Re: [PATCH v7 05/11] PCI/P2PDMA: Document DMABUF model

[Leon Romanovsky <leon@kernel.org>]

On Fri, Nov 07, 2025 at 10:58:27AM -0800, Randy Dunlap wrote:
> 	
> 
> On 11/7/25 8:01 AM, Leon Romanovsky wrote:
> > On Thu, Nov 06, 2025 at 10:15:07PM -0800, Randy Dunlap wrote:
> >>
> >>
> >> On 11/6/25 6:16 AM, Leon Romanovsky wrote:
> >>> From: Jason Gunthorpe <jgg@nvidia.com>
> >>>
> >>> Reflect latest changes in p2p implementation to support DMABUF lifecycle.
> >>>
> >>> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> >>> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> >>> ---
> >>>  Documentation/driver-api/pci/p2pdma.rst | 95 +++++++++++++++++++++++++--------
> >>>  1 file changed, 72 insertions(+), 23 deletions(-)

<...>

> >>> -The second issue is that to make use of existing interfaces in Linux,
> >>> -memory that is used for P2P transactions needs to be backed by struct
> >>> -pages. However, PCI BARs are not typically cache coherent so there are
> >>> -a few corner case gotchas with these pages so developers need to
> >>> -be careful about what they do with them.
> >>> +For PCIe the routing of TLPs is well defined up until they reach a host bridge
> >>
> >> Define what TLP means?
> > 
> > In PCIe "world", TLP is very well-known and well-defined acronym, which
> > means Transaction Layer Packet.
> 
> It's your choice (or Bjorn's). I'm just reviewing...

Thanks a lot.