From: Chuck Lever <cel@kernel.org>
To: NeilBrown <neil@brown.name>, Jeff Layton <jlayton@kernel.org>,
Olga Kornievskaia <okorniev@redhat.com>,
Dai Ngo <dai.ngo@oracle.com>, Tom Talpey <tom@talpey.com>
Cc: <linux-nfs@vger.kernel.org>, Mike Snitzer <snitzer@kernel.org>
Subject: [PATCH v4 1/4] NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
Date: Fri, 26 Sep 2025 10:51:48 -0400 [thread overview]
Message-ID: <20250926145151.59941-2-cel@kernel.org> (raw)
In-Reply-To: <20250926145151.59941-1-cel@kernel.org>
From: Mike Snitzer <snitzer@kernel.org>
Use STATX_DIOALIGN and STATX_DIO_READ_ALIGN to get DIO alignment
attributes from the underlying filesystem and store them in the
associated nfsd_file. This is done when the nfsd_file is first
opened for each regular file.
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/filecache.c | 34 ++++++++++++++++++++++++++++++++++
fs/nfsd/filecache.h | 4 ++++
fs/nfsd/nfsfh.c | 4 ++++
fs/nfsd/trace.h | 27 +++++++++++++++++++++++++++
include/trace/misc/fs.h | 22 ++++++++++++++++++++++
5 files changed, 91 insertions(+)
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 75bc48031c07..78cca0d751ac 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -231,6 +231,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,
refcount_set(&nf->nf_ref, 1);
nf->nf_may = need;
nf->nf_mark = NULL;
+ nf->nf_dio_mem_align = 0;
+ nf->nf_dio_offset_align = 0;
+ nf->nf_dio_read_offset_align = 0;
return nf;
}
@@ -1048,6 +1051,35 @@ nfsd_file_is_cached(struct inode *inode)
return ret;
}
+static __be32
+nfsd_file_get_dio_attrs(const struct svc_fh *fhp, struct nfsd_file *nf)
+{
+ struct inode *inode = file_inode(nf->nf_file);
+ struct kstat stat;
+ __be32 status;
+
+ /* Currently only need to get DIO alignment info for regular files */
+ if (!S_ISREG(inode->i_mode))
+ return nfs_ok;
+
+ status = fh_getattr(fhp, &stat);
+ if (status != nfs_ok)
+ return status;
+
+ trace_nfsd_file_get_dio_attrs(inode, &stat);
+
+ if (stat.result_mask & STATX_DIOALIGN) {
+ nf->nf_dio_mem_align = stat.dio_mem_align;
+ nf->nf_dio_offset_align = stat.dio_offset_align;
+ }
+ if (stat.result_mask & STATX_DIO_READ_ALIGN)
+ nf->nf_dio_read_offset_align = stat.dio_read_offset_align;
+ else
+ nf->nf_dio_read_offset_align = nf->nf_dio_offset_align;
+
+ return nfs_ok;
+}
+
static __be32
nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
struct svc_cred *cred,
@@ -1166,6 +1198,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
}
status = nfserrno(ret);
trace_nfsd_file_open(nf, status);
+ if (status == nfs_ok)
+ status = nfsd_file_get_dio_attrs(fhp, nf);
}
} else
status = nfserr_jukebox;
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 24ddf60e8434..e3d6ca2b6030 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -54,6 +54,10 @@ struct nfsd_file {
struct list_head nf_gc;
struct rcu_head nf_rcu;
ktime_t nf_birthtime;
+
+ u32 nf_dio_mem_align;
+ u32 nf_dio_offset_align;
+ u32 nf_dio_read_offset_align;
};
int nfsd_file_cache_init(void);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index bd9acfdc7b01..ed85dd43da18 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -696,8 +696,12 @@ __be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat)
.mnt = fhp->fh_export->ex_path.mnt,
