From: Pranjal Shrivastava <praan@google.com>
To: linux-nfs@vger.kernel.org, Trond Myklebust <trondmy@kernel.org>,
Anna Schumaker <anna@kernel.org>
Cc: Chuck Lever <cel@kernel.org>, Jeff Layton <jlayton@kernel.org>,
linux-kernel@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
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>, Leon Romanovsky <leon@kernel.org>,
Unnati Sachan <unnatisachan@google.com>,
Pranjal Shrivastava <praan@google.com>
Subject: [RFC PATCH v1 5/8] nfs: tag READ/WRITE RPCs carrying P2PDMA pages
Date: Tue, 6 Oct 2026 23:32:45 +0000 [thread overview]
Message-ID: <20261006233248.705086-6-praan@google.com> (raw)
In-Reply-To: <20261006233248.705086-1-praan@google.com>
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(+)
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 9eff09158518..5a8f2eccd068 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -628,6 +628,8 @@ static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->count,
NFS_readres_sz - NFS_pagepad_sz);
req->rq_rcv_buf.flags |= XDRBUF_READ;
+ if (args->p2pdma)
+ req->rq_rcv_buf.flags |= XDRBUF_P2PDMA;
}
/*
@@ -668,6 +670,8 @@ static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req,
encode_writeargs(xdr, args);
xdr->buf->flags |= XDRBUF_WRITE;
+ if (args->p2pdma)
+ xdr->buf->flags |= XDRBUF_P2PDMA;
}
/*
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index e745e78faab0..e39c58883a2a 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -946,6 +946,8 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
rpc_prepare_reply_pages(req, args->pages, args->pgbase,
args->count, replen);
req->rq_rcv_buf.flags |= XDRBUF_READ;
+ if (args->p2pdma)
+ req->rq_rcv_buf.flags |= XDRBUF_P2PDMA;
}
/*
@@ -988,6 +990,8 @@ static void nfs3_xdr_enc_write3args(struct rpc_rqst *req,
encode_write3args(xdr, args);
xdr->buf->flags |= XDRBUF_WRITE;
+ if (args->p2pdma)
+ xdr->buf->flags |= XDRBUF_P2PDMA;
}
/*
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index beb659744760..443079f5adc9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5721,6 +5721,9 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr,
struct rpc_message *msg)
{
+ /* P2PDMA payloads move only by DMA */
+ if (hdr->args.p2pdma)
+ return false;
/* Note: We don't use READ_PLUS with pNFS yet */
if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) {
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 8b3d96b4a0f0..04765b56de28 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2621,6 +2621,8 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
rpc_prepare_reply_pages(req, args->pages, args->pgbase,
args->count, hdr.replen - pagepad_maxsz);
req->rq_rcv_buf.flags |= XDRBUF_READ;
+ if (args->p2pdma)
+ req->rq_rcv_buf.flags |= XDRBUF_P2PDMA;
encode_nops(&hdr);
}
@@ -2686,6 +2688,8 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
encode_putfh(xdr, args->fh, &hdr);
encode_write(xdr, args, &hdr);
req->rq_snd_buf.flags |= XDRBUF_WRITE;
+ if (args->p2pdma)
+ req->rq_snd_buf.flags |= XDRBUF_P2PDMA;
if (args->bitmask)
encode_getfattr(xdr, args->bitmask, &hdr);
encode_nops(&hdr);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 71f0ce2bc4ea..3ec4e1e5fe1f 100644
--- a/fs/nfs/pagelist.c
+++ 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;
}
}
}
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index c0e29b4dfa62..85cdee107559 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -685,6 +685,7 @@ struct nfs_pgio_args {
__u32 count;
unsigned int pgbase;
struct page ** pages;
+ bool p2pdma; /* pages include P2PDMA memory */
union {
unsigned int replen; /* used by read */
struct {
--
2.56.0.rc1.315.gc6ed9934b7-goog
next prev parent reply other threads:[~2026-10-06 23:33 UTC|newest]
Thread overview: 10+ 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
2026-10-06 23:32 ` Pranjal Shrivastava [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=20261006233248.705086-6-praan@google.com \
--to=praan@google.com \
--cc=anna@kernel.org \
--cc=cel@kernel.org \
--cc=hch@lst.de \
--cc=jgg@ziepe.ca \
--cc=jlayton@kernel.org \
--cc=leon@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=shivajikant@google.com \
--cc=tom@talpey.com \
--cc=trondmy@kernel.org \
--cc=unnatisachan@google.com \
/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®