Merge tag 'ceph-for-5.18-rc1' of https://github.com/ceph/ceph-client

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

   - several changes to how snap context and snap realms are tracked
     (Xiubo Li). In particular, this should resolve a long-standing
     issue of high kworker CPU usage and various stalls caused by
     needless iteration over all inodes in the snap realm.

   - async create fixes to address hangs in some edge cases (Jeff
     Layton)

   - support for getvxattr MDS op for querying server-side xattrs, such
     as file/directory layouts and ephemeral pins (Milind Changire)

   - average latency is now maintained for all metrics (Venky Shankar)

   - some tweaks around handling inline data to make it fit better with
     netfs helper library (David Howells)

  Also a couple of memory leaks got plugged along with a few assorted
  fixups. Last but not least, Xiubo has stepped up to serve as a CephFS
  co-maintainer"

* tag 'ceph-for-5.18-rc1' of https://github.com/ceph/ceph-client: (27 commits)
  ceph: fix memory leak in ceph_readdir when note_last_dentry returns error
  ceph: uninitialized variable in debug output
  ceph: use tracked average r/w/m latencies to display metrics in debugfs
  ceph: include average/stdev r/w/m latency in mds metrics
  ceph: track average r/w/m latency
  ceph: use ktime_to_timespec64() rather than jiffies_to_timespec64()
  ceph: assign the ci only when the inode isn't NULL
  ceph: fix inode reference leakage in ceph_get_snapdir()
  ceph: misc fix for code style and logs
  ceph: allocate capsnap memory outside of ceph_queue_cap_snap()
  ceph: do not release the global snaprealm until unmounting
  ceph: remove incorrect and unused CEPH_INO_DOTDOT macro
  MAINTAINERS: add Xiubo Li as cephfs co-maintainer
  ceph: eliminate the recursion when rebuilding the snap context
  ceph: do not update snapshot context when there is no new snapshot
  ceph: zero the dir_entries memory when allocating it
  ceph: move to a dedicated slabcache for ceph_cap_snap
  ceph: add getvxattr op
  libceph: drop else branches in prepare_read_data{,_cont}
  ceph: fix comments mentioning i_mutex
  ...

1 files changed, 13 insertions, 4 deletions

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 133dbd9338e7..eae417d71136 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -145,7 +145,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
 			return ERR_PTR(-EAGAIN);
 		}
 		/* reading/filling the cache are serialized by
-		   i_mutex, no need to use page lock */
+		   i_rwsem, no need to use page lock */
 		unlock_page(cache_ctl->page);
 		cache_ctl->dentries = kmap(cache_ctl->page);
 	}
@@ -155,7 +155,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
 	rcu_read_lock();
 	spin_lock(&parent->d_lock);
 	/* check i_size again here, because empty directory can be
-	 * marked as complete while not holding the i_mutex. */
+	 * marked as complete while not holding the i_rwsem. */
 	if (ceph_dir_is_complete_ordered(dir) && ptr_pos < i_size_read(dir))
 		dentry = cache_ctl->dentries[cache_ctl->index];
 	else
@@ -478,8 +478,11 @@ more:
 					2 : (fpos_off(rde->offset) + 1);
 			err = note_last_dentry(dfi, rde->name, rde->name_len,
 					       next_offset);
-			if (err)
+			if (err) {
+				ceph_mdsc_put_request(dfi->last_readdir);
+				dfi->last_readdir = NULL;
 				return err;
+			}
 		} else if (req->r_reply_info.dir_end) {
 			dfi->next_offset = 2;
 			/* keep last name */
@@ -520,6 +523,12 @@ more:
 		if (!dir_emit(ctx, rde->name, rde->name_len,
 			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
 			      le32_to_cpu(rde->inode.in->mode) >> 12)) {
+			/*
+			 * NOTE: Here no need to put the 'dfi->last_readdir',
+			 * because when dir_emit stops us it's most likely
+			 * doesn't have enough memory, etc. So for next readdir
+			 * it will continue.
+			 */
 			dout("filldir stopping us...\n");
 			return 0;
 		}
@@ -671,7 +680,7 @@ struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
 				   struct dentry *dentry)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
-	struct inode *parent = d_inode(dentry->d_parent); /* we hold i_mutex */
+	struct inode *parent = d_inode(dentry->d_parent); /* we hold i_rwsem */
 
 	/* .snap dir? */
 	if (ceph_snap(parent) == CEPH_NOSNAP &&