.dentry = fhp->fh_dentry,
};
+ struct inode *inode = d_inode(p.dentry);
u32 request_mask = STATX_BASIC_STATS;
+ if (S_ISREG(inode->i_mode))
+ request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN);
+
if (fhp->fh_maxsize == NFS4_FHSIZE)
request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index a664fdf1161e..6e2c8e2aab10 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1133,6 +1133,33 @@ TRACE_EVENT(nfsd_file_alloc,
)
);
+TRACE_EVENT(nfsd_file_get_dio_attrs,
+ TP_PROTO(
+ const struct inode *inode,
+ const struct kstat *stat
+ ),
+ TP_ARGS(inode, stat),
+ TP_STRUCT__entry(
+ __field(const void *, inode)
+ __field(unsigned long, mask)
+ __field(u32, mem_align)
+ __field(u32, offset_align)
+ __field(u32, read_offset_align)
+ ),
+ TP_fast_assign(
+ __entry->inode = inode;
+ __entry->mask = stat->result_mask;
+ __entry->mem_align = stat->dio_mem_align;
+ __entry->offset_align = stat->dio_offset_align;
+ __entry->read_offset_align = stat->dio_read_offset_align;
+ ),
+ TP_printk("inode=%p flags=%s mem_align=%u offset_align=%u read_offset_align=%u",
+ __entry->inode, show_statx_mask(__entry->mask),
+ __entry->mem_align, __entry->offset_align,
+ __entry->read_offset_align
+ )
+);
+
TRACE_EVENT(nfsd_file_acquire,
TP_PROTO(
const struct svc_rqst *rqstp,
diff --git a/include/trace/misc/fs.h b/include/trace/misc/fs.h
index 0406ebe2a80a..7ead1c61f0cb 100644
--- a/include/trace/misc/fs.h
+++ b/include/trace/misc/fs.h
@@ -141,3 +141,25 @@
{ ATTR_TIMES_SET, "TIMES_SET" }, \
{ ATTR_TOUCH, "TOUCH"}, \
{ ATTR_DELEG, "DELEG"})
+
+#define show_statx_mask(flags) \
+ __print_flags(flags, "|", \
+ { STATX_TYPE, "TYPE" }, \
+ { STATX_MODE, "MODE" }, \
+ { STATX_NLINK, "NLINK" }, \
+ { STATX_UID, "UID" }, \
+ { STATX_GID, "GID" }, \
+ { STATX_ATIME, "ATIME" }, \
+ { STATX_MTIME, "MTIME" }, \
+ { STATX_CTIME, "CTIME" }, \
+ { STATX_INO, "INO" }, \
+ { STATX_SIZE, "SIZE" }, \
+ { STATX_BLOCKS, "BLOCKS" }, \
+ { STATX_BASIC_STATS, "BASIC_STATS" }, \
+ { STATX_BTIME, "BTIME" }, \
+ { STATX_MNT_ID, "MNT_ID" }, \
+ { STATX_DIOALIGN, "DIOALIGN" }, \
+ { STATX_MNT_ID_UNIQUE, "MNT_ID_UNIQUE" }, \
+ { STATX_SUBVOL, "SUBVOL" }, \
+ { STATX_WRITE_ATOMIC, "WRITE_ATOMIC" }, \
+ { STATX_DIO_READ_ALIGN, "DIO_READ_ALIGN" })
--
2.51.0
next prev parent reply other threads:[~2025-09-26 14:51 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-26 14:51 [PATCH v4 0/4] NFSD direct I/O read Chuck Lever
2025-09-26 14:51 ` Chuck Lever [this message]
2025-09-26 14:51 ` [PATCH v4 2/4] NFSD: pass nfsd_file to nfsd_iter_read() Chuck Lever
2025-09-26 14:51 ` [PATCH v4 3/4] NFSD: Relocate the xdr_reserve_space_vec() call site Chuck Lever
2025-09-29 3:55 ` NeilBrown
2025-09-29 11:49 ` Jeff Layton
2025-09-26 14:51 ` [PATCH v4 4/4] NFSD: Implement NFSD_IO_DIRECT for NFS READ Chuck Lever
2025-09-29 4:02 ` NeilBrown
2025-09-29 7:29 ` Christoph Hellwig
2025-09-29 13:03 ` Chuck Lever
2025-09-29 13:06 ` 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=20250926145151.59941-2-cel@kernel.org \
--to=cel@kernel.org \
--cc=dai.ngo@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neil@brown.name \
--cc=okorniev@redhat.com \
--cc=snitzer@kernel.org \
--cc=tom@talpey.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