From: Leon Romanovsky <leon@kernel.org>
To: Pranjal Shrivastava <praan@google.com>,
Chuck Lever <cel@kernel.org>, Christoph Hellwig <hch@lst.de>,
Matthew Wilcox <willy@infradead.org>
Cc: linux-nfs@vger.kernel.org, Trond Myklebust <trondmy@kernel.org>,
Anna Schumaker <anna@kernel.org>,
Jeff Layton <jlayton@kernel.org>,
linux-kernel@vger.kernel.org,
Logan Gunthorpe <logang@deltatee.com>,
Jason Gunthorpe <jgg@ziepe.ca>,
linux-pci@vger.kernel.org, linux-rdma@vger.kernel.org,
Shivaji Kant <shivajikant@google.com>,
Tom Talpey <tom@talpey.com>,
Unnati Sachan <unnatisachan@google.com>
Subject: Re: [RFC PATCH v1 5/8] nfs: tag READ/WRITE RPCs carrying P2PDMA pages
Date: Mon, 12 Oct 2026 10:10:20 +0300 [thread overview]
Message-ID: <20261012071020.GH27033@unreal> (raw)
In-Reply-To: <20261006233248.705086-6-praan@google.com>
On Tue, Oct 06, 2026 at 11:32:45PM +0000, Pranjal Shrivastava wrote:
> A transport must know when an RPC's payload pages are P2PDMA memory,
> so it can move them by DMA or refuse the RPC.
>
> Check each page as nfs_generic_pgio() builds the page array, and
> record the result in nfs_pgio_args. The READ and WRITE encoders of
> every NFS version then set XDRBUF_P2PDMA on the buffer holding the
> payload.
>
> Additionally, avoid using READ_PLUS when the pages are P2PDMA memory.
>
> Signed-off-by: Pranjal Shrivastava <praan@google.com>
> ---
> fs/nfs/nfs2xdr.c | 4 ++++
> fs/nfs/nfs3xdr.c | 4 ++++
> fs/nfs/nfs4proc.c | 3 +++
> fs/nfs/nfs4xdr.c | 4 ++++
> fs/nfs/pagelist.c | 2 ++
> include/linux/nfs_xdr.h | 1 +
> 6 files changed, 18 insertions(+)
<...>
> +++ b/fs/nfs/pagelist.c
> @@ -970,6 +970,8 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
> if (pageused > pagecount)
> goto full;
> *pages++ = last_page = page;
> + if (is_pci_p2pdma_page(page))
> + hdr->args.p2pdma = true;
Should we allow wider use of is_pci_p2pdma_page()? Does NFS require
`struct page`?
Thanks
next prev parent reply other threads:[~2026-10-12 7:10 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-06 23:32 [RFC PATCH v1 0/8] nfs: PCI P2PDMA for O_DIRECT over RDMA Pranjal Shrivastava
2026-10-06 23:32 ` [RFC PATCH v1 1/8] sunrpc: introduce XDRBUF_P2PDMA flag Pranjal Shrivastava
2026-10-06 23:41 ` sashiko-bot
2026-10-06 23:32 ` [RFC PATCH v1 2/8] sunrpc: fail only the RPC a transport refuses Pranjal Shrivastava
2026-10-06 23:41 ` sashiko-bot
2026-10-06 23:32 ` [RFC PATCH v1 3/8] xprtrdma: move P2PDMA payloads only via chunks Pranjal Shrivastava
2026-10-06 23:47 ` sashiko-bot
2026-10-06 23:32 ` [RFC PATCH v1 4/8] xprtrdma: return -EREMOTEIO on P2PDMA map failure Pranjal Shrivastava
2026-10-06 23:42 ` sashiko-bot
2026-10-12 7:01 ` Leon Romanovsky
2026-10-06 23:32 ` [RFC PATCH v1 5/8] nfs: tag READ/WRITE RPCs carrying P2PDMA pages Pranjal Shrivastava
2026-10-06 23:45 ` sashiko-bot
2026-10-12 7:10 ` Leon Romanovsky [this message]
2026-10-06 23:32 ` [RFC PATCH v1 6/8] nfs: refuse P2PDMA pages with krb5i and krb5p Pranjal Shrivastava
2026-10-06 23:46 ` sashiko-bot
2026-10-06 23:32 ` [RFC PATCH v1 7/8] nfs: allow LOCALIO for P2PDMA pages only as aligned direct I/O Pranjal Shrivastava
2026-10-06 23:51 ` sashiko-bot
2026-10-06 23:32 ` [RFC PATCH v1 8/8] nfs: allow P2PDMA pages for O_DIRECT on RDMA mounts Pranjal Shrivastava
2026-10-06 23:42 ` sashiko-bot
2026-10-10 13:00 ` kernel test robot
2026-10-07 21:20 ` [RFC PATCH v1 0/8] nfs: PCI P2PDMA for O_DIRECT over RDMA Chuck Lever
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=20261012071020.GH27033@unreal \
--to=leon@kernel.org \
--cc=anna@kernel.org \
--cc=cel@kernel.org \
--cc=hch@lst.de \
--cc=jgg@ziepe.ca \
--cc=jlayton@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=praan@google.com \
--cc=shivajikant@google.com \
--cc=tom@talpey.com \
--cc=trondmy@kernel.org \
--cc=unnatisachan@google.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.