From: David Howells <dhowells@redhat.com>
To: Tom Talpey <tom@talpey.com>
Cc: dhowells@redhat.com, Steve French <sfrench@samba.org>,
Stefan Metzmacher <metze@samba.org>,
Paulo Alcantara <pc@manguebit.com>,
Matthew Wilcox <willy@infradead.org>,
linux-cifs@vger.kernel.org
Subject: Re: cifs RDMA restrictions
Date: Tue, 01 Apr 2025 20:34:47 +0100 [thread overview]
Message-ID: <659109.1743536087@warthog.procyon.org.uk> (raw)
In-Reply-To: <78c910b0-3391-484e-aa44-42e2f9ff4637@talpey.com>
Tom Talpey <tom@talpey.com> wrote:
> A single sge is just a hunk of memory that is registered with the RDMA
> provider. The routine you're quoting is generating the dma_addr that
> the provider (adapter) will use to access the data so it's passing what
> the ib_dma stuff wants.
The issue is that currently, we pass individual page fragments to the RDMA
layer, and none of them will cross a page boundary and they will be at most
PAGE_SIZE in size.
However, in order to better support large folios and large bvec descriptors, I
could in theory set a segment much larger than PAGE_SIZE.
But, will the device handle that? And can the DMA API map a single buffer
that big with the IOMMU? And does it need aligning to a larger pow-of-2
granule?
David
next prev parent reply other threads:[~2025-04-01 19:34 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-01 16:55 cifs RDMA restrictions David Howells
2025-04-01 18:02 ` Tom Talpey
2025-04-01 19:34 ` David Howells [this message]
2025-04-02 17:02 ` Tom Talpey
2025-04-02 17:09 ` David Howells
[not found] ` <CAH2r5ms2J06tJr4VEVDgmcj_1uqOnhYzbC1ybrMWDm=f8wVDoA@mail.gmail.com>
2025-04-02 18:04 ` Tom Talpey
2025-04-02 19:26 ` David Howells
2025-04-02 19:36 ` Tom Talpey
2025-04-02 19:54 ` [RFC PATCH] cifs: Collapse smbd_recv_*() into smbd_recv() and just use copy_to_iter() David Howells
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=659109.1743536087@warthog.procyon.org.uk \
--to=dhowells@redhat.com \
--cc=linux-cifs@vger.kernel.org \
--cc=metze@samba.org \
--cc=pc@manguebit.com \
--cc=sfrench@samba.org \
--cc=tom@talpey.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.