mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
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

  reply	other threads:[~2026-10-12  7:10 UTC|newest]

Thread overview: 12+ 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 23:32 ` [RFC PATCH v1 2/8] sunrpc: fail only the RPC a transport refuses Pranjal Shrivastava
2026-10-06 23:32 ` [RFC PATCH v1 3/8] xprtrdma: move P2PDMA payloads only via chunks Pranjal Shrivastava
2026-10-06 23:32 ` [RFC PATCH v1 4/8] xprtrdma: return -EREMOTEIO on P2PDMA map failure Pranjal Shrivastava
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
2026-10-12  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 23:32 ` [RFC PATCH v1 7/8] nfs: allow LOCALIO for P2PDMA pages only as aligned direct I/O Pranjal Shrivastava
2026-10-06 23:32 ` [RFC PATCH v1 8/8] nfs: allow P2PDMA pages for O_DIRECT on RDMA mounts Pranjal Shrivastava
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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®