Merge tag 'ceph-for-5.20-rc1' of https://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "We have a good pile of various fixes and cleanups from Xiubo, Jeff,
  Luis and others, almost exclusively in the filesystem.

  Several patches touch files outside of our normal purview to set the
  stage for bringing in Jeff's long awaited ceph+fscrypt series in the
  near future. All of them have appropriate acks and sat in linux-next
  for a while"

* tag 'ceph-for-5.20-rc1' of https://github.com/ceph/ceph-client: (27 commits)
  libceph: clean up ceph_osdc_start_request prototype
  libceph: fix ceph_pagelist_reserve() comment typo
  ceph: remove useless check for the folio
  ceph: don't truncate file in atomic_open
  ceph: make f_bsize always equal to f_frsize
  ceph: flush the dirty caps immediatelly when quota is approaching
  libceph: print fsid and epoch with osd id
  libceph: check pointer before assigned to "c->rules[]"
  ceph: don't get the inline data for new creating files
  ceph: update the auth cap when the async create req is forwarded
  ceph: make change_auth_cap_ses a global symbol
  ceph: fix incorrect old_size length in ceph_mds_request_args
  ceph: switch back to testing for NULL folio->private in ceph_dirty_folio
  ceph: call netfs_subreq_terminated with was_async == false
  ceph: convert to generic_file_llseek
  ceph: fix the incorrect comment for the ceph_mds_caps struct
  ceph: don't leak snap_rwsem in handle_cap_grant
  ceph: prevent a client from exceeding the MDS maximum xattr size
  ceph: choose auth MDS for getxattr with the Xs caps
  ceph: add session already open notify support
  ...

11 files changed, 397 insertions, 177 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 2c3a9b5b4b74..dcf701b05cc1 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -122,7 +122,7 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio)
 	 * Reference snap context in folio->private.  Also set
 	 * PagePrivate so that we get invalidate_folio callback.
 	 */
-	VM_BUG_ON_FOLIO(folio_test_private(folio), folio);
+	VM_WARN_ON_FOLIO(folio->private, folio);
 	folio_attach_private(folio, snapc);
 
 	return ceph_fscache_dirty_folio(mapping, folio);
@@ -237,7 +237,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	if (err >= 0 && err < subreq->len)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 
-	netfs_subreq_terminated(subreq, err, true);
+	netfs_subreq_terminated(subreq, err, false);
 
 	num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
 	ceph_put_page_vector(osd_data->pages, num_pages, false);
@@ -313,8 +313,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	int err = 0;
 	u64 len = subreq->len;
 
-	if (ci->i_inline_version != CEPH_INLINE_NONE &&
-	    ceph_netfs_issue_op_inline(subreq))
+	if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
 		return;
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
@@ -338,6 +337,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	/* should always give us a page-aligned read */
 	WARN_ON_ONCE(page_off);
 	len = err;
+	err = 0;
 
 	osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
 	req->r_callback = finish_netfs_read;
@@ -345,9 +345,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	req->r_inode = inode;
 	ihold(inode);
 
-	err = ceph_osdc_start_request(req->r_osdc, req, false);
-	if (err)
-		iput(inode);
+	ceph_osdc_start_request(req->r_osdc, req);
 out:
 	ceph_osdc_put_request(req);
 	if (err)
@@ -621,9 +619,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(osdc, req, true);
-	if (!err)
-		err = ceph_osdc_wait_request(osdc, req);
+	ceph_osdc_start_request(osdc, req);
+	err = ceph_osdc_wait_request(osdc, req);
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
@@ -1151,8 +1148,7 @@ new_request:
 		}
 
 		req->r_mtime = inode->i_mtime;
-		rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
-		BUG_ON(rc);
+		ceph_osdc_start_request(&fsc->client->osdc, req);
 		req = NULL;
 
 		wbc->nr_to_write -= i;
@@ -1327,16 +1323,13 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 	int r;
 
 	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
-	if (r == 0)
-		folio_wait_fscache(folio);
-	if (r < 0) {
-		if (folio)
-			folio_put(folio);
-	} else {
-		WARN_ON_ONCE(!folio_test_locked(folio));
-		*pagep = &folio->page;
-	}
-	return r;
+	if (r < 0)
+		return r;
+
+	folio_wait_fscache(folio);
+	WARN_ON_ONCE(!folio_test_locked(folio));
+	*pagep = &folio->page;
+	return 0;
 }
 
