ceph: allow rename operation under different quota realms

Returning -EXDEV when trying to 'mv' files/directories from different
quota realms results in copy+unlink operations instead of the faster
CEPH_MDS_OP_RENAME. This will occur even when there aren't any quotas
set in the destination directory, or if there's enough space left for
the new file(s).

This patch adds a new helper function to be called on rename operations
which will allow these operations if they can be executed. This patch
mimics userland fuse client commit b8954e5734b3 ("client:
optimize rename operation under different quota root").

Since ceph_quota_is_same_realm() is now called only from this new
helper, make it static.

URL: https://tracker.ceph.com/issues/44791
Signed-off-by: Luis Henriques <[e-mail]>
Reviewed-by: Jeff Layton <[e-mail]>
Signed-off-by: Ilya Dryomov <[e-mail]>

fs/ceph/dir.c

···
 			op = CEPH_MDS_OP_RENAMESNAP;
 		else
 			return -EROFS;
+	} else if (old_dir != new_dir) {
+		err = ceph_quota_check_rename(mdsc, d_inode(old_dentry),
+					      new_dir);
+		if (err)
+			return err;
 	}
-	/* don't allow cross-quota renames */
-	if ((old_dir != new_dir) &&
-	    (!ceph_quota_is_same_realm(old_dir, new_dir)))
-		return -EXDEV;
 
 	dout("rename dir %p dentry %p to dir %p dentry %p\n",
 	     old_dir, old_dentry, new_dir, new_dentry);

fs/ceph/quota.c

···
 	return NULL;
 }
 
-bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
+static bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(old)->mdsc;
 	struct ceph_snap_realm *old_realm, *new_realm;
···
 	return is_updated;
 }
 
+/*
+ * ceph_quota_check_rename - check if a rename can be executed
+ * @mdsc:	MDS client instance
+ * @old:	inode to be copied
+ * @new:	destination inode (directory)
+ *
+ * This function verifies if a rename (e.g. moving a file or directory) can be
+ * executed.  It forces an rstat update in the @new target directory (and in the
+ * source @old as well, if it's a directory).  The actual check is done both for
+ * max_files and max_bytes.
+ *
+ * This function returns 0 if it's OK to do the rename, or, if quotas are
+ * exceeded, -EXDEV (if @old is a directory) or -EDQUOT.
+ */
+int ceph_quota_check_rename(struct ceph_mds_client *mdsc,
+			    struct inode *old, struct inode *new)
+{
+	struct ceph_inode_info *ci_old = ceph_inode(old);
+	int ret = 0;
+
+	if (ceph_quota_is_same_realm(old, new))
+		return 0;
+
+	/*
+	 * Get the latest rstat for target directory (and for source, if a
+	 * directory)
+	 */
+	ret = ceph_do_getattr(new, CEPH_STAT_RSTAT, false);
+	if (ret)
+		return ret;
+
+	if (S_ISDIR(old->i_mode)) {
+		ret = ceph_do_getattr(old, CEPH_STAT_RSTAT, false);
+		if (ret)
+			return ret;
+		ret = check_quota_exceeded(new, QUOTA_CHECK_MAX_BYTES_OP,
+					   ci_old->i_rbytes);
+		if (!ret)
+			ret = check_quota_exceeded(new,
+						   QUOTA_CHECK_MAX_FILES_OP,
+						   ci_old->i_rfiles +
+						   ci_old->i_rsubdirs);
+		if (ret)
+			ret = -EXDEV;
+	} else {
+		ret = check_quota_exceeded(new, QUOTA_CHECK_MAX_BYTES_OP,
+					   i_size_read(old));
+		if (!ret)
+			ret = check_quota_exceeded(new,
+						   QUOTA_CHECK_MAX_FILES_OP, 1);
+		if (ret)
+			ret = -EDQUOT;
+	}
+
+	return ret;
+}

fs/ceph/super.h

···
 			      struct ceph_mds_session *session,
 			      struct ceph_msg *msg);
 extern bool ceph_quota_is_max_files_exceeded(struct inode *inode);
-extern bool ceph_quota_is_same_realm(struct inode *old, struct inode *new);
 extern bool ceph_quota_is_max_bytes_exceeded(struct inode *inode,
 					     loff_t newlen);
 extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode,
 						loff_t newlen);
 extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc,
 				     struct kstatfs *buf);
+extern int ceph_quota_check_rename(struct ceph_mds_client *mdsc,
+				   struct inode *old, struct inode *new);
 extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc);
 
 #endif /* _FS_CEPH_SUPER_H */