci_dev(dev);
>>>> + if (WARN_ON_ONCE(!client))
>>>> + return 0;
>>>>
>>>> + dist = upstream_bridge_distance(pgmap->pci_p2pdma_provider,
>>>> + client, NULL);
>>>
>>> Doing this on every mapping call sounds expensive..
>>
>> The result of this function is cached in an xarray (per patch 4) so, on
>> the hot path, it should just be a single xa_load() which should be a
>> relatively fast lookup which is similarly used for other hot path
>> operations.
>
> We don't cache find_parent_pci_dev, though. So we should probably
> export find_parent_pci_dev with a proper namespaces name and cache
> that in the caler.
Oh, yes, I'll take a look at this. Of the two callers: NVMe should be
easy we could just pass the PCI device instead of the struct device.
RDMA is significantly more unclear: would you add a pci_dev to struct
ib_device? Or maybe we should be able to simply rely on the fact that
the DMA device *must* be a PCI device and just use to_pci_dev() directly?
>>>
>>>> + if (WARN_ON_ONCE(dist & P2PDMA_NOT_SUPPORTED))
>>>> + return 0;
>>>> +
>>>> + if (dist & P2PDMA_THRU_HOST_BRIDGE)
>>>> + return dma_map_sg_attrs(dev, sg, nents, dir, attrs);
>>>> + else
>>>> + return __pci_p2pdma_map_sg(pgmap, dev, sg, nents);
>>>
>>> Can't we organize the values so that we can switch on the return
>>> value instead of doing flag checks?
>>
>> Sorry, I don't follow what you are saying here. If you mean for
>> upstream_bridge_distance() to just return how to map and not the
>> distance that would interfere with other uses of that function.
>
> The point is that in the map path we don't even care about the
> distance. I think we should just have a function that returns the
> P2PDMA_ values from the xarray (maybe also store it there as two
> values, but that isn't quite as important), and get rid of even
> the concept of distance in the map path. e.g.:
>
> switch (pci_p2pdma_supported(pgmap->pci_p2pdma_provider, client))) {
> case P2PDMA_HOST_BRIDGE:
> return dma_map_sg_attrs(dev, sg, nents, dir, attrs);
> case P2PDMA_SWITCH:
> return __pci_p2pdma_map_sg(pgmap, dev, sg, nents);
> default:
> WARN_ON_ONCE(1);
> return 0;
> }
Ok, will change for v2.
Thanks,
Logan