 /*
@@ -1439,7 +1432,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	     inode, off, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
-	    ci->i_inline_version == CEPH_INLINE_NONE) {
+	    !ceph_has_inline_data(ci)) {
 		CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
 		ceph_add_rw_context(fi, &rw_ctx);
 		ret = filemap_fault(vmf);
@@ -1696,9 +1689,8 @@ int ceph_uninline_data(struct file *file)
 	}
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 	ceph_osdc_put_request(req);
 	if (err < 0)
 		goto out_unlock;
@@ -1739,9 +1731,8 @@ int ceph_uninline_data(struct file *file)
 	}
 
 	req->r_mtime = inode->i_mtime;
-	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
 	ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 				  req->r_end_latency, len, err);
@@ -1912,15 +1903,13 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 
 	osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
 				     0, false, true);
-	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
+	ceph_osdc_start_request(&fsc->client->osdc, rd_req);
 
 	wr_req->r_mtime = ci->netfs.inode.i_mtime;
-	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
+	ceph_osdc_start_request(&fsc->client->osdc, wr_req);
 
-	if (!err)
-		err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
-	if (!err2)
-		err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
+	err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
+	err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
 
 	if (err >= 0 || err == -ENOENT)
 		have |= POOL_READ;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ac8fd5e7f540..53cfe026b3ea 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -602,8 +602,8 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
  * @ci: inode to be moved
  * @session: new auth caps session
  */
-static void change_auth_cap_ses(struct ceph_inode_info *ci,
-				struct ceph_mds_session *session)
+void change_auth_cap_ses(struct ceph_inode_info *ci,
+			 struct ceph_mds_session *session)
 {
 	lockdep_assert_held(&ci->i_ceph_lock);
 
@@ -1978,14 +1978,15 @@ retry:
 	}
 
 	dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s"
-	     " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode),
+	     " issued %s revoking %s retain %s %s%s%s\n", ceph_vinop(inode),
 	     ceph_cap_string(file_wanted),
 	     ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
 	     ceph_cap_string(ci->i_flushing_caps),
 	     ceph_cap_string(issued), ceph_cap_string(revoking),
 	     ceph_cap_string(retain),
 	     (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
-	     (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "");
+	     (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "",
+	     (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "");
 
 	/*
 	 * If we no longer need to hold onto old our caps, and we may
@@ -3005,7 +3006,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 		}
 
 		if (S_ISREG(ci->netfs.inode.i_mode) &&
-		    ci->i_inline_version != CEPH_INLINE_NONE &&
+		    ceph_has_inline_data(ci) &&
 		    (_got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
 		    i_size_read(inode) > 0) {
 			struct page *page =
@@ -3578,24 +3579,23 @@ static void handle_cap_grant(struct inode *inode,
 			fill_inline = true;
 	}
 
-	if (ci->i_auth_cap == cap &&
-	    le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
-		if (newcaps & ~extra_info->issued)
-			wake = true;
+	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+		if (ci->i_auth_cap == cap) {
+			if (newcaps & ~extra_info->issued)
+				wake = true;
 
-		if (ci->i_requested_max_size > max_size ||
-		    !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) {
-			/* re-request max_size if necessary */
-			ci->i_requested_max_size = 0;
-			wake = true;
-		}
+			if (ci->i_requested_max_size > max_size ||
+			    !(le32_to_cpu(grant->wanted) & CEPH_CAP_ANY_FILE_WR)) {
+				/* re-request max_size if necessary */
+				ci->i_requested_max_size = 0;
+				wake = true;
+			}
 
-		ceph_kick_flushing_inode_caps(session, ci);
-		spin_unlock(&ci->i_ceph_lock);
+			ceph_kick_flushing_inode_caps(session, ci);
+		}
 		up_read(&session->s_mdsc->snap_rwsem);
-	} else {
-		spin_unlock(&ci->i_ceph_lock);
 	}
+	spin_unlock(&ci->i_ceph_lock);
 
 	if (fill_inline)
 		ceph_fill_inline_data(inode, NULL, extra_info->inline_data,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index eae417d71136..e7e2ebac330d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -856,6 +856,10 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		return -EROFS;
 
+	err = ceph_wait_on_conflict_unlink(dentry);
+	if (err)
+		return err;
+
 	if (ceph_quota_is_max_files_exceeded(dir)) {
 		err = -EDQUOT;
 		goto out;
@@ -918,6 +922,10 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		return -EROFS;
 
+	err = ceph_wait_on_conflict_unlink(dentry);
+	if (err)
+		return err;
+
 	if (ceph_quota_is_max_files_exceeded(dir)) {
 		err = -EDQUOT;
 		goto out;
@@ -968,9 +976,13 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
 	struct ceph_mds_request *req;
 	struct ceph_acl_sec_ctx as_ctx = {};
-	int err = -EROFS;
+	int err;
 	int op;
 
+	err = ceph_wait_on_conflict_unlink(dentry);
+	if (err)
+		return err;
+
 	if (ceph_snap(dir) == CEPH_SNAPDIR) {
 		/* mkdir .snap/foo is a MKSNAP */
 		op = CEPH_MDS_OP_MKSNAP;
@@ -980,6 +992,7 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 		dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode);
 		op = CEPH_MDS_OP_MKDIR;
 	} else {
+		err = -EROFS;
 		goto out;
 	}
 
