nfsd: fix nfs read eof detection
Currently, the knfsd server assumes that a short read indicates an
end of file. That assumption is incorrect. The short read means that
either we've hit the end of file, or we've hit a read error.
In the case of a read error, the client may want to retry (as per the
implementation recommendations in RFC1813 and RFC7530), but currently it
is being told that it hit an eof.
Move the code to detect eof from version specific code into the generic
nfsd read.
Report eof only in the two following cases:
1) read() returns a zero length short read with no error.
2) the offset+length of the read is >= the file size.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e0f7792..a13fd9d 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -80,13 +80,16 @@ __be32 nfsd_open_verified(struct svc_rqst *, struct svc_fh *, umode_t,
int, struct file **);
__be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct file *file, loff_t offset,
- unsigned long *count);
+ unsigned long *count,
+ u32 *eof);
__be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct file *file, loff_t offset,
struct kvec *vec, int vlen,
- unsigned long *count);
+ unsigned long *count,
+ u32 *eof);
__be32 nfsd_read(struct svc_rqst *, struct svc_fh *,
- loff_t, struct kvec *, int, unsigned long *);
+ loff_t, struct kvec *, int, unsigned long *,
+ u32 *eof);
__be32 nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t,
struct kvec *, int, unsigned long *, int);
__be32 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -149,23 +152,4 @@ static inline int nfsd_create_is_exclusive(int createmode)
|| createmode == NFS4_CREATE_EXCLUSIVE4_1;
}
-static inline bool nfsd_eof_on_read(long requested, long read,
- loff_t offset, loff_t size)
-{
- /* We assume a short read means eof: */
- if (requested > read)
- return true;
- /*
- * A non-short read might also reach end of file. The spec
- * still requires us to set eof in that case.
- *
- * Further operations may have modified the file size since
- * the read, so the following check is not atomic with the read.
- * We've only seen that cause a problem for a client in the case
- * where the read returned a count of 0 without setting eof.
- * That case was fixed by the addition of the above check.
- */
- return (offset + read >= size);
-}
-
#endif /* LINUX_NFSD_VFS_H */