Merge tag 'fsnotify_for_v6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:

 - Support for fanotify events returning file handles for filesystems
   not exportable via NFS

 - Improved error handling exportfs functions

 - Add missing FS_OPEN events when unusual open helpers are used

* tag 'fsnotify_for_v6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  fsnotify: move fsnotify_open() hook into do_dentry_open()
  exportfs: check for error return value from exportfs_encode_*()
  fanotify: support reporting non-decodeable file handles
  exportfs: allow exporting non-decodeable file handles to userspace
  exportfs: add explicit flag to request non-decodeable file handles
  exportfs: change connectable argument to bit flags

12 files changed, 85 insertions, 37 deletions

diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst
index 0e98edd353b5..3d97b8d8f735 100644
--- a/Documentation/filesystems/nfs/exporting.rst
+++ b/Documentation/filesystems/nfs/exporting.rst
@@ -122,8 +122,8 @@ are exportable by setting the s_export_op field in the struct
 super_block.  This field must point to a "struct export_operations"
 struct which has the following members:
 
- encode_fh  (optional)
-    Takes a dentry and creates a filehandle fragment which can later be used
+  encode_fh (optional)
+    Takes a dentry and creates a filehandle fragment which may later be used
     to find or create a dentry for the same object.  The default
     implementation creates a filehandle fragment that encodes a 32bit inode
     and generation number for the inode encoded, and if necessary the
diff --git a/fs/exec.c b/fs/exec.c
index 80b8611c416d..1a827d55ba94 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -152,8 +152,6 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 			 path_noexec(&file->f_path)))
 		goto exit;
 
-	fsnotify_open(file);
-
 	error = -ENOEXEC;
 
 	read_lock(&binfmt_lock);
@@ -940,9 +938,6 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	if (err)
 		goto exit;
 
-	if (name->name[0] != '\0')
-		fsnotify_open(file);
-
 out:
 	return file;
 
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index ab88d33d106c..40e624cf7e92 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -381,11 +381,27 @@ static int export_encode_fh(struct inode *inode, struct fid *fid,
 	return type;
 }
 
+/**
+ * exportfs_encode_inode_fh - encode a file handle from inode
+ * @inode:   the object to encode
+ * @fid:     where to store the file handle fragment
+ * @max_len: maximum length to store there
+ * @flags:   properties of the requested file handle
+ *
+ * Returns an enum fid_type or a negative errno.
+ */
 int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
-			     int *max_len, struct inode *parent)
+			     int *max_len, struct inode *parent, int flags)
 {
 	const struct export_operations *nop = inode->i_sb->s_export_op;
 
+	/*
+	 * If a decodeable file handle was requested, we need to make sure that
+	 * filesystem can decode file handles.
+	 */
+	if (nop && !(flags & EXPORT_FH_FID) && !nop->fh_to_dentry)
+		return -EOPNOTSUPP;
+
 	if (nop && nop->encode_fh)
 		return nop->encode_fh(inode, fid->raw, max_len, parent);
 
@@ -393,14 +409,23 @@ int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
 }
 EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh);
 
+/**
+ * exportfs_encode_fh - encode a file handle from dentry
+ * @dentry:  the object to encode
+ * @fid:     where to store the file handle fragment
+ * @max_len: maximum length to store there
+ * @flags:   properties of the requested file handle
+ *
+ * Returns an enum fid_type or a negative errno.
+ */
 int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
-		int connectable)
+		       int flags)
 {
 	int error;
 	struct dentry *p = NULL;
 	struct inode *inode = dentry->d_inode, *parent = NULL;
 
-	if (connectable && !S_ISDIR(inode->i_mode)) {
+	if ((flags & EXPORT_FH_CONNECTABLE) && !S_ISDIR(inode->i_mode)) {
 		p = dget_parent(dentry);
 		/*
 		 * note that while p might've ceased to be our parent already,
@@ -409,7 +434,7 @@ int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
 		parent = p->d_inode;
 	}
 
-	error = exportfs_encode_inode_fh(inode, fid, max_len, parent);
+	error = exportfs_encode_inode_fh(inode, fid, max_len, parent, flags);
 	dput(p);
 
 	return error;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index f2bc27d1975e..6ea8d35a9382 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -16,7 +16,7 @@
 
 static long do_sys_name_to_handle(const struct path *path,
 				  struct file_handle __user *ufh,
-				  int __user *mnt_id)
+				  int __user *mnt_id, int fh_flags)
 {
 	long retval;
 	struct file_handle f_handle;
@@ -24,11 +24,14 @@ static long do_sys_name_to_handle(const struct path *path,
 	struct file_handle *handle = NULL;
 