@@ -1037,6 +1050,10 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	struct ceph_mds_request *req;
 	int err;
 
+	err = ceph_wait_on_conflict_unlink(dentry);
+	if (err)
+		return err;
+
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		return -EROFS;
 
@@ -1071,9 +1088,27 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 				 struct ceph_mds_request *req)
 {
+	struct dentry *dentry = req->r_dentry;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	int result = req->r_err ? req->r_err :
 			le32_to_cpu(req->r_reply_info.head->result);
 
+	if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags))
+		pr_warn("%s dentry %p:%pd async unlink bit is not set\n",
+			__func__, dentry, dentry);
+
+	spin_lock(&fsc->async_unlink_conflict_lock);
+	hash_del_rcu(&di->hnode);
+	spin_unlock(&fsc->async_unlink_conflict_lock);
+
+	spin_lock(&dentry->d_lock);
+	di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK;
+	wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT);
+	spin_unlock(&dentry->d_lock);
+
+	synchronize_rcu();
+
 	if (result == -EJUKEBOX)
 		goto out;
 
@@ -1081,7 +1116,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 	if (result) {
 		int pathlen = 0;
 		u64 base = 0;
-		char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
+		char *path = ceph_mdsc_build_path(dentry, &pathlen,
 						  &base, 0);
 
 		/* mark error on parent + clear complete */
@@ -1089,13 +1124,13 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 		ceph_dir_clear_complete(req->r_parent);
 
 		/* drop the dentry -- we don't know its status */
-		if (!d_unhashed(req->r_dentry))
-			d_drop(req->r_dentry);
+		if (!d_unhashed(dentry))
+			d_drop(dentry);
 
 		/* mark inode itself for an error (since metadata is bogus) */
 		mapping_set_error(req->r_old_inode->i_mapping, result);
 
-		pr_warn("ceph: async unlink failure path=(%llx)%s result=%d!\n",
+		pr_warn("async unlink failure path=(%llx)%s result=%d!\n",
 			base, IS_ERR(path) ? "<<bad>>" : path, result);
 		ceph_mdsc_free_path(path, pathlen);
 	}
@@ -1180,6 +1215,8 @@ retry:
 
 	if (try_async && op == CEPH_MDS_OP_UNLINK &&
 	    (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) {
+		struct ceph_dentry_info *di = ceph_dentry(dentry);
+
 		dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir),
 		     dentry->d_name.len, dentry->d_name.name,
 		     ceph_cap_string(req->r_dir_caps));
@@ -1187,6 +1224,16 @@ retry:
 		req->r_callback = ceph_async_unlink_cb;
 		req->r_old_inode = d_inode(dentry);
 		ihold(req->r_old_inode);
+
+		spin_lock(&dentry->d_lock);
+		di->flags |= CEPH_DENTRY_ASYNC_UNLINK;
+		spin_unlock(&dentry->d_lock);
+
+		spin_lock(&fsc->async_unlink_conflict_lock);
+		hash_add_rcu(fsc->async_unlink_conflict, &di->hnode,
+			     dentry->d_name.hash);
+		spin_unlock(&fsc->async_unlink_conflict_lock);
+
 		err = ceph_mdsc_submit_request(mdsc, dir, req);
 		if (!err) {
 			/*
@@ -1195,10 +1242,20 @@ retry:
 			 */
 			drop_nlink(inode);
 			d_delete(dentry);
-		} else if (err == -EJUKEBOX) {
-			try_async = false;
-			ceph_mdsc_put_request(req);
-			goto retry;
+		} else {
+			spin_lock(&fsc->async_unlink_conflict_lock);
+			hash_del_rcu(&di->hnode);
+			spin_unlock(&fsc->async_unlink_conflict_lock);
+
+			spin_lock(&dentry->d_lock);
+			di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK;
+			spin_unlock(&dentry->d_lock);
+
+			if (err == -EJUKEBOX) {
+				try_async = false;
+				ceph_mdsc_put_request(req);
+				goto retry;
+			}
 		}
 	} else {
 		set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
@@ -1237,6 +1294,10 @@ static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 	    (!ceph_quota_is_same_realm(old_dir, new_dir)))
 		return -EXDEV;
 
+	err = ceph_wait_on_conflict_unlink(new_dentry);
+	if (err)
+		return err;
+
 	dout("rename dir %p dentry %p to dir %p dentry %p\n",
 	     old_dir, old_dentry, new_dir, new_dentry);
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 284d2fda663d..04fd34557de8 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -240,8 +240,7 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
 	INIT_LIST_HEAD(&fi->rw_contexts);
 	fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
 
