On 5/7/24 17:23, Christoph Hellwig wrote:
On Tue, May 07, 2024 at 01:18:57PM -0300, Jason Gunthorpe wrote:
On Tue, May 07, 2024 at 05:05:12PM +0100, Pavel Begunkov wrote:
even in tree if you give them enough rope, and they should not have
that rope when the only sensible options are page/folio based kernel
memory (incuding large/huge folios) and dmabuf.
I believe there is at least one deep confusion here, considering you
previously mentioned Keith's pre-mapping patches. The "hooks" are not
that about in what format you pass memory, it's arguably the least
interesting part for page pool, more or less it'd circulate whatever
is given. It's more of how to have a better control over buffer lifetime
and implement a buffer pool passing data to users and empty buffers
back.
Isn't that more or less exactly what dmabuf is? Why do you need
another almost dma-buf thing for another project?
That's the exact point I've been making since the last round of
the series. We don't need to reinvent dmabuf poorly in every
subsystem, but instead fix the odd parts in it and make it suitable
for everyone.
Someone would need to elaborate how dma-buf is like that addition
to page pool infra. The granularity here is usually 4K and less
(hw dictated), what user receives cannot be guaranteed to be
contiguous in memory. Having thousands of dma-buf instances is
not an option, so a completion would need to include a range
where data sits. Then who controls lifetime of buffers? If it's
dma-buf, then at least it needs to track what sub-buffers are
handed to user and what are currently in the kernel. How it would be
accounted? ioctl_return_subrange(dmabuf, [range]), sounds like
a bad idea for performance. To cover user memory it'd also need
to be read from userspace, ioctl here wouldn't be an option, but
let's say it's somehow done in the kernel.
That's not all the list, but in short, even though I haven't been
following dma-buf developments too closely, I have hard time seeing
how it can be a replacement here.
--
Pavel Begunkov
