Merge tag 'ceph-for-4.9-rc1' of git://github.com/ceph/ceph-client

Pull Ceph updates from Ilya Dryomov:
 "The big ticket item here is support for rbd exclusive-lock feature,
  with maintenance operations offloaded to userspace (Douglas Fuller,
  Mike Christie and myself). Another block device bullet is a series
  fixing up layering error paths (myself).

  On the filesystem side, we've got patches that improve our handling of
  buffered vs dio write races (Neil Brown) and a few assorted fixes from
  Zheng. Also included a couple of random cleanups and a minor CRUSH
  update"

* tag 'ceph-for-4.9-rc1' of git://github.com/ceph/ceph-client: (39 commits)
  crush: remove redundant local variable
  crush: don't normalize input of crush_ln iteratively
  libceph: ceph_build_auth() doesn't need ceph_auth_build_hello()
  libceph: use CEPH_AUTH_UNKNOWN in ceph_auth_build_hello()
  ceph: fix description for rsize and rasize mount options
  rbd: use kmalloc_array() in rbd_header_from_disk()
  ceph: use list_move instead of list_del/list_add
  ceph: handle CEPH_SESSION_REJECT message
  ceph: avoid accessing / when mounting a subpath
  ceph: fix mandatory flock check
  ceph: remove warning when ceph_releasepage() is called on dirty page
  ceph: ignore error from invalidate_inode_pages2_range() in direct write
  ceph: fix error handling of start_read()
  rbd: add rbd_obj_request_error() helper
  rbd: img_data requests don't own their page array
  rbd: don't call rbd_osd_req_format_read() for !img_data requests
  rbd: rework rbd_img_obj_exists_submit() error paths
  rbd: don't crash or leak on errors in rbd_img_obj_parent_read_full_callback()
  rbd: move bumping img_request refcount into rbd_obj_request_submit()
  rbd: mark the original request as done if stat request fails
  ...

7 files changed, 61 insertions, 53 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index d5b6f959a3c3..ef3ebd780aff 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -175,9 +175,8 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 
 static int ceph_releasepage(struct page *page, gfp_t g)
 {
-	dout("%p releasepage %p idx %lu\n", page->mapping->host,
-	     page, page->index);
-	WARN_ON(PageDirty(page));
+	dout("%p releasepage %p idx %lu (%sdirty)\n", page->mapping->host,
+	     page, page->index, PageDirty(page) ? "" : "not ");
 
 	/* Can we release the page from the cache? */
 	if (!ceph_release_fscache_page(page, g))
@@ -298,14 +297,6 @@ unlock:
 	kfree(osd_data->pages);
 }
 
-static void ceph_unlock_page_vector(struct page **pages, int num_pages)
-{
-	int i;
-
-	for (i = 0; i < num_pages; i++)
-		unlock_page(pages[i]);
-}
-
 /*
  * start an async read(ahead) operation.  return nr_pages we submitted
  * a read for on success, or negative error code.
@@ -370,6 +361,10 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 			dout("start_read %p add_to_page_cache failed %p\n",
 			     inode, page);
 			nr_pages = i;
+			if (nr_pages > 0) {
+				len = nr_pages << PAGE_SHIFT;
+				break;
+			}
 			goto out_pages;
 		}
 		pages[i] = page;
@@ -386,8 +381,11 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	return nr_pages;
 
 out_pages:
-	ceph_unlock_page_vector(pages, nr_pages);
-	ceph_release_page_vector(pages, nr_pages);
+	for (i = 0; i < nr_pages; ++i) {
+		ceph_fscache_readpage_cancel(inode, pages[i]);
+		unlock_page(pages[i]);
+	}
+	ceph_put_page_vector(pages, nr_pages, false);
 out:
 	ceph_osdc_put_request(req);
 	return ret;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 0f5375d8e030..395c7fcb1cea 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -902,10 +902,10 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		return ret;
 
 	if (write) {
-		ret = invalidate_inode_pages2_range(inode->i_mapping,
+		int ret2 = invalidate_inode_pages2_range(inode->i_mapping,
 					pos >> PAGE_SHIFT,
 					(pos + count) >> PAGE_SHIFT);
-		if (ret < 0)
+		if (ret2 < 0)
 			dout("invalidate_inode_pages2_range returned %d\n", ret);
 