-	if ((file->f_mode & FMODE_WRITE) &&
-	    ci->i_inline_version != CEPH_INLINE_NONE) {
+	if ((file->f_mode & FMODE_WRITE) && ceph_has_inline_data(ci)) {
 		ret = ceph_uninline_data(file);
 		if (ret < 0)
 			goto error;
@@ -568,7 +567,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 		char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
 						  &base, 0);
 
-		pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n",
+		pr_warn("async create failure path=(%llx)%s result=%d!\n",
 			base, IS_ERR(path) ? "<<bad>>" : path, result);
 		ceph_mdsc_free_path(path, pathlen);
 
@@ -611,6 +610,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_reply_inode in = { };
 	struct ceph_mds_reply_info_in iinfo = { .in = &in };
 	struct ceph_inode_info *ci = ceph_inode(dir);
+	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	struct inode *inode;
 	struct timespec64 now;
 	struct ceph_string *pool_ns;
@@ -709,6 +709,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 		file->f_mode |= FMODE_CREATED;
 		ret = finish_open(file, dentry, ceph_open);
 	}
+
+	spin_lock(&dentry->d_lock);
+	di->flags &= ~CEPH_DENTRY_ASYNC_CREATE;
+	wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT);
+	spin_unlock(&dentry->d_lock);
+
 	return ret;
 }
 
@@ -735,6 +741,15 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (dentry->d_name.len > NAME_MAX)
 		return -ENAMETOOLONG;
 
+	err = ceph_wait_on_conflict_unlink(dentry);
+	if (err)
+		return err;
+	/*
+	 * Do not truncate the file, since atomic_open is called before the
+	 * permission check. The caller will do the truncation afterward.
+	 */
+	flags &= ~O_TRUNC;
+
 	if (flags & O_CREAT) {
 		if (ceph_quota_is_max_files_exceeded(dir))
 			return -EDQUOT;
@@ -781,9 +796,16 @@ retry:
 		    (req->r_dir_caps =
 		      try_prep_async_create(dir, dentry, &lo,
 					    &req->r_deleg_ino))) {
+			struct ceph_dentry_info *di = ceph_dentry(dentry);
+
 			set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
 			req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL);
 			req->r_callback = ceph_async_create_cb;
+
+			spin_lock(&dentry->d_lock);
+			di->flags |= CEPH_DENTRY_ASYNC_CREATE;
+			spin_unlock(&dentry->d_lock);
+
 			err = ceph_mdsc_submit_request(mdsc, dir, req);
 			if (!err) {
 				err = ceph_finish_async_create(dir, dentry,
@@ -802,9 +824,7 @@ retry:
 	}
 
 	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
-	err = ceph_mdsc_do_request(mdsc,
-				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
-				   req);
+	err = ceph_mdsc_do_request(mdsc, (flags & O_CREAT) ? dir : NULL, req);
 	if (err == -ENOENT) {
 		dentry = ceph_handle_snapdir(req, dentry);
 		if (IS_ERR(dentry)) {
@@ -960,9 +980,8 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 
 		osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
 						 false, false);
-		ret = ceph_osdc_start_request(osdc, req, false);
-		if (!ret)
-			ret = ceph_osdc_wait_request(osdc, req);
+		ceph_osdc_start_request(osdc, req);
+		ret = ceph_osdc_wait_request(osdc, req);
 
 		ceph_update_read_metrics(&fsc->mdsc->metric,
 					 req->r_start_latency,
@@ -1225,7 +1244,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
 	req->r_inode = inode;
 	req->r_priv = aio_req;
 
-	ret = ceph_osdc_start_request(req->r_osdc, req, false);
+	ceph_osdc_start_request(req->r_osdc, req);
 out:
 	if (ret < 0) {
 		req->r_result = ret;
@@ -1362,9 +1381,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 			continue;
 		}
 
-		ret = ceph_osdc_start_request(req->r_osdc, req, false);
-		if (!ret)
-			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+		ceph_osdc_start_request(req->r_osdc, req);
+		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
 		if (write)
 			ceph_update_write_metrics(metric, req->r_start_latency,
@@ -1427,8 +1445,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 					       r_private_item);
 			list_del_init(&req->r_private_item);
 			if (ret >= 0)
-				ret = ceph_osdc_start_request(req->r_osdc,
-							      req, false);
+				ceph_osdc_start_request(req->r_osdc, req);
 			if (ret < 0) {
 				req->r_result = ret;
 				ceph_aio_complete_req(req);
@@ -1541,9 +1558,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 						false, true);
 
 		req->r_mtime = mtime;
-		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-		if (!ret)
-			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+		ceph_osdc_start_request(&fsc->client->osdc, req);
+		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 
 		ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
 					  req->r_end_latency, len, ret);
@@ -1627,7 +1643,7 @@ again:
 		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
 		     ceph_cap_string(got));
 
