* [PATCH v3 1/6] nfs4.2: add UNCACHEABLE_FILE_DATA attribute support
2026-07-01 20:43 [PATCH v3 0/6] nfs: NFSv4.2 client support for UNCACHEABLE_FILE_DATA and UNCACHEABLE_DIRENT_METADATA Mike Snitzer
@ 2026-07-01 20:43 ` Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 2/6] nfs4.2: request UNCACHEABLE_FILE_DATA only for regular files Mike Snitzer
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Mike Snitzer @ 2026-07-01 20:43 UTC (permalink / raw)
To: Trond Myklebust, Anna Schumaker; +Cc: Tom Haynes, Chuck Lever, linux-nfs
From: Tom Haynes <loghyr@hammerspace.com>
Recognize the NFSv4.2 per-file UNCACHEABLE_FILE_DATA attribute (attr 87,
draft-ietf-nfsv4-uncacheable-files): decode it via GETATTR, track per-
exported-filesystem support, and record on the inode whether a regular
file's data must not be cached. Acting on the attribute (opening such
files O_DIRECT) is done by a subsequent change.
If the NFSv4 server reports a regular file's UNCACHEABLE_FILE_DATA as
true, it indicates the file's data must not be cached; the client records
this in NFS_I(inode)->uncacheable_file_data for use by the I/O paths.
The UNCACHEABLE_FILE_DATA attribute applies only to regular files
(NF4REG); per the draft a server MUST reject a query of it on any other
object type with NFS4ERR_INVAL. A subsequent commit gates the client
accordingly.
See: https://datatracker.ietf.org/doc/draft-ietf-nfsv4-uncacheable-files/
Signed-off-by: Tom Haynes <loghyr@hammerspace.com>
[snitzer: adapt Tom's original code focused on metadata for ABE]
Co-developed-by: Mike Snitzer <snitzer@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@hammerspace.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
fs/nfs/inode.c | 22 +++++++++++++++++++---
fs/nfs/nfs4proc.c | 15 ++++++++++++---
fs/nfs/nfs4trace.h | 3 ++-
fs/nfs/nfs4xdr.c | 35 ++++++++++++++++++++++++++++++++++-
fs/nfs/nfstrace.h | 3 ++-
include/linux/nfs4.h | 9 +++++++++
include/linux/nfs_fs.h | 3 +++
include/linux/nfs_xdr.h | 8 +++++++-
8 files changed, 88 insertions(+), 10 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5bcd4027d203..68a1d97d9560 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -507,6 +507,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
inode->i_blocks = 0;
nfsi->write_io = 0;
nfsi->read_io = 0;
+ nfsi->uncacheable_file_data = false;
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
@@ -561,6 +562,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
} else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED &&
fattr->size != 0)
nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
+ if (fattr->valid & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ nfsi->uncacheable_file_data =
+ fattr->aux_flags & NFS_AUX_UNCACHEABLE_FILE_DATA;
+ else if (fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_UNCACHEABLE_FILE_DATA);
nfs_setsecurity(inode, fattr);
@@ -1975,7 +1981,8 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
- NFS_INO_INVALID_NLINK | NFS_INO_INVALID_BTIME;
+ NFS_INO_INVALID_NLINK | NFS_INO_INVALID_BTIME |
+ NFS_INO_INVALID_UNCACHEABLE_FILE_DATA;
unsigned long cache_validity = NFS_I(inode)->cache_validity;
enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type;
@@ -2297,7 +2304,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_FORCED
- | NFS_INO_INVALID_BLOCKS);
+ | NFS_INO_INVALID_BLOCKS
+ | NFS_INO_INVALID_UNCACHEABLE_FILE_DATA);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
@@ -2337,7 +2345,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
| NFS_INO_INVALID_NLINK
| NFS_INO_INVALID_MODE
| NFS_INO_INVALID_OTHER
- | NFS_INO_INVALID_BTIME;
+ | NFS_INO_INVALID_BTIME
+ | NFS_INO_INVALID_UNCACHEABLE_FILE_DATA;
if (S_ISDIR(inode->i_mode))
nfs_force_lookup_revalidate(inode);
attr_changed = true;
@@ -2461,6 +2470,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->cache_validity |=
save_cache_validity & NFS_INO_INVALID_BLOCKS;
+ if (fattr->valid & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ nfsi->uncacheable_file_data =
+ fattr->aux_flags & NFS_AUX_UNCACHEABLE_FILE_DATA;
+ else if (fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ nfsi->cache_validity |=
+ save_cache_validity & NFS_INO_INVALID_UNCACHEABLE_FILE_DATA;
+
/* Update attrtimeo value if we're out of the unstable period */
if (attr_changed) {
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1360409d8de9..ad03b8518c14 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -225,8 +225,9 @@ const u32 nfs4_fattr_bitmap[3] = {
| FATTR4_WORD1_TIME_METADATA
| FATTR4_WORD1_TIME_MODIFY
| FATTR4_WORD1_MOUNTED_ON_FILEID,
+ FATTR4_WORD2_UNCACHEABLE_FILE_DATA
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
- FATTR4_WORD2_SECURITY_LABEL
+ | FATTR4_WORD2_SECURITY_LABEL
#endif
};
@@ -250,6 +251,7 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
| FATTR4_WORD2_SECURITY_LABEL
#endif
+ | FATTR4_WORD2_UNCACHEABLE_FILE_DATA
};
static const u32 nfs4_open_noattr_bitmap[3] = {
@@ -327,6 +329,9 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
if (!(cache_validity & NFS_INO_INVALID_BTIME))
dst[1] &= ~FATTR4_WORD1_TIME_CREATE;
+ if (!(cache_validity & NFS_INO_INVALID_UNCACHEABLE_FILE_DATA))
+ dst[2] &= ~FATTR4_WORD2_UNCACHEABLE_FILE_DATA;
+
if (nfs_have_delegated_mtime(inode)) {