 		flags = CEPH_OSD_FLAG_ORDERSNAP |
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index a2cb0c254060..6806dbeaee19 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -210,8 +210,8 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 	/* No mandatory locks */
-	if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
-		return -ENOLCK;
+	if (fl->fl_type & LOCK_MAND)
+		return -EOPNOTSUPP;
 
 	dout("ceph_flock, fl_file: %p", fl->fl_file);
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f72d4ae303b2..815acd1a56d4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -370,6 +370,7 @@ const char *ceph_session_state_name(int s)
 	case CEPH_MDS_SESSION_CLOSING: return "closing";
 	case CEPH_MDS_SESSION_RESTARTING: return "restarting";
 	case CEPH_MDS_SESSION_RECONNECTING: return "reconnecting";
+	case CEPH_MDS_SESSION_REJECTED: return "rejected";
 	default: return "???";
 	}
 }
@@ -1150,8 +1151,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		while (!list_empty(&ci->i_cap_flush_list)) {
 			cf = list_first_entry(&ci->i_cap_flush_list,
 					      struct ceph_cap_flush, i_list);
-			list_del(&cf->i_list);
-			list_add(&cf->i_list, &to_remove);
+			list_move(&cf->i_list, &to_remove);
 		}
 
 		spin_lock(&mdsc->cap_dirty_lock);
@@ -1378,7 +1378,7 @@ static int request_close_session(struct ceph_mds_client *mdsc,
 	if (!msg)
 		return -ENOMEM;
 	ceph_con_send(&session->s_con, msg);
-	return 0;
+	return 1;
 }
 
 /*
@@ -2131,6 +2131,10 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	     ceph_session_state_name(session->s_state));
 	if (session->s_state != CEPH_MDS_SESSION_OPEN &&
 	    session->s_state != CEPH_MDS_SESSION_HUNG) {
+		if (session->s_state == CEPH_MDS_SESSION_REJECTED) {
+			err = -EACCES;
+			goto out_session;
+		}
 		if (session->s_state == CEPH_MDS_SESSION_NEW ||
 		    session->s_state == CEPH_MDS_SESSION_CLOSING)
 			__open_session(mdsc, session);
@@ -2652,6 +2656,15 @@ static void handle_session(struct ceph_mds_session *session,
 		wake_up_session_caps(session, 0);
 		break;
 
+	case CEPH_SESSION_REJECT:
+		WARN_ON(session->s_state != CEPH_MDS_SESSION_OPENING);
+		pr_info("mds%d rejected session\n", session->s_mds);
+		session->s_state = CEPH_MDS_SESSION_REJECTED;
+		cleanup_session_requests(mdsc, session);
+		remove_session_caps(session);
+		wake = 2; /* for good measure */
+		break;
+
 	default:
 		pr_err("mdsc_handle_session bad op %d mds%d\n", op, mds);
 		WARN_ON(1);
@@ -3557,11 +3570,11 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 /*
  * true if all sessions are closed, or we force unmount
  */
-static bool done_closing_sessions(struct ceph_mds_client *mdsc)
+static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped)
 {
 	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 		return true;
-	return atomic_read(&mdsc->num_sessions) == 0;
+	return atomic_read(&mdsc->num_sessions) <= skipped;
 }
 
 /*
@@ -3572,6 +3585,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	struct ceph_options *opts = mdsc->fsc->client->options;
 	struct ceph_mds_session *session;
 	int i;
+	int skipped = 0;
 
 	dout("close_sessions\n");
 
@@ -3583,7 +3597,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 			continue;
 		mutex_unlock(&mdsc->mutex);
 		mutex_lock(&session->s_mutex);
-		__close_session(mdsc, session);
+		if (__close_session(mdsc, session) <= 0)
+			skipped++;
 		mutex_unlock(&session->s_mutex);
 		ceph_put_mds_session(session);
 		mutex_lock(&mdsc->mutex);
@@ -3591,7 +3606,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	mutex_unlock(&mdsc->mutex);
 
 	dout("waiting for sessions to close\n");
-	wait_event_timeout(mdsc->session_close_wq, done_closing_sessions(mdsc),
+	wait_event_timeout(mdsc->session_close_wq,
+			   done_closing_sessions(mdsc, skipped),
 			   ceph_timeout_jiffies(opts->mount_timeout));
 
