[PATCH v2 3/6] nfs4.2: open UNCACHEABLE_FILE_DATA files with O_DIRECT

Honor the per-file UNCACHEABLE_FILE_DATA attribute by transparently
opening such regular files with O_DIRECT, so reads and writes bypass the
page cache as the attribute requires, without the application having to
request O_DIRECT itself.

This follows the model the specification describes: the attribute is
"similar in intent to O_DIRECT" and clients "retain flexibility in how
they satisfy the requirements" (draft-ietf-nfsv4-uncacheable-files
Section 4.4, "Relationship to Direct I/O"), and its Implementation
Status (Section 6) describes a prototype Linux client that "treats the
attribute as an indication to use O_DIRECT-like behavior for file
access".

Introduce an NFS_CONTEXT_O_DIRECT open-context flag: nfs4_atomic_open()
sets it when the resolved inode has uncacheable_file_data set (and the
open is not O_APPEND), and the open paths nfs_atomic_open() and
nfs4_file_open() apply O_DIRECT to the file when the flag is set.

The I/O mode is thus selected at open time and is not changed for an
already-open file: a later change to the attribute takes effect on the
next open.  The specification permits this -- a client that has already
opened a file MAY continue with its existing caching behavior and apply
the updated attribute to subsequent operations (Section 5).

The delegation interaction in Section 4.3 was considered: it permits read
caching to remain when another NFSv4.2 mechanism, such as a delegation,
already ensures a consistent view of the file.  That relaxation is
optional ("may remain appropriate") and read-only -- it does not relax
write-behind suppression (Section 4.1) or the WRITE durability invariant
(Section 4.2).  This implementation deliberately does not take it: an
uncacheable file is opened O_DIRECT regardless of any delegation held,
which is compliant (read caching is simply suppressed more aggressively
than the Section 4.3 minimum) and avoids decoupling read vs write caching
behind a single open flag.  Relaxing reads under a delegation is left as
a possible future optimization.

Section 6 observes the benefit holds "for applications that issue
well-formed I/O requests".  That alignment caveat does not constrain the
Linux NFS client's over-the-wire path: the client readily issues
misaligned I/O using O_DIRECT over SunRPC to the remote NFS server.  The
only place a fallback from O_DIRECT to buffered I/O for misaligned I/O
applies is NFS LOCALIO (fs/nfs/localio.c), which detects non-DIO-aligned
I/O and falls back internally; that path is unaffected by this change.

See: https://datatracker.ietf.org/doc/draft-ietf-nfsv4-uncacheable-files/

Signed-off-by: Mike Snitzer <[email protected]>
Assisted-by: Claude:claude-opus-4-8
---
 fs/nfs/dir.c           |  4 ++++
 fs/nfs/nfs4file.c      |  2 ++
 fs/nfs/nfs4proc.c      | 10 ++++++++++
 include/linux/nfs_fs.h |  1 +
 4 files changed, 17 insertions(+)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c7b723c18620..6b07abf272b1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2208,6 +2208,10 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 	file->f_mode |= FMODE_CAN_ODIRECT;
+	if (test_bit(NFS_CONTEXT_O_DIRECT, &ctx->flags)) {
+		file->f_flags |= O_DIRECT;
+		open_flags |= O_DIRECT;
+	}
 
 	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
 	trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index be40e126c539..6401f6363f75 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -91,6 +91,8 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	nfs_fscache_open_file(inode, filp);
 	err = 0;
 	filp->f_mode |= FMODE_CAN_ODIRECT;
+	if (test_bit(NFS_CONTEXT_O_DIRECT, &ctx->flags))
+		filp->f_flags |= O_DIRECT;
 
 out_put_ctx:
 	put_nfs_open_context(ctx);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c8b777465ded..5bec57a2027c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3853,6 +3853,16 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx,
 
 	if (IS_ERR(state))
 		return ERR_CAST(state);
+
+	/*
+	 * Use O_DIRECT if file was marked as Uncacheable, see:
+	 * https://datatracker.ietf.org/doc/draft-ietf-nfsv4-uncacheable-files/
+	 */
+	if (!(open_flags & O_DIRECT) && NFS_I(state->inode)->uncacheable_file_data) {
+		if (!(open_flags & O_APPEND))
+			set_bit(NFS_CONTEXT_O_DIRECT, &ctx->flags);
+	}
+
 	return state->inode;
 }
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 8552a0d778d9..48b806aa3a2f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -110,6 +110,7 @@ struct nfs_open_context {
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
 #define NFS_CONTEXT_WRITE_SYNC		(5)
+#define NFS_CONTEXT_O_DIRECT		(6)
 
 	struct nfs4_threshold	*mdsthreshold;
 	struct list_head list;
-- 
2.47.3