-		if (ci->i_inline_version == CEPH_INLINE_NONE) {
+		if (!ceph_has_inline_data(ci)) {
 			if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
 				ret = ceph_direct_read_write(iocb, to,
 							     NULL, NULL);
@@ -1890,7 +1906,7 @@ retry_snap:
 		if (dirty)
 			__mark_inode_dirty(inode, dirty);
 		if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
-			ceph_check_caps(ci, 0, NULL);
+			ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
 	}
 
 	dout("aio_write %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
@@ -1930,57 +1946,15 @@ out_unlocked:
  */
 static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 {
-	struct inode *inode = file->f_mapping->host;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	loff_t i_size;
-	loff_t ret;
-
-	inode_lock(inode);
-
 	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
+		struct inode *inode = file_inode(file);
+		int ret;
+
 		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
 		if (ret < 0)
-			goto out;
-	}
-
-	i_size = i_size_read(inode);
-	switch (whence) {
-	case SEEK_END:
-		offset += i_size;
-		break;
-	case SEEK_CUR:
-		/*
-		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
-		 * position-querying operation.  Avoid rewriting the "same"
-		 * f_pos value back to the file because a concurrent read(),
-		 * write() or lseek() might have altered it
-		 */
-		if (offset == 0) {
-			ret = file->f_pos;
-			goto out;
-		}
-		offset += file->f_pos;
-		break;
-	case SEEK_DATA:
-		if (offset < 0 || offset >= i_size) {
-			ret = -ENXIO;
-			goto out;
-		}
-		break;
-	case SEEK_HOLE:
-		if (offset < 0 || offset >= i_size) {
-			ret = -ENXIO;
-			goto out;
-		}
-		offset = i_size;
-		break;
+			return ret;
 	}
-
-	ret = vfs_setpos(file, offset, max(i_size, fsc->max_file_size));
-
-out:
-	inode_unlock(inode);
-	return ret;
+	return generic_file_llseek(file, offset, whence);
 }
 
 static inline void ceph_zero_partial_page(
@@ -2049,12 +2023,10 @@ static int ceph_zero_partial_object(struct inode *inode,
 	}
 
 	req->r_mtime = inode->i_mtime;
-	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
-	if (!ret) {
-		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
-		if (ret == -ENOENT)
-			ret = 0;
-	}
+	ceph_osdc_start_request(&fsc->client->osdc, req);
+	ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+	if (ret == -ENOENT)
+		ret = 0;
 	ceph_osdc_put_request(req);
 
 out:
@@ -2356,7 +2328,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 		if (IS_ERR(req))
 			ret = PTR_ERR(req);
 		else {
-			ceph_osdc_start_request(osdc, req, false);
+			ceph_osdc_start_request(osdc, req);
 			ret = ceph_osdc_wait_request(osdc, req);
 			ceph_update_copyfrom_metrics(&fsc->mdsc->metric,
 						     req->r_start_latency,
@@ -2549,7 +2521,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 		/* Let the MDS know about dst file size change */
 		if (ceph_inode_set_size(dst_inode, dst_off) ||
 		    ceph_quota_is_max_bytes_approaching(dst_inode, dst_off))
-			ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY, NULL);
+			ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_FLUSH,
+					NULL);
 	}
 	/* Mark Fw dirty */
 	spin_lock(&dst_ci->i_ceph_lock);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 56c53ab3618e..42351d7a0dd6 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1049,7 +1049,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	    iinfo->inline_version >= ci->i_inline_version) {
 		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
 		ci->i_inline_version = iinfo->inline_version;
-		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		if (ceph_has_inline_data(ci) &&
 		    (locked_page || (info_caps & cache_caps)))
 			fill_inline = true;
 	}
@@ -2275,9 +2275,15 @@ int ceph_try_to_choose_auth_mds(struct inode *inode, int mask)
 	 *
 	 * This cost much when doing the Locker state transition and
 	 * usually will need to revoke caps from clients.
+	 *
+	 * And for the 'Xs' caps for getxattr we will also choose the
+	 * auth MDS, because the MDS side code is buggy due to setxattr
+	 * won't notify the replica MDSes when the values changed and
+	 * the replica MDS will return the old values. Though we will
+	 * fix it in MDS code, but this still makes sense for old ceph.
 	 */
 	if (((mask & CEPH_CAP_ANY_SHARED) && (issued & CEPH_CAP_ANY_EXCL))
-	    || (mask & CEPH_STAT_RSTAT))
+	    || (mask & (CEPH_STAT_RSTAT | CEPH_STAT_CAP_XATTR)))
 		return USE_AUTH_MDS;
 	else
 		return USE_ANY_MDS;
@@ -2321,7 +2327,8 @@ int __ceph_do_getattr(struct inode *inode, struct page *locked_page,
 		if (inline_version == 0) {
 			/* the reply is supposed to contain inline data */
 			err = -EINVAL;
-		} else if (inline_version == CEPH_INLINE_NONE) {
+		} else if (inline_version == CEPH_INLINE_NONE ||
+			   inline_version == 1) {
 			err = -ENODATA;
 		} else {
 			err = req->r_reply_info.targeti.inline_len;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 33f517d549ce..80f8b9ec1a31 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -456,7 +456,7 @@ static int ceph_parse_deleg_inos(void **p, void *end,
 				dout("added delegated inode 0x%llx\n",
 				     start - 1);
 			} else if (err == -EBUSY) {
-				pr_warn("ceph: MDS delegated inode 0x%llx more than once.\n",
+				pr_warn("MDS delegated inode 0x%llx more than once.\n",
 					start - 1);
 			} else {
 				return err;
@@ -655,6 +655,79 @@ static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
 	free_pages((unsigned long)info->dir_entries, get_order(info->dir_buf_size));
 }
 