 	/* tear down remaining sessions */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 6b3679737d4a..3c6f77b7bb02 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -121,6 +121,7 @@ enum {
 	CEPH_MDS_SESSION_CLOSING = 5,
 	CEPH_MDS_SESSION_RESTARTING = 6,
 	CEPH_MDS_SESSION_RECONNECTING = 7,
+	CEPH_MDS_SESSION_REJECTED = 8,
 };
 
 struct ceph_mds_session {
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index 89e6bc321df3..913dea163d5c 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -43,6 +43,8 @@ const char *ceph_session_op_name(int op)
 	case CEPH_SESSION_RECALL_STATE: return "recall_state";
 	case CEPH_SESSION_FLUSHMSG: return "flushmsg";
 	case CEPH_SESSION_FLUSHMSG_ACK: return "flushmsg_ack";
+	case CEPH_SESSION_FORCE_RO: return "force_ro";
+	case CEPH_SESSION_REJECT: return "reject";
 	}
 	return "???";
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index e247f6f0feb7..a29ffce98187 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -396,10 +396,12 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	 */
 	dev_name_end = strchr(dev_name, '/');
 	if (dev_name_end) {
-		fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
-		if (!fsopt->server_path) {
-			err = -ENOMEM;
-			goto out;
+		if (strlen(dev_name_end) > 1) {
+			fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL);
+			if (!fsopt->server_path) {
+				err = -ENOMEM;
+				goto out;
+			}
 		}
 	} else {
 		dev_name_end = dev_name + strlen(dev_name);
@@ -788,15 +790,10 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
 		struct inode *inode = req->r_target_inode;
 		req->r_target_inode = NULL;
 		dout("open_root_inode success\n");
-		if (ceph_ino(inode) == CEPH_INO_ROOT &&
-		    fsc->sb->s_root == NULL) {
-			root = d_make_root(inode);
-			if (!root) {
-				root = ERR_PTR(-ENOMEM);
-				goto out;
-			}
-		} else {
-			root = d_obtain_root(inode);
+		root = d_make_root(inode);
+		if (!root) {
+			root = ERR_PTR(-ENOMEM);
+			goto out;
 		}
 		ceph_init_dentry(root);
 		dout("open_root_inode success, root dentry is %p\n", root);
@@ -825,17 +822,24 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
 	mutex_lock(&fsc->client->mount_mutex);
 
 	if (!fsc->sb->s_root) {
+		const char *path;
 		err = __ceph_open_session(fsc->client, started);
 		if (err < 0)
 			goto out;
 
-		dout("mount opening root\n");
-		root = open_root_dentry(fsc, "", started);
+		if (!fsc->mount_options->server_path) {
+			path = "";
+			dout("mount opening path \\t\n");
+		} else {
+			path = fsc->mount_options->server_path + 1;
+			dout("mount opening path %s\n", path);
+		}
+		root = open_root_dentry(fsc, path, started);
 		if (IS_ERR(root)) {
 			err = PTR_ERR(root);
 			goto out;
 		}
-		fsc->sb->s_root = root;
+		fsc->sb->s_root = dget(root);
 		first = 1;
 
 		err = ceph_fs_debugfs_init(fsc);
@@ -843,19 +847,6 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
 			goto fail;
 	}
 
-	if (!fsc->mount_options->server_path) {
-		root = fsc->sb->s_root;
-		dget(root);
-	} else {
-		const char *path = fsc->mount_options->server_path + 1;
-		dout("mount opening path %s\n", path);
-		root = open_root_dentry(fsc, path, started);
-		if (IS_ERR(root)) {
-			err = PTR_ERR(root);
-			goto fail;
-		}
-	}
-
 	fsc->mount_state = CEPH_MOUNT_MOUNTED;
 	dout("mount success\n");
 	mutex_unlock(&fsc->client->mount_mutex);