Merge tag 'ceph-for-5.8-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The highlights are:

   - OSD/MDS latency and caps cache metrics infrastructure for the
     filesytem (Xiubo Li). Currently available through debugfs and will
     be periodically sent to the MDS in the future.

   - support for replica reads (balanced and localized reads) for rbd
     and the filesystem (myself). The default remains to always read
     from primary, users can opt-in with the new crush_location and
     read_from_replica options. Note that reading from replica is safe
     for general use only since Octopus.

   - support for RADOS allocation hint flags (myself). Currently used by
     rbd to propagate the compressible/incompressible hint given with
     the new compression_hint map option and ready for passing on more
     advanced hints, e.g. based on fadvise() from the filesystem.

   - support for efficient cross-quota-realm renames (Luis Henriques)

   - assorted cap handling improvements and cleanups, particularly
     untangling some of the locking (Jeff Layton)"

* tag 'ceph-for-5.8-rc1' of git://github.com/ceph/ceph-client: (29 commits)
  rbd: compression_hint option
  libceph: support for alloc hint flags
  libceph: read_from_replica option
  libceph: support for balanced and localized reads
  libceph: crush_location infrastructure
  libceph: decode CRUSH device/bucket types and names
  libceph: add non-asserting rbtree insertion helper
  ceph: skip checking caps when session reconnecting and releasing reqs
  ceph: make sure mdsc->mutex is nested in s->s_mutex to fix dead lock
  ceph: don't return -ESTALE if there's still an open file
  libceph, rbd: replace zero-length array with flexible-array
  ceph: allow rename operation under different quota realms
  ceph: normalize 'delta' parameter usage in check_quota_exceeded
  ceph: ceph_kick_flushing_caps needs the s_mutex
  ceph: request expedited service on session's last cap flush
  ceph: convert mdsc->cap_dirty to a per-session list
  ceph: reset i_requested_max_size if file write is not wanted
  ceph: throw a warning if we destroy session with mutex still locked
  ceph: fix potential race in ceph_check_caps
  ceph: document what protects i_dirty_item and i_flushing_item
  ...

1 files changed, 58 insertions, 4 deletions

diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 19507e2fdb57..198ddde5c1e6 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -264,7 +264,7 @@ restart:
 	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;
@@ -361,8 +361,6 @@ restart:
 		spin_unlock(&ci->i_ceph_lock);
 		switch (op) {
 		case QUOTA_CHECK_MAX_FILES_OP:
-			exceeded = (max && (rvalue >= max));
-			break;
 		case QUOTA_CHECK_MAX_BYTES_OP:
 			exceeded = (max && (rvalue + delta > max));
 			break;
@@ -417,7 +415,7 @@ bool ceph_quota_is_max_files_exceeded(struct inode *inode)
 
 	WARN_ON(!S_ISDIR(inode->i_mode));
 
-	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_FILES_OP, 0);
+	return check_quota_exceeded(inode, QUOTA_CHECK_MAX_FILES_OP, 1);
 }
 
 /*
@@ -518,3 +516,59 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
 	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;
+}