+/*
+ * 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.
+ */
+int ceph_wait_on_conflict_unlink(struct dentry *dentry)
+{
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct dentry *pdentry = dentry->d_parent;
+	struct dentry *udentry, *found = NULL;
+	struct ceph_dentry_info *di;
+	struct qstr dname;
+	u32 hash = dentry->d_name.hash;
+	int err;
+
+	dname.name = dentry->d_name.name;
+	dname.len = dentry->d_name.len;
+
+	rcu_read_lock();
+	hash_for_each_possible_rcu(fsc->async_unlink_conflict, di,
+				   hnode, hash) {
+		udentry = di->dentry;
+
+		spin_lock(&udentry->d_lock);
+		if (udentry->d_name.hash != hash)
+			goto next;
+		if (unlikely(udentry->d_parent != pdentry))
+			goto next;
+		if (!hash_hashed(&di->hnode))
+			goto next;
+
+		if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags))
+			pr_warn("%s dentry %p:%pd async unlink bit is not set\n",
+				__func__, dentry, dentry);
+
+		if (!d_same_name(udentry, pdentry, &dname))
+			goto next;
+
+		spin_unlock(&udentry->d_lock);
+		found = dget(udentry);
+		break;
+next:
+		spin_unlock(&udentry->d_lock);
+	}
+	rcu_read_unlock();
+
+	if (likely(!found))
+		return 0;
+
+	dout("%s dentry %p:%pd conflict with old %p:%pd\n", __func__,
+	     dentry, dentry, found, found);
+
+	err = wait_on_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT,
+			  TASK_KILLABLE);
+	dput(found);
+	return err;
+}
+
 
 /*
  * sessions
@@ -1220,14 +1293,17 @@ static int encode_supported_features(void **p, void *end)
 	if (count > 0) {
 		size_t i;
 		size_t size = FEATURE_BYTES(count);
+		unsigned long bit;
 
 		if (WARN_ON_ONCE(*p + 4 + size > end))
 			return -ERANGE;
 
 		ceph_encode_32(p, size);
 		memset(*p, 0, size);
-		for (i = 0; i < count; i++)
-			((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8);
+		for (i = 0; i < count; i++) {
+			bit = feature_bits[i];
+			((unsigned char *)(*p))[bit / 8] |= BIT(bit % 8);
+		}
 		*p += size;
 	} else {
 		if (WARN_ON_ONCE(*p + 4 > end))
@@ -2884,6 +2960,64 @@ static void __do_request(struct ceph_mds_client *mdsc,
 	if (req->r_request_started == 0)   /* note request start time */
 		req->r_request_started = jiffies;
 