if (!(cache_validity & NFS_INO_INVALID_ATIME))
dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
@@ -1238,7 +1243,7 @@ nfs4_update_changeattr_locked(struct inode *inode,
NFS_INO_INVALID_SIZE | NFS_INO_INVALID_OTHER |
NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK |
NFS_INO_INVALID_MODE | NFS_INO_INVALID_BTIME |
- NFS_INO_INVALID_XATTR;
+ NFS_INO_INVALID_XATTR | NFS_INO_INVALID_UNCACHEABLE_FILE_DATA;
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
}
nfsi->attrtimeo_timestamp = jiffies;
@@ -3857,7 +3862,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
-#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_OPEN_ARGUMENTS - 1UL)
+#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_UNCACHEABLE_FILE_DATA - 1UL)
#define FATTR4_WORD2_NFS42_TIME_DELEG_MASK \
(FATTR4_WORD2_TIME_DELEG_MODIFY|FATTR4_WORD2_TIME_DELEG_ACCESS)
@@ -3981,6 +3986,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
memcpy(server->attr_bitmask_nl, res.attr_bitmask,
sizeof(server->attr_bitmask));
server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
+ if (!(res.attr_bitmask[2] & FATTR4_WORD2_UNCACHEABLE_FILE_DATA))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA;
if (res.open_caps.oa_share_access_want[0] &
NFS4_SHARE_WANT_OPEN_XOR_DELEGATION)
@@ -5809,6 +5816,8 @@ void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[],
bitmask[1] |= FATTR4_WORD1_SPACE_USED;
if (cache_validity & NFS_INO_INVALID_BTIME)
bitmask[1] |= FATTR4_WORD1_TIME_CREATE;
+ if (cache_validity & NFS_INO_INVALID_UNCACHEABLE_FILE_DATA)
+ bitmask[2] |= FATTR4_WORD2_UNCACHEABLE_FILE_DATA;
if (cache_validity & NFS_INO_INVALID_SIZE)
bitmask[0] |= FATTR4_WORD0_SIZE;
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 1ed677810d9d..3298dab34a78 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -33,7 +33,8 @@
{ NFS_ATTR_FATTR_CHANGE, "CHANGE" }, \
{ NFS_ATTR_FATTR_OWNER_NAME, "OWNER_NAME" }, \
{ NFS_ATTR_FATTR_GROUP_NAME, "GROUP_NAME" }, \
- { NFS_ATTR_FATTR_BTIME, "BTIME" })
+ { NFS_ATTR_FATTR_BTIME, "BTIME" }, \
+ { NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA, "UNCACHEABLE_FILE_DATA" })
DECLARE_EVENT_CLASS(nfs4_clientid_event,
TP_PROTO(
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c23c2eee1b5c..fc049ce4ba8a 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -120,7 +120,8 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
3*nfstime4_maxsz + \
nfs4_owner_maxsz + \
nfs4_group_maxsz + nfs4_label_maxsz + \
- decode_mdsthreshold_maxsz))
+ decode_mdsthreshold_maxsz + \
+ 1)) /* uncacheable_file_data */
#define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \
nfs4_fattr_value_maxsz)
#define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz)
@@ -4380,6 +4381,30 @@ static int decode_attr_open_arguments(struct xdr_stream *xdr, uint32_t *bitmap,
return 0;
}
+static int decode_attr_uncacheable_file_data(struct xdr_stream *xdr, uint32_t *bitmap,
+ uint32_t *res, uint64_t *flags)
+{
+ int status = 0;
+ __be32 *p;
+
+ if (unlikely(bitmap[2] & (FATTR4_WORD2_UNCACHEABLE_FILE_DATA - 1U)))
+ return -EIO;
+ if (likely(bitmap[2] & FATTR4_WORD2_UNCACHEABLE_FILE_DATA)) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ return -EIO;
+ if (be32_to_cpup(p))
+ *res |= NFS_AUX_UNCACHEABLE_FILE_DATA;
+ else
+ *res &= ~NFS_AUX_UNCACHEABLE_FILE_DATA;
+ bitmap[2] &= ~FATTR4_WORD2_UNCACHEABLE_FILE_DATA;
+ *flags |= NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA;
+ }
+ dprintk("%s: uncacheable_file_data: =%s\n", __func__,
+ (*res & NFS_AUX_UNCACHEABLE_FILE_DATA) == 0 ? "false" : "true");
+ return status;
+}
+
static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
{
unsigned int attrwords = XDR_QUADLEN(attrlen);
@@ -4725,6 +4750,8 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
uint32_t type;
int32_t err;
+ fattr->aux_flags = 0;
+
status = decode_attr_type(xdr, bitmap, &type);
if (status < 0)
goto xdr_error;
@@ -4843,6 +4870,12 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
goto xdr_error;
fattr->valid |= status;
+ status = decode_attr_uncacheable_file_data(xdr, bitmap, &fattr->aux_flags,
+ &fattr->valid);
+ if (status < 0)
+ goto xdr_error;
+
+ status = 0;
xdr_error:
dprintk("%s: xdr returned %d\n", __func__, -status);
return status;
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 4ada21f4eebd..b15c1732c869 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -33,7 +33,8 @@
{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \
{ NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \
{ NFS_INO_INVALID_MODE, "INVALID_MODE" }, \
- { NFS_INO_INVALID_BTIME, "INVALID_BTIME" })
+ { NFS_INO_INVALID_BTIME, "INVALID_BTIME" }, \
+ { NFS_INO_INVALID_UNCACHEABLE_FILE_DATA, "INVALID_UNCACHEABLE_FILE_DATA" })
#define nfs_show_nfsi_flags(v) \
__print_flags(v, "|", \
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 44e5e9fa12e1..1a3981c26b23 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -389,6 +389,14 @@ enum {
FATTR4_XATTR_SUPPORT = 82,
};
+/*
+ * Symbol name and value are from draft-ietf-nfsv4-uncacheable-files
+ * Section 7. "XDR for Uncacheable Attribute"
+ */
+enum {
+ FATTR4_UNCACHEABLE_FILE_DATA = 87,
+};
+
/*
* The following internal definitions enable processing the above
* attribute bits within 32-bit word boundaries.
