ceph: wait for the first reply of inflight async unlink

In async unlink case the kclient won't wait for the first reply
from MDS and just drop all the links and unhash the dentry and then
succeeds immediately.

For any new create/link/rename,etc requests followed by using the
same file names we must wait for the first reply of the inflight
unlink request, or the MDS possibly will fail these following
requests with -EEXIST if the inflight async unlink request was
delayed for some reasons.

And the worst case is that for the none async openc request it will
successfully open the file if the CDentry hasn't been unlinked yet,
but later the previous delayed async unlink request will remove the
CDenty. That means the just created file is possiblly deleted later
by accident.

We need to wait for the inflight async unlink requests to finish
when creating new files/directories by using the same file names.

Link: https://tracker.ceph.com/issues/55332
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 14 insertions, 5 deletions

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f59dac66955b..59469253592b 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -19,6 +19,7 @@
 #include <linux/security.h>
 #include <linux/netfs.h>
 #include <linux/fscache.h>
+#include <linux/hashtable.h>
 
 #include <linux/ceph/libceph.h>
 
@@ -99,6 +100,8 @@ struct ceph_mount_options {
 	char *mon_addr;
 };
 
+#define CEPH_ASYNC_CREATE_CONFLICT_BITS 8
+
 struct ceph_fs_client {
 	struct super_block *sb;
 
@@ -124,6 +127,9 @@ struct ceph_fs_client {
 	struct workqueue_struct *inode_wq;
 	struct workqueue_struct *cap_wq;
 
+	DECLARE_HASHTABLE(async_unlink_conflict, CEPH_ASYNC_CREATE_CONFLICT_BITS);
+	spinlock_t async_unlink_conflict_lock;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
@@ -280,7 +286,8 @@ struct ceph_dentry_info {
 	struct dentry *dentry;
 	struct ceph_mds_session *lease_session;
 	struct list_head lease_list;
-	unsigned flags;
+	struct hlist_node hnode;
+	unsigned long flags;
 	int lease_shared_gen;
 	u32 lease_gen;
 	u32 lease_seq;
@@ -289,10 +296,12 @@ struct ceph_dentry_info {
 	u64 offset;
 };
 
-#define CEPH_DENTRY_REFERENCED		1
-#define CEPH_DENTRY_LEASE_LIST		2
-#define CEPH_DENTRY_SHRINK_LIST		4
-#define CEPH_DENTRY_PRIMARY_LINK	8
+#define CEPH_DENTRY_REFERENCED		(1 << 0)
+#define CEPH_DENTRY_LEASE_LIST		(1 << 1)
+#define CEPH_DENTRY_SHRINK_LIST		(1 << 2)
+#define CEPH_DENTRY_PRIMARY_LINK	(1 << 3)
+#define CEPH_DENTRY_ASYNC_UNLINK_BIT	(4)
+#define CEPH_DENTRY_ASYNC_UNLINK	(1 << CEPH_DENTRY_ASYNC_UNLINK_BIT)
 
 struct ceph_inode_xattrs_info {
 	/*