+	/*
+	 * For async create we will choose the auth MDS of frag in parent
+	 * directory to send the request and ususally this works fine, but
+	 * if the migrated the dirtory to another MDS before it could handle
+	 * it the request will be forwarded.
+	 *
+	 * And then the auth cap will be changed.
+	 */
+	if (test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) && req->r_num_fwd) {
+		struct ceph_dentry_info *di = ceph_dentry(req->r_dentry);
+		struct ceph_inode_info *ci;
+		struct ceph_cap *cap;
+
+		/*
+		 * The request maybe handled very fast and the new inode
+		 * hasn't been linked to the dentry yet. We need to wait
+		 * for the ceph_finish_async_create(), which shouldn't be
+		 * stuck too long or fail in thoery, to finish when forwarding
+		 * the request.
+		 */
+		if (!d_inode(req->r_dentry)) {
+			err = wait_on_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT,
+					  TASK_KILLABLE);
+			if (err) {
+				mutex_lock(&req->r_fill_mutex);
+				set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
+				mutex_unlock(&req->r_fill_mutex);
+				goto out_session;
+			}
+		}
+
+		ci = ceph_inode(d_inode(req->r_dentry));
+
+		spin_lock(&ci->i_ceph_lock);
+		cap = ci->i_auth_cap;
+		if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE && mds != cap->mds) {
+			dout("do_request session changed for auth cap %d -> %d\n",
+			     cap->session->s_mds, session->s_mds);
+
+			/* Remove the auth cap from old session */
+			spin_lock(&cap->session->s_cap_lock);
+			cap->session->s_nr_caps--;
+			list_del_init(&cap->session_caps);
+			spin_unlock(&cap->session->s_cap_lock);
+
+			/* Add the auth cap to the new session */
+			cap->mds = mds;
+			cap->session = session;
+			spin_lock(&session->s_cap_lock);
+			session->s_nr_caps++;
+			list_add_tail(&cap->session_caps, &session->s_caps);
+			spin_unlock(&session->s_cap_lock);
+
+			change_auth_cap_ses(ci, session);
+		}
+		spin_unlock(&ci->i_ceph_lock);
+	}
+
 	err = __send_request(session, req, false);
 
 out_session:
@@ -3464,11 +3598,26 @@ static void handle_session(struct ceph_mds_session *session,
 	case CEPH_SESSION_OPEN:
 		if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
 			pr_info("mds%d reconnect success\n", session->s_mds);
-		session->s_state = CEPH_MDS_SESSION_OPEN;
-		session->s_features = features;
-		renewed_caps(mdsc, session, 0);
-		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features))
-			metric_schedule_delayed(&mdsc->metric);
+
+		if (session->s_state == CEPH_MDS_SESSION_OPEN) {
+			pr_notice("mds%d is already opened\n", session->s_mds);
+		} else {
+			session->s_state = CEPH_MDS_SESSION_OPEN;
+			session->s_features = features;
+			renewed_caps(mdsc, session, 0);
+			if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT,
+				     &session->s_features))
+				metric_schedule_delayed(&mdsc->metric);
+		}
+
+		/*
+		 * The connection maybe broken and the session in client
+		 * side has been reinitialized, need to update the seq
+		 * anyway.
+		 */
+		if (!session->s_seq && seq)
+			session->s_seq = seq;
+
 		wake = 1;
 		if (mdsc->stopping)
 			__close_session(mdsc, session);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 1140aecd82ce..256e3eada6c1 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -29,14 +29,12 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MULTI_RECONNECT,
 	CEPHFS_FEATURE_DELEG_INO,
 	CEPHFS_FEATURE_METRIC_COLLECT,
+	CEPHFS_FEATURE_ALTERNATE_NAME,
+	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,
 
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_NOTIFY_SESSION_STATE,
 };
 
-/*
- * This will always have the highest feature bit value
- * as the last element of the array.
- */
 #define CEPHFS_FEATURES_CLIENT_SUPPORTED {	\
 	0, 1, 2, 3, 4, 5, 6, 7,			\
 	CEPHFS_FEATURE_MIMIC,			\
@@ -45,10 +43,8 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
 	CEPHFS_FEATURE_METRIC_COLLECT,		\
-						\
-	CEPHFS_FEATURE_MAX,			\
+	CEPHFS_FEATURE_NOTIFY_SESSION_STATE,	\
 }
-#define CEPHFS_FEATURES_CLIENT_REQUIRED {}
 
 /*
  * Some lock dependencies:
@@ -582,6 +578,7 @@ static inline int ceph_wait_on_async_create(struct inode *inode)
 			   TASK_KILLABLE);
 }
 
+extern int ceph_wait_on_conflict_unlink(struct dentry *dentry);
 extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session);
 extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino);
 #endif
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 30387733765d..8d0a6d2c2da4 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -352,12 +352,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 		__decode_and_drop_type(p, end, u8, bad_ext);
 	}
 	if (mdsmap_ev >= 8) {
-		u32 name_len;
 		/* enabled */
 		ceph_decode_8_safe(p, end, m->m_enabled, bad_ext);
-		ceph_decode_32_safe(p, end, name_len, bad_ext);
-		ceph_decode_need(p, end, name_len, bad_ext);
-		*p += name_len;
+		/* fs_name */
+		ceph_decode_skip_string(p, end, bad_ext);
 	}
 	/* damaged */
 	if (mdsmap_ev >= 9) {
@@ -370,6 +368,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 	} else {
 		m->m_damaged = false;
 	}
+	if (mdsmap_ev >= 17) {
+		/* balancer */
+		ceph_decode_skip_string(p, end, bad_ext);
+		/* standby_count_wanted */
+		ceph_decode_skip_32(p, end, bad_ext);
+		/* old_max_mds */
+		ceph_decode_skip_32(p, end, bad_ext);
+		/* min_compat_client */
+		ceph_decode_skip_8(p, end, bad_ext);
+		/* required_client_features */
+		ceph_decode_skip_set(p, end, 64, bad_ext);
+		ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext);
+	} else {
+		/* This forces the usage of the (sync) SETXATTR Op */
+		m->m_max_xattr_size = 0;
+	}
 bad_ext:
 	dout("mdsmap_decode m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
 	     !!m->m_enabled, !!m->m_damaged, m->m_num_laggy);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 40140805bdcf..3fc48b43cab0 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -72,15 +72,9 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_type = CEPH_SUPER_MAGIC;  /* ?? */
 