@@ -475,6 +483,7 @@ enum {
#define FATTR4_WORD2_ACL_TRUEFORM_SCOPE BIT(FATTR4_ACL_TRUEFORM_SCOPE - 64)
#define FATTR4_WORD2_POSIX_DEFAULT_ACL BIT(FATTR4_POSIX_DEFAULT_ACL - 64)
#define FATTR4_WORD2_POSIX_ACCESS_ACL BIT(FATTR4_POSIX_ACCESS_ACL - 64)
+#define FATTR4_WORD2_UNCACHEABLE_FILE_DATA BIT(FATTR4_UNCACHEABLE_FILE_DATA - 64)
/* MDS threshold bitmap bits */
#define THRESHOLD_RD (1UL << 0)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index ec17e602c979..8552a0d778d9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -162,6 +162,8 @@ struct nfs_inode {
struct timespec64 btime;
+ bool uncacheable_file_data : 1;
+
/*
* read_cache_jiffies is when we started read-caching this inode.
* attrtimeo is for how long the cached information is assumed
@@ -319,6 +321,7 @@ struct nfs4_copy_state {
#define NFS_INO_INVALID_NLINK BIT(16) /* cached nlinks is invalid */
#define NFS_INO_INVALID_MODE BIT(17) /* cached mode is invalid */
#define NFS_INO_INVALID_BTIME BIT(18) /* cached btime is invalid */
+#define NFS_INO_INVALID_UNCACHEABLE_FILE_DATA BIT(19) /* cached uncacheable_file_data is invalid */
#define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \
| NFS_INO_INVALID_CTIME \
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 11c5b31cfc7d..2e1987ac403d 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -17,6 +17,9 @@
#define NFS_BITMASK_SZ 3
+/* aux_flags in nfs_fattr */
+#define NFS_AUX_UNCACHEABLE_FILE_DATA BIT(0)
+
struct nfs4_string {
unsigned int len;
char *data;
@@ -68,6 +71,7 @@ struct nfs_fattr {
struct timespec64 mtime;
struct timespec64 ctime;
struct timespec64 btime;
+ __u32 aux_flags; /* NFSv4 auxiliary flags bitfield */
__u64 change_attr; /* NFSv4 change attribute */
__u64 pre_change_attr;/* pre-op NFSv4 change attribute */
__u64 pre_size; /* pre_op_attr.size */
@@ -108,6 +112,7 @@ struct nfs_fattr {
#define NFS_ATTR_FATTR_GROUP_NAME BIT_ULL(24)
#define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
#define NFS_ATTR_FATTR_BTIME BIT_ULL(26)
+#define NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA BIT_ULL(27)
#define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
| NFS_ATTR_FATTR_MODE \
@@ -129,7 +134,8 @@ struct nfs_fattr {
#define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
| NFS_ATTR_FATTR_SPACE_USED \
| NFS_ATTR_FATTR_BTIME \
- | NFS_ATTR_FATTR_V4_SECURITY_LABEL)
+ | NFS_ATTR_FATTR_V4_SECURITY_LABEL \
+ | NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
/*
* Maximal number of supported layout drivers.
