Re: [PATCH] PCI/P2PDMA: Root complex whitelist should not apply when an IOMMU is present

From: Christoph Hellwig <hch@lst.de>
To: Logan Gunthorpe <logang@deltatee.com>
Cc: Christoph Hellwig <hch@lst.de>,
	"Koenig, Christian" <Christian.Koenig@amd.com>,
	"linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
	Bjorn Helgaas <bhelgaas@google.com>
Subject: Re: [PATCH] PCI/P2PDMA: Root complex whitelist should not apply when an IOMMU is present
Date: Thu, 23 May 2019 17:59:22 +0200	[thread overview]
Message-ID: <20190523155922.GA21552@lst.de> (raw)
In-Reply-To: <252313a9-9af4-14bd-1bfa-1c2327baf2b2@deltatee.com>

On Thu, May 23, 2019 at 09:53:53AM -0600, Logan Gunthorpe wrote:
> > The problem shows up if pci_bus_address() returns a different address
> > than pci_resource_start(), should be easy to check if that happens.
> > IIRC it is something mostly seen on embedded SOCs.
> > 
> 
> I think it's a bit more complicated then that: If you're calling
> dma_map_resource() to program the IOMMU then I'm pretty sure you'd want
> to use the pci_resource_start() address as the phys_addr_t. If you're
> bypassing the root complex (like the current p2pdma code enforces), then
> you'd simply use a pci_bus_address() directly as the dma_addr and would
> not program the IOMMU at all seeing it's not involved (which is what is
> currently done).

True.  What we need is:

 if (both device are behind the same root port (using a switch)) {
 	use the current direct map + offset code
 } else {
 	call ->map_resource()
 }