vfs: break parent dir delegations in open(..., O_CREAT) codepath

In order to add directory delegation support, we need to break
delegations on the parent whenever there is going to be a change in the
directory.

Add a delegated_inode parameter to lookup_open and have it break the
delegation. Then, open_last_lookups can wait for the delegation break
and retry the call to lookup_open once it's done.

Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20251111-dir-deleg-ro-v6-8-52f3feebb2f2@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: jtlayton

fs/namei.c

@@ -3697,7 +3697,7 @@ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry,
  */
 static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 				  const struct open_flags *op,
-				  bool got_write)
+				  bool got_write, struct delegated_inode *delegated_inode)
 {
 	struct mnt_idmap *idmap;
 	struct dentry *dir = nd->path.dentry;
@@ -3786,6 +3786,11 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 
 	/* Negative dentry, just create the file */
 	if (!dentry->d_inode && (open_flag & O_CREAT)) {
+		/* but break the directory lease first! */
+		error = try_break_deleg(dir_inode, delegated_inode);
+		if (error)
+			goto out_dput;
+
 		file->f_mode |= FMODE_CREATED;
 		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 		if (!dir_inode->i_op->create) {
@@ -3848,6 +3853,7 @@ static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
 static const char *open_last_lookups(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op)
 {
+	struct delegated_inode delegated_inode = { };
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
 	bool got_write = false;
@@ -3879,7 +3885,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 				return ERR_PTR(-ECHILD);
 		}
 	}
-
+retry:
 	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
 		got_write = !mnt_want_write(nd->path.mnt);
 		/*
@@ -3892,7 +3898,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 		inode_lock(dir->d_inode);
 	else
 		inode_lock_shared(dir->d_inode);
-	dentry = lookup_open(nd, file, op, got_write);
+	dentry = lookup_open(nd, file, op, got_write, &delegated_inode);
 	if (!IS_ERR(dentry)) {
 		if (file->f_mode & FMODE_CREATED)
 			fsnotify_create(dir->d_inode, dentry);
@@ -3907,8 +3913,16 @@ static const char *open_last_lookups(struct nameidata *nd,
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		if (is_delegated(&delegated_inode)) {
+			int error = break_deleg_wait(&delegated_inode);
+
+			if (!error)
+				goto retry;
+			return ERR_PTR(error);
+		}
 		return ERR_CAST(dentry);
+	}
 
 	if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) {
 		dput(nd->path.dentry);