On Thu, Jul 2, 2026 at 4:10 AM David Laight
<[email protected]> wrote:
>
> On Thu, 2 Jul 2026 00:56:40 -0400
> David Hu <[email protected]> wrote:
>
> > On Tue, Jun 30, 2026 at 8:42 AM Jason Gunthorpe <[email protected]> wrote:
> > >
> > > On Tue, Jun 23, 2026 at 11:53:50PM +0100, David Laight wrote:
> > >
> > > > > If we restrict incoming dmabuf transfers to fit within VFS-centric
> > > > > limits (2GB), we impose unnecessary overhead on the RDMA stack, 
> > > > > forcing
> > > > > it to manage a significantly higher number of memory registrations. By
> > > > > cleanly splitting these massive contiguous device buffers into
> > > > > page-aligned SGL entries, we directly improve the efficiency of P2P
> > > > > transfers and memory registration.
> > > >
> > > > But a divide by '4G - PAGE_SIZE' is also non-trivial and (I think 
> > > > affects
> > > > a lot of io) when the quotient is always 1.
> > > > Splitting into 2G chunks is a lot cheaper.
> > >
> > > Doesn't matter this isn't fast path stuff. It is better to use fewer
> > > SGL entries, IHMO.
> > >
> > > > > Since this change doesn't seem to have a negative impact on standard 
> > > > > file
> > > > > I/O or break existing VFS constraints, I'm curious why we shouldn't
> > > > > support splitting these >4GB P2P transfers? Am I missing something?
> > > >
> > > > I was only wondering whether it was needed...
> > > > It does bring up the question of why the >4GB transfers even need 
> > > > splitting.
> > > > But that is another question.
> > >
> > > SGL can only store an unsigned int size, so any large physical range
> > > has to be split down.
> > >
> > > rdma now a days has code to process the sgl and restore back the > 4G
> > > sizes since mode RDMA HW can accept that.
> > >
> > > commit 486055f5e09df959ad4e3aa4ee75b5c91ddeec2e
> > > Author: Michael Margolin <[email protected]>
> > > Date:   Mon Feb 17 14:16:23 2025 +0000
> > >
> > >     RDMA/core: Fix best page size finding when it can cross SG entries
> > >
> > > So whatever this produces needs to be compatible with that to undo it.
> >
> > Thank you everyone. It looks like most open issues are sorted out.
> > I'll wait for maintainers to weigh in before sending out v3 (which
> > will remove the type cast for min() per David L.'s feedback, and
> > revert to ALIGN_DOWN(UINT_MAX, PAGE_SIZE) per Jason's feedback).
>
> Does this code get used a lot for 'normal' transfers?
> I'm away from my normal systems and can't check.
> But if pretty much all of the fragments are small (< 4G) then
> it is probably worth adding a check for 'size < limit' before
> anything else and optimising that case.
>

Hi David,

Thank you for raising this. This file (`dma-buf-mapping.c`) was
recently added [1] to exclusively export MMIO device memory.
Therefore, it is bypassed completely for `normal` transfers (IIUC,
e.g., video buffers for V4L2 or DRM).

Regards,
David

[1] 
https://lore.kernel.org/all/[email protected]/

Reply via email to