--
2.47.3
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 2/6] nfs4.2: request UNCACHEABLE_FILE_DATA only for regular files
2026-07-01 20:43 [PATCH v3 0/6] nfs: NFSv4.2 client support for UNCACHEABLE_FILE_DATA and UNCACHEABLE_DIRENT_METADATA Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 1/6] nfs4.2: add UNCACHEABLE_FILE_DATA attribute support Mike Snitzer
@ 2026-07-01 20:43 ` Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 3/6] nfs4.2: open UNCACHEABLE_FILE_DATA files with O_DIRECT Mike Snitzer
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Mike Snitzer @ 2026-07-01 20:43 UTC (permalink / raw)
To: Trond Myklebust, Anna Schumaker; +Cc: Tom Haynes, Chuck Lever, linux-nfs
The UNCACHEABLE_FILE_DATA attribute applies only to regular files
(NF4REG); per draft-ietf-nfsv4-uncacheable-files a server MUST reject a
query of it on any other object type with NFS4ERR_INVAL. The previous
commit decodes and tracks the attribute but does not gate it: the bit
rides in the per-server attribute bitmask (server->attr_bitmask) and in
the generic getattr request bitmap (nfs4_fattr_bitmap), so it would be
requested for non-regular objects too -- e.g. a plain directory GETATTR,
a LOOKUP that resolves to a directory, or a CREATE (which only ever makes
non-regular objects). A strict server would fail those compounds.
Gate the client accordingly:
- Only set NFS_INO_INVALID_UNCACHEABLE_FILE_DATA on regular-file inodes,
so the attribute is never (re)requested for directories or other
non-regular objects via the delegation GETATTR or nfs4_bitmask_set()
refresh paths.
- Gate the request by object type at the single choke point
nfs4_bitmap_copy_adjust(), which clears
FATTR4_WORD2_UNCACHEABLE_FILE_DATA unless the target inode is a
regular file (a NULL inode -- unknown object type -- clears it too).
This already covers GETATTR, SETATTR and LINK; route LOOKUP, LOOKUPP
and CREATE through it as well.
The bit is kept in server->attr_bitmask (it is server-supported, and OPEN
still requests it via its regular-file-only open_bitmap), so no bespoke
per-data-file bitmask plumbing is needed. The remaining getattr-bearing
compounds are already safe: ACCESS, DELEGRETURN, WRITE, CLOSE and
LAYOUTCOMMIT use server->cache_consistency_bitmask (no word2 attributes)
or operate on regular files; READDIR does not encode the bit; and
LOOKUP_ROOT, FSINFO, STATFS and PATHCONF use fixed bitmaps without it.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
fs/nfs/inode.c | 6 ++++--
fs/nfs/nfs4proc.c | 37 ++++++++++++++++++++++++++++++++++---
2 files changed, 38 insertions(+), 5 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 68a1d97d9560..bb6e58123341 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -565,7 +565,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
if (fattr->valid & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
nfsi->uncacheable_file_data =
fattr->aux_flags & NFS_AUX_UNCACHEABLE_FILE_DATA;
- else if (fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ else if (S_ISREG(inode->i_mode) &&
+ (fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_UNCACHEABLE_FILE_DATA);
nfs_setsecurity(inode, fattr);
@@ -2473,7 +2474,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
if (fattr->valid & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
nfsi->uncacheable_file_data =
fattr->aux_flags & NFS_AUX_UNCACHEABLE_FILE_DATA;
- else if (fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ else if (S_ISREG(inode->i_mode) &&
+ (fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA))
nfsi->cache_validity |=
save_cache_validity & NFS_INO_INVALID_UNCACHEABLE_FILE_DATA;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ad03b8518c14..a0d088cd47ac 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -308,6 +308,15 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
unsigned long cache_validity;
memcpy(dst, src, NFS4_BITMASK_SZ*sizeof(*dst));
+ /*
+ * The uncacheable_file_data attribute applies only to regular files
+ * (NF4REG); a server must reject a query of it on any other object
+ * type with NFS4ERR_INVAL. Never request it unless the target is
+ * known to be a regular file (callers with an unknown object type,
+ * e.g. LOOKUP, pass a NULL inode).
+ */
+ if (!inode || !S_ISREG(inode->i_mode))
+ dst[2] &= ~FATTR4_WORD2_UNCACHEABLE_FILE_DATA;
if (!inode || !nfs_have_read_or_write_delegation(inode))
return;
@@ -4598,6 +4607,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
.rpc_resp = &res,
};
unsigned short task_flags = 0;
+ __u32 bitmask[NFS4_BITMASK_SZ];
if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
task_flags = RPC_TASK_MOVEABLE;
@@ -4606,7 +4616,13 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
if (nfs_lookup_is_soft_revalidate(dentry))
task_flags |= RPC_TASK_TIMEOUT;
- args.bitmask = nfs4_bitmask(server, fattr->label);
+ /*
+ * The looked-up object's type is unknown here, so gate out the
+ * regular-file-only uncacheable_file_data attribute (NULL inode).
+ */
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label),
+ NULL, 0);
+ args.bitmask = bitmask;
nfs_fattr_init(fattr);
@@ -4720,13 +4736,20 @@ static int _nfs4_proc_lookupp(struct inode *inode,
.rpc_resp = &res,
};
unsigned short task_flags = 0;
+ __u32 bitmask[NFS4_BITMASK_SZ];
if (server->flags & NFS_MOUNT_SOFTREVAL)
task_flags |= RPC_TASK_TIMEOUT;
if (server->caps & NFS_CAP_MOVEABLE)
task_flags |= RPC_TASK_MOVEABLE;
- args.bitmask = nfs4_bitmask(server, fattr->label);
+ /*
+ * The looked-up object's type is unknown here, so gate out the
+ * regular-file-only uncacheable_file_data attribute (NULL inode).