 	/*
-	 * express utilization in terms of large blocks to avoid
+	 * Express utilization in terms of large blocks to avoid
 	 * overflow on 32-bit machines.
-	 *
-	 * NOTE: for the time being, we make bsize == frsize to humor
-	 * not-yet-ancient versions of glibc that are broken.
-	 * Someday, we will probably want to report a real block
-	 * size...  whatever that may mean for a network file system!
 	 */
-	buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
 	buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
 
 	/*
@@ -95,6 +89,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 		buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
 	}
 
+	/*
+	 * NOTE: for the time being, we make bsize == frsize to humor
+	 * not-yet-ancient versions of glibc that are broken.
+	 * Someday, we will probably want to report a real block
+	 * size...  whatever that may mean for a network file system!
+	 */
+	buf->f_bsize = buf->f_frsize;
+
 	buf->f_files = le64_to_cpu(st.num_objects);
 	buf->f_ffree = -1;
 	buf->f_namelen = NAME_MAX;
@@ -816,6 +818,9 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->cap_wq)
 		goto fail_inode_wq;
 
+	hash_init(fsc->async_unlink_conflict);
+	spin_lock_init(&fsc->async_unlink_conflict_lock);
+
 	spin_lock(&ceph_fsc_lock);
 	list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list);
 	spin_unlock(&ceph_fsc_lock);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index f59dac66955b..40630e6f691c 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 +296,14 @@ 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)
+#define CEPH_DENTRY_ASYNC_CREATE_BIT	(5)
+#define CEPH_DENTRY_ASYNC_CREATE	(1 << CEPH_DENTRY_ASYNC_CREATE_BIT)
 
 struct ceph_inode_xattrs_info {
 	/*
@@ -758,6 +769,8 @@ extern void ceph_unreserve_caps(struct ceph_mds_client *mdsc,
 extern void ceph_reservation_status(struct ceph_fs_client *client,
 				    int *total, int *avail, int *used,
 				    int *reserved, int *min);
+extern void change_auth_cap_ses(struct ceph_inode_info *ci,
+				struct ceph_mds_session *session);
 
 
 
@@ -1218,6 +1231,14 @@ extern int ceph_pool_perm_check(struct inode *inode, int need);
 extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
 int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate);
 
+static inline bool ceph_has_inline_data(struct ceph_inode_info *ci)
+{
+	if (ci->i_inline_version == CEPH_INLINE_NONE ||
+	    ci->i_inline_version == 1) /* initial version, no data */
+		return false;
+	return true;
+}
+
 /* file.c */
 extern const struct file_operations ceph_file_fops;
 
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index f141f5246163..f31350cda960 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1086,7 +1086,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
 			flags |= CEPH_XATTR_REMOVE;
 	}
 
-	dout("setxattr value=%.*s\n", (int)size, value);
+	dout("setxattr value size: %zu\n", size);
 
 	/* do request */
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
@@ -1184,8 +1184,14 @@ int __ceph_setxattr(struct inode *inode, const char *name,
 	spin_lock(&ci->i_ceph_lock);
 retry:
 	issued = __ceph_caps_issued(ci, NULL);
-	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
+	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
+	if ((ci->i_xattrs.version == 0) || !(issued & CEPH_CAP_XATTR_EXCL) ||
+	    (required_blob_size > mdsc->mdsmap->m_max_xattr_size)) {
+		dout("%s do sync setxattr: version: %llu size: %d max: %llu\n",
+		     __func__, ci->i_xattrs.version, required_blob_size,
+		     mdsc->mdsmap->m_max_xattr_size);
 		goto do_sync;
+	}
 
 	if (!lock_snap_rwsem && !ci->i_head_snapc) {
 		lock_snap_rwsem = true;
@@ -1201,8 +1207,6 @@ retry:
 	     ceph_cap_string(issued));
 	__build_xattrs(inode);
 
-	required_blob_size = __get_required_blob_size(ci, name_len, val_len);
-
 	if (!ci->i_xattrs.prealloc_blob ||
 	    required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
 		struct ceph_buffer *blob;