Merge tag 'iversion-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux

Pull i_version updates from Jeff Layton:
 "This overhauls how we handle i_version queries from nfsd.

  Instead of having special routines and grabbing the i_version field
  directly out of the inode in some cases, we've moved most of the
  handling into the various filesystems' getattr operations. As a bonus,
  this makes ceph's change attribute usable by knfsd as well.

  This should pave the way for future work to make this value queryable
  by userland, and to make it more resilient against rolling back on a
  crash"

* tag 'iversion-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux:
  nfsd: remove fetch_iversion export operation
  nfsd: use the getattr operation to fetch i_version
  nfsd: move nfsd4_change_attribute to nfsfh.c
  ceph: report the inode version in getattr if requested
  nfs: report the inode version in getattr if requested
  vfs: plumb i_version handling into struct kstat
  fs: clarify when the i_version counter must be updated
  fs: uninline inode_query_iversion

4 files changed, 52 insertions, 30 deletions

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 97edb32be77f..e12e5a4ad502 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2965,7 +2965,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 			goto out;
 	}
 
-	err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+	err = vfs_getattr(&path, &stat,
+			  STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE,
+			  AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_nfserr;
 	if (!(stat.result_mask & STATX_BTIME))
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 8c52b6c9d31a..76ea268dc420 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -628,6 +628,10 @@ void fh_fill_pre_attrs(struct svc_fh *fhp)
 		stat.mtime = inode->i_mtime;
 		stat.ctime = inode->i_ctime;
 		stat.size  = inode->i_size;
+		if (v4 && IS_I_VERSION(inode)) {
+			stat.change_cookie = inode_query_iversion(inode);
+			stat.result_mask |= STATX_CHANGE_COOKIE;
+		}
 	}
 	if (v4)
 		fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
@@ -659,6 +663,10 @@ void fh_fill_post_attrs(struct svc_fh *fhp)
 	if (err) {
 		fhp->fh_post_saved = false;
 		fhp->fh_post_attr.ctime = inode->i_ctime;
+		if (v4 && IS_I_VERSION(inode)) {
+			fhp->fh_post_attr.change_cookie = inode_query_iversion(inode);
+			fhp->fh_post_attr.result_mask |= STATX_CHANGE_COOKIE;
+		}
 	} else
 		fhp->fh_post_saved = true;
 	if (v4)
@@ -748,3 +756,37 @@ enum fsid_source fsid_source(const struct svc_fh *fhp)
 		return FSIDSOURCE_UUID;
 	return FSIDSOURCE_DEV;
 }
+
+/*
+ * We could use i_version alone as the change attribute.  However, i_version
+ * can go backwards on a regular file after an unclean shutdown.  On its own
+ * that doesn't necessarily cause a problem, but if i_version goes backwards
+ * and then is incremented again it could reuse a value that was previously
+ * used before boot, and a client who queried the two values might incorrectly
+ * assume nothing changed.
+ *
+ * By using both ctime and the i_version counter we guarantee that as long as
+ * time doesn't go backwards we never reuse an old value. If the filesystem
+ * advertises STATX_ATTR_CHANGE_MONOTONIC, then this mitigation is not
+ * needed.
+ *
+ * We only need to do this for regular files as well. For directories, we
+ * assume that the new change attr is always logged to stable storage in some
+ * fashion before the results can be seen.
+ */
+u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode)
+{
+	u64 chattr;
+
+	if (stat->result_mask & STATX_CHANGE_COOKIE) {
+		chattr = stat->change_cookie;
+		if (S_ISREG(inode->i_mode) &&
+		    !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) {
+			chattr += (u64)stat->ctime.tv_sec << 30;
+			chattr += stat->ctime.tv_nsec;
+		}
+	} else {
+		chattr = time_to_chattr(&stat->ctime);
+	}
+	return chattr;
+}
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 513e028b0bbe..4e0ecf0ae2cf 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -293,34 +293,7 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
 	fhp->fh_pre_saved = false;
 }
 
-/*
- * We could use i_version alone as the change attribute.  However,
- * i_version can go backwards after a reboot.  On its own that doesn't
- * necessarily cause a problem, but if i_version goes backwards and then
- * is incremented again it could reuse a value that was previously used
- * before boot, and a client who queried the two values might
- * incorrectly assume nothing changed.
- *
- * By using both ctime and the i_version counter we guarantee that as
- * long as time doesn't go backwards we never reuse an old value.
- */
-static inline u64 nfsd4_change_attribute(struct kstat *stat,
-					 struct inode *inode)
-{
-	if (inode->i_sb->s_export_op->fetch_iversion)
-		return inode->i_sb->s_export_op->fetch_iversion(inode);
-	else if (IS_I_VERSION(inode)) {
-		u64 chattr;
-
-		chattr =  stat->ctime.tv_sec;
-		chattr <<= 30;
-		chattr += stat->ctime.tv_nsec;
-		chattr += inode_query_iversion(inode);
-		return chattr;
-	} else
-		return time_to_chattr(&stat->ctime);
-}
-
+u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode);
 extern void fh_fill_pre_attrs(struct svc_fh *fhp);
 extern void fh_fill_post_attrs(struct svc_fh *fhp);
 extern void fh_fill_both_attrs(struct svc_fh *fhp);
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index dbdfef7ae85b..43fb57a301d3 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -170,9 +170,14 @@ static inline void fh_drop_write(struct svc_fh *fh)
 
 static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat)
 {
+	u32 request_mask = STATX_BASIC_STATS;
 	struct path p = {.mnt = fh->fh_export->ex_path.mnt,
 			 .dentry = fh->fh_dentry};
-	return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS,
+
+	if (fh->fh_maxsize == NFS4_FHSIZE)
+		request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
+
+	return nfserrno(vfs_getattr(&p, stat, request_mask,
 				    AT_STATX_SYNC_AS_STAT));
 }