+ */
+ nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label),
+ NULL, 0);
+ args.bitmask = bitmask;
nfs_fattr_init(fattr);
nfs4_init_sequence(server->nfs_client, &args.seq_args, &res.seq_res, 0, 0);
@@ -5141,6 +5164,7 @@ struct nfs4_createdata {
struct nfs4_create_res res;
struct nfs_fh fh;
struct nfs_fattr fattr;
+ u32 bitmask[NFS4_BITMASK_SZ];
};
static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
@@ -5164,7 +5188,14 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
data->arg.name = name;
data->arg.attrs = sattr;
data->arg.ftype = ftype;
- data->arg.bitmask = nfs4_bitmask(server, data->fattr.label);
+ /*
+ * CREATE only makes non-regular objects, so gate out the
+ * regular-file-only uncacheable_file_data attribute (NULL inode).
+ */
+ nfs4_bitmap_copy_adjust(data->bitmask,
+ nfs4_bitmask(server, data->fattr.label),
+ NULL, 0);
+ data->arg.bitmask = data->bitmask;
data->arg.umask = current_umask();
data->res.server = server;
data->res.fh = &data->fh;
--
2.47.3
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 3/6] nfs4.2: open UNCACHEABLE_FILE_DATA files with O_DIRECT
2026-07-01 20:43 [PATCH v3 0/6] nfs: NFSv4.2 client support for UNCACHEABLE_FILE_DATA and UNCACHEABLE_DIRENT_METADATA Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 1/6] nfs4.2: add UNCACHEABLE_FILE_DATA attribute support Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 2/6] nfs4.2: request UNCACHEABLE_FILE_DATA only for regular files Mike Snitzer
@ 2026-07-01 20:43 ` Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 4/6] nfs4.2: add UNCACHEABLE_DIRENT_METADATA attribute support Mike Snitzer
` (2 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Mike Snitzer @ 2026-07-01 20:43 UTC (permalink / raw)
To: Trond Myklebust, Anna Schumaker; +Cc: Tom Haynes, Chuck Lever, linux-nfs
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 <snitzer@kernel.org>
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 a0d088cd47ac..3903d613f3eb 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
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 4/6] nfs4.2: add UNCACHEABLE_DIRENT_METADATA attribute support
2026-07-01 20:43 [PATCH v3 0/6] nfs: NFSv4.2 client support for UNCACHEABLE_FILE_DATA and UNCACHEABLE_DIRENT_METADATA Mike Snitzer
` (2 preceding siblings ...)
2026-07-01 20:43 ` [PATCH v3 3/6] nfs4.2: open UNCACHEABLE_FILE_DATA files with O_DIRECT Mike Snitzer
@ 2026-07-01 20:43 ` Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 5/6] nfs4.2: request UNCACHEABLE_DIRENT_METADATA only for directories Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 6/6] nfs4.2: honor UNCACHEABLE_DIRENT_METADATA by refetching readdir Mike Snitzer
5 siblings, 0 replies; 7+ messages in thread
From: Mike Snitzer @ 2026-07-01 20:43 UTC (permalink / raw)
To: Trond Myklebust, Anna Schumaker; +Cc: Tom Haynes, Chuck Lever, linux-nfs
Recognize the NFSv4.2 per-directory UNCACHEABLE_DIRENT_METADATA attribute
(attr 88, draft-ietf-nfsv4-uncacheable-directories): decode it via
GETATTR, track per-exported-filesystem support, and record on the inode
whether a directory's directory-entry metadata must not be cached.
Honoring the attribute (refetching directory-entry metadata from the
server on each READDIR) is done by a subsequent change.
If the NFSv4 server reports a directory's UNCACHEABLE_DIRENT_METADATA as
true, it indicates the directory's directory-entry metadata must not be
cached; the client records this in
NFS_I(inode)->uncacheable_dirent_metadata for use by the readdir path.
The UNCACHEABLE_DIRENT_METADATA attribute applies only to directory
objects (NF4DIR) and is independent of the companion
UNCACHEABLE_FILE_DATA attribute (attr 87); the two govern different
aspects of client caching and may be used separately. A subsequent
commit gates the client accordingly so the attribute is requested only
for directories.
Unlike the per-file UNCACHEABLE_FILE_DATA attribute, this directory
attribute is deliberately not tied to the cache_validity / file-delegation
machinery (nfs4_bitmap_copy_adjust()'s delegation block, nfs4_bitmask_set()):
a directory cannot hold an NFSv4 read/write (file) delegation, and per the
draft a server must recall or withhold a directory delegation while the
attribute is set, so there is never an authoritative cached state to
optimize against. The attribute is simply requested on every directory
GETATTR and recorded on receipt.
See: https://datatracker.ietf.org/doc/draft-ietf-nfsv4-uncacheable-directories/
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
fs/nfs/inode.c | 8 ++++++++
fs/nfs/nfs4proc.c | 6 +++++-
fs/nfs/nfs4trace.h | 3 ++-
fs/nfs/nfs4xdr.c | 31 ++++++++++++++++++++++++++++++-
include/linux/nfs4.h | 9 +++++++++
include/linux/nfs_fs.h | 1 +
include/linux/nfs_xdr.h | 5 ++++-
7 files changed, 59 insertions(+), 4 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index bb6e58123341..080a9fed99ba 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -508,6 +508,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
nfsi->write_io = 0;
nfsi->read_io = 0;
nfsi->uncacheable_file_data = false;
+ nfsi->uncacheable_dirent_metadata = false;
nfsi->read_cache_jiffies = fattr->time_start;
nfsi->attr_gencount = fattr->gencount;
@@ -568,6 +569,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
else if (S_ISREG(inode->i_mode) &&
(fattr_supported & NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA))
nfs_set_cache_invalid(inode, NFS_INO_INVALID_UNCACHEABLE_FILE_DATA);
+ if (fattr->valid & NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA)
+ nfsi->uncacheable_dirent_metadata =
+ fattr->aux_flags & NFS_AUX_UNCACHEABLE_DIRENT_METADATA;
nfs_setsecurity(inode, fattr);
@@ -2479,6 +2483,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->cache_validity |=
save_cache_validity & NFS_INO_INVALID_UNCACHEABLE_FILE_DATA;
+ if (fattr->valid & NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA)
+ nfsi->uncacheable_dirent_metadata =
+ fattr->aux_flags & NFS_AUX_UNCACHEABLE_DIRENT_METADATA;
+
/* Update attrtimeo value if we're out of the unstable period */
if (attr_changed) {
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3903d613f3eb..4c8436ac5cfc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -226,6 +226,7 @@ const u32 nfs4_fattr_bitmap[3] = {
| FATTR4_WORD1_TIME_MODIFY
| FATTR4_WORD1_MOUNTED_ON_FILEID,
FATTR4_WORD2_UNCACHEABLE_FILE_DATA
+ | FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
| FATTR4_WORD2_SECURITY_LABEL
#endif
@@ -252,6 +253,7 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
| FATTR4_WORD2_SECURITY_LABEL
#endif
| FATTR4_WORD2_UNCACHEABLE_FILE_DATA
+ | FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA
};
static const u32 nfs4_open_noattr_bitmap[3] = {
@@ -3881,7 +3883,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
-#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_UNCACHEABLE_FILE_DATA - 1UL)
+#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA - 1UL)
#define FATTR4_WORD2_NFS42_TIME_DELEG_MASK \
(FATTR4_WORD2_TIME_DELEG_MODIFY|FATTR4_WORD2_TIME_DELEG_ACCESS)
@@ -4007,6 +4009,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
if (!(res.attr_bitmask[2] & FATTR4_WORD2_UNCACHEABLE_FILE_DATA))
server->fattr_valid &= ~NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA;
+ if (!(res.attr_bitmask[2] & FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA))
+ server->fattr_valid &= ~NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA;
if (res.open_caps.oa_share_access_want[0] &
NFS4_SHARE_WANT_OPEN_XOR_DELEGATION)
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 3298dab34a78..868c201d024f 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -34,7 +34,8 @@
{ NFS_ATTR_FATTR_OWNER_NAME, "OWNER_NAME" }, \
{ NFS_ATTR_FATTR_GROUP_NAME, "GROUP_NAME" }, \
{ NFS_ATTR_FATTR_BTIME, "BTIME" }, \
- { NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA, "UNCACHEABLE_FILE_DATA" })
+ { NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA, "UNCACHEABLE_FILE_DATA" }, \
+ { NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA, "UNCACHEABLE_DIRENT_METADATA" })
DECLARE_EVENT_CLASS(nfs4_clientid_event,
TP_PROTO(
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index fc049ce4ba8a..8329d5baf90e 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -121,7 +121,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
nfs4_owner_maxsz + \
nfs4_group_maxsz + nfs4_label_maxsz + \
decode_mdsthreshold_maxsz + \
- 1)) /* uncacheable_file_data */
+ 1)) /* uncacheable_file_data / dirent_metadata */
#define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \
nfs4_fattr_value_maxsz)
#define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz)
@@ -4405,6 +4405,30 @@ static int decode_attr_uncacheable_file_data(struct xdr_stream *xdr, uint32_t *b
return status;
}
+static int decode_attr_uncacheable_dirent_metadata(struct xdr_stream *xdr, uint32_t *bitmap,
+ uint32_t *res, uint64_t *flags)
+{
+ int status = 0;
+ __be32 *p;
+
+ if (unlikely(bitmap[2] & (FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA - 1U)))
+ return -EIO;
+ if (likely(bitmap[2] & FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA)) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ return -EIO;
+ if (be32_to_cpup(p))
+ *res |= NFS_AUX_UNCACHEABLE_DIRENT_METADATA;
+ else
+ *res &= ~NFS_AUX_UNCACHEABLE_DIRENT_METADATA;
+ bitmap[2] &= ~FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA;
+ *flags |= NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA;
+ }
+ dprintk("%s: uncacheable_dirent_metadata: =%s\n", __func__,
+ (*res & NFS_AUX_UNCACHEABLE_DIRENT_METADATA) == 0 ? "false" : "true");
+ return status;
+}
+
static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
{
unsigned int attrwords = XDR_QUADLEN(attrlen);
@@ -4875,6 +4899,11 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
if (status < 0)
goto xdr_error;
+ status = decode_attr_uncacheable_dirent_metadata(xdr, bitmap, &fattr->aux_flags,
+ &fattr->valid);
+ if (status < 0)
+ goto xdr_error;
+
status = 0;
xdr_error:
dprintk("%s: xdr returned %d\n", __func__, -status);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 1a3981c26b23..a30905cb4118 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -397,6 +397,14 @@ enum {
FATTR4_UNCACHEABLE_FILE_DATA = 87,
};
+/*
+ * Symbol name and value are from draft-ietf-nfsv4-uncacheable-directories
+ * Section 8. "XDR for Uncacheable Dirents Attribute"
+ */
+enum {
+ FATTR4_UNCACHEABLE_DIRENT_METADATA = 88,
+};
+
/*
* The following internal definitions enable processing the above
* attribute bits within 32-bit word boundaries.
@@ -484,6 +492,7 @@ enum {
#define FATTR4_WORD2_POSIX_DEFAULT_ACL BIT(FATTR4_POSIX_DEFAULT_ACL - 64)
#define FATTR4_WORD2_POSIX_ACCESS_ACL BIT(FATTR4_POSIX_ACCESS_ACL - 64)
#define FATTR4_WORD2_UNCACHEABLE_FILE_DATA BIT(FATTR4_UNCACHEABLE_FILE_DATA - 64)
+#define FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA BIT(FATTR4_UNCACHEABLE_DIRENT_METADATA - 64)
/* MDS threshold bitmap bits */
#define THRESHOLD_RD (1UL << 0)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 48b806aa3a2f..887b76c2a5dd 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -164,6 +164,7 @@ struct nfs_inode {
struct timespec64 btime;
bool uncacheable_file_data : 1;
+ bool uncacheable_dirent_metadata : 1;
/*
* read_cache_jiffies is when we started read-caching this inode.
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 2e1987ac403d..2018cc3c9c31 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -19,6 +19,7 @@
/* aux_flags in nfs_fattr */
#define NFS_AUX_UNCACHEABLE_FILE_DATA BIT(0)
+#define NFS_AUX_UNCACHEABLE_DIRENT_METADATA BIT(1)
struct nfs4_string {
unsigned int len;
@@ -113,6 +114,7 @@ struct nfs_fattr {
#define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
#define NFS_ATTR_FATTR_BTIME BIT_ULL(26)
#define NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA BIT_ULL(27)
+#define NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA BIT_ULL(28)
#define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
| NFS_ATTR_FATTR_MODE \
@@ -135,7 +137,8 @@ struct nfs_fattr {
| NFS_ATTR_FATTR_SPACE_USED \
| NFS_ATTR_FATTR_BTIME \
| NFS_ATTR_FATTR_V4_SECURITY_LABEL \
- | NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
+ | NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA \
+ | NFS_ATTR_FATTR_UNCACHEABLE_DIRENT_METADATA)
/*
* Maximal number of supported layout drivers.
--
2.47.3
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 5/6] nfs4.2: request UNCACHEABLE_DIRENT_METADATA only for directories
2026-07-01 20:43 [PATCH v3 0/6] nfs: NFSv4.2 client support for UNCACHEABLE_FILE_DATA and UNCACHEABLE_DIRENT_METADATA Mike Snitzer
` (3 preceding siblings ...)
2026-07-01 20:43 ` [PATCH v3 4/6] nfs4.2: add UNCACHEABLE_DIRENT_METADATA attribute support Mike Snitzer
@ 2026-07-01 20:43 ` Mike Snitzer
2026-07-01 20:43 ` [PATCH v3 6/6] nfs4.2: honor UNCACHEABLE_DIRENT_METADATA by refetching readdir Mike Snitzer
5 siblings, 0 replies; 7+ messages in thread
From: Mike Snitzer @ 2026-07-01 20:43 UTC (permalink / raw)
To: Trond Myklebust, Anna Schumaker; +Cc: Tom Haynes, Chuck Lever, linux-nfs
The UNCACHEABLE_DIRENT_METADATA attribute (attr 88) applies only to
directory objects (NF4DIR); per draft-ietf-nfsv4-uncacheable-directories
a server must reject a query of it on any other object type with
NFS4ERR_INVAL. Gate the request by object type at the single choke point
nfs4_bitmap_copy_adjust(), stripping FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA
unless the target is known to be a directory (callers with an unknown
object type, e.g. LOOKUP/LOOKUPP/CREATE, pass a NULL inode and are already
routed through this helper). This mirrors the NF4REG gating of the
companion UNCACHEABLE_FILE_DATA attribute: a regular file requests
file_data and never dirent_metadata, a directory requests dirent_metadata
and never file_data, and an unknown/other object requests neither.
The bit stays in server->attr_bitmask, so OPEN (which requests the
regular-file open bitmap) is unaffected. This type gate runs before the
helper's read/write (file) delegation handling and is the only adjustment
the directory attribute needs: a directory cannot hold a file delegation,
so the delegation-based suppression below it never applies.
See: https://datatracker.ietf.org/doc/draft-ietf-nfsv4-uncacheable-directories/
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
fs/nfs/nfs4proc.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4c8436ac5cfc..273fc9fc5fd7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -312,13 +312,16 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
memcpy(dst, src, NFS4_BITMASK_SZ*sizeof(*dst));
/*
* The uncacheable_file_data attribute applies only to regular files
- * (NF4REG); a server must reject a query of it on any other object
- * type with NFS4ERR_INVAL. Never request it unless the target is
- * known to be a regular file (callers with an unknown object type,
- * e.g. LOOKUP, pass a NULL inode).
+ * (NF4REG) and the uncacheable_dirent_metadata attribute only to
+ * directories (NF4DIR); a server must reject a query of either on any
+ * other object type with NFS4ERR_INVAL. Never request either unless
+ * the target is known to be of the matching type (callers with an
+ * unknown object type, e.g. LOOKUP, pass a NULL inode).
*/
if (!inode || !S_ISREG(inode->i_mode))
dst[2] &= ~FATTR4_WORD2_UNCACHEABLE_FILE_DATA;
+ if (!inode || !S_ISDIR(inode->i_mode))
+ dst[2] &= ~FATTR4_WORD2_UNCACHEABLE_DIRENT_METADATA;
if (!inode || !nfs_have_read_or_write_delegation(inode))
return;
--
2.47.3
^ permalink raw reply related [flat|nested] 7+ messages in thread* [PATCH v3 6/6] nfs4.2: honor UNCACHEABLE_DIRENT_METADATA by refetching readdir
2026-07-01 20:43 [PATCH v3 0/6] nfs: NFSv4.2 client support for UNCACHEABLE_FILE_DATA and UNCACHEABLE_DIRENT_METADATA Mike Snitzer
` (4 preceding siblings ...)
2026-07-01 20:43 ` [PATCH v3 5/6] nfs4.2: request UNCACHEABLE_DIRENT_METADATA only for directories Mike Snitzer
@ 2026-07-01 20:43 ` Mike Snitzer
5 siblings, 0 replies; 7+ messages in thread
From: Mike Snitzer @ 2026-07-01 20:43 UTC (permalink / raw)
To: Trond Myklebust, Anna Schumaker; +Cc: Tom Haynes, Chuck Lever, linux-nfs
Honor the per-directory UNCACHEABLE_DIRENT_METADATA attribute: when a
directory is marked uncacheable, nfs_readdir() bypasses the readdir page
cache and refetches directory-entry metadata from the server on every
readdir, satisfying the always-refetch semantics the attribute requires
(draft-ietf-nfsv4-uncacheable-directories Section 5.1).
Rather than searching the cached readdir folios, nfs_readdir() forces the
-EBADCOOKIE path so the request is served by uncached_readdir(); the
dir_cookie == 0 (start-of-directory) case is included so the very first
readdir of an uncacheable directory also goes to the server. A
tracepoint records when an uncacheable directory bypasses the cache.
The metadata the attribute governs is the per-entry size and timestamps,
which are carried only by READDIRPLUS (a plain READDIR refreshes names
but leaves the entries' attributes to the inode attribute caches). So
also force READDIRPLUS for an uncacheable directory (when the server is
capable): nfs_use_readdirplus() otherwise enables it only at the start of
the directory or once cache usage crosses a threshold, and the cache-
bypassing path above never accrues that usage -- which would leave
continuation READDIRs of a large directory refreshing names but serving
stale per-entry attributes. Forcing READDIRPLUS makes each READDIR
refresh the entries' attribute caches (via nfs_prime_dcache() ->
nfs_refresh_inode()), so a subsequent stat() observes current values.
The attribute does not change NFSv4.2 change-attribute semantics: the
client continues to use the directory change attribute for validation;
this only suppresses serving READDIR responses from the local cache.
See: https://datatracker.ietf.org/doc/draft-ietf-nfsv4-uncacheable-directories/
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Assisted-by: Claude:claude-opus-4-8
---
fs/nfs/dir.c | 18 ++++++++++++++++--
fs/nfs/nfstrace.h | 1 +
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 6b07abf272b1..2162e93992c2 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -667,6 +667,14 @@ static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx,
return false;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_FORCE_RDIRPLUS)
return true;
+ /*
+ * An uncacheable directory must refetch directory-entry metadata
+ * (including per-entry size and timestamps) from the server on each
+ * READDIR; force READDIRPLUS so those attributes are refreshed on
+ * every call rather than left stale in the inode attribute caches.
+ */
+ if (NFS_I(dir)->uncacheable_dirent_metadata)
+ return true;
if (ctx->pos == 0 ||
cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD)
return true;
@@ -1274,12 +1282,18 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->clear_cache = force_clear;
do {
- res = readdir_search_pagecache(desc);
+ if (nfsi->uncacheable_dirent_metadata) {
+ res = -EBADCOOKIE;
+ trace_nfs_readdir_uncacheable_directory(inode);
+ } else {
+ res = readdir_search_pagecache(desc);
+ }
if (res == -EBADCOOKIE) {
res = 0;
/* This means either end of directory */
- if (desc->dir_cookie && !desc->eof) {
+ if ((desc->dir_cookie || nfsi->uncacheable_dirent_metadata) &&
+ !desc->eof) {
/* Or that the server has 'lost' a cookie */
res = uncached_readdir(desc);
if (res == 0)
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index b15c1732c869..a9930d59c610 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -181,6 +181,7 @@ DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit);
DEFINE_NFS_INODE_EVENT(nfs_access_enter);
DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid);
DEFINE_NFS_INODE_EVENT(nfs_readdir_force_readdirplus);
+DEFINE_NFS_INODE_EVENT(nfs_readdir_uncacheable_directory);
DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done);
DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done);
--
2.47.3
^ permalink raw reply related [flat|nested] 7+ messages in thread