 	/*
-	 * We need to make sure whether the file system
-	 * support decoding of the file handle
+	 * We need to make sure whether the file system support decoding of
+	 * the file handle if decodeable file handle was requested.
+	 * Otherwise, even empty export_operations are sufficient to opt-in
+	 * to encoding FIDs.
 	 */
 	if (!path->dentry->d_sb->s_export_op ||
-	    !path->dentry->d_sb->s_export_op->fh_to_dentry)
+	    (!(fh_flags & EXPORT_FH_FID) &&
+	     !path->dentry->d_sb->s_export_op->fh_to_dentry))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
@@ -45,27 +48,28 @@ static long do_sys_name_to_handle(const struct path *path,
 	/* convert handle size to multiple of sizeof(u32) */
 	handle_dwords = f_handle.handle_bytes >> 2;
 
-	/* we ask for a non connected handle */
+	/* we ask for a non connectable maybe decodeable file handle */
 	retval = exportfs_encode_fh(path->dentry,
 				    (struct fid *)handle->f_handle,
-				    &handle_dwords,  0);
+				    &handle_dwords, fh_flags);
 	handle->handle_type = retval;
 	/* convert handle size to bytes */
 	handle_bytes = handle_dwords * sizeof(u32);
 	handle->handle_bytes = handle_bytes;
 	if ((handle->handle_bytes > f_handle.handle_bytes) ||
-	    (retval == FILEID_INVALID) || (retval == -ENOSPC)) {
+	    (retval == FILEID_INVALID) || (retval < 0)) {
 		/* As per old exportfs_encode_fh documentation
 		 * we could return ENOSPC to indicate overflow
 		 * But file system returned 255 always. So handle
 		 * both the values
 		 */
+		if (retval == FILEID_INVALID || retval == -ENOSPC)
+			retval = -EOVERFLOW;
 		/*
 		 * set the handle size to zero so we copy only
 		 * non variable part of the file_handle
 		 */
 		handle_bytes = 0;
-		retval = -EOVERFLOW;
 	} else
 		retval = 0;
 	/* copy the mount id */
@@ -84,6 +88,7 @@ static long do_sys_name_to_handle(const struct path *path,
  * @handle: resulting file handle
  * @mnt_id: mount id of the file system containing the file
  * @flag: flag value to indicate whether to follow symlink or not
+ *        and whether a decodable file handle is required.
  *
  * @handle->handle_size indicate the space available to store the
  * variable part of the file handle in bytes. If there is not
@@ -96,17 +101,19 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 {
 	struct path path;
 	int lookup_flags;
+	int fh_flags;
 	int err;
 
-	if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
+	if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID))
 		return -EINVAL;
 
 	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
+	fh_flags = (flag & AT_HANDLE_FID) ? EXPORT_FH_FID : 0;
 	if (flag & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
 	err = user_path_at(dfd, name, lookup_flags, &path);
 	if (!err) {
-		err = do_sys_name_to_handle(&path, handle, mnt_id);
+		err = do_sys_name_to_handle(&path, handle, mnt_id, fh_flags);
 		path_put(&path);
 	}
 	return err;
@@ -235,7 +242,6 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh,
 		retval =  PTR_ERR(file);
 	} else {
 		retval = fd;
-		fsnotify_open(file);
 		fd_install(fd, file);
 	}
 	path_put(&path);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index e8e13ae72e3c..c291389a1d71 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -414,10 +414,13 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
 		struct fid *fid = (struct fid *)
 			(fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1);
 		int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
-		int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK);
+		int fh_flags = (exp->ex_flags & NFSEXP_NOSUBTREECHECK) ? 0 :
+				EXPORT_FH_CONNECTABLE;
+		int fileid_type =
+			exportfs_encode_fh(dentry, fid, &maxsize, fh_flags);
 
 		fhp->fh_handle.fh_fileid_type =
-			exportfs_encode_fh(dentry, fid, &maxsize, subtreecheck);
+			fileid_type > 0 ? fileid_type : FILEID_INVALID;
 		fhp->fh_handle.fh_size += maxsize * 4;
 	} else {
 		fhp->fh_handle.fh_fileid_type = FILEID_ROOT;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 29bdd99b29fa..9dac7f6e72d2 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -380,7 +380,7 @@ static int fanotify_encode_fh_len(struct inode *inode)
 	if (!inode)
 		return 0;
 
-	exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
+	exportfs_encode_fid(inode, NULL, &dwords);
 	fh_len = dwords << 2;
 
 	/*
@@ -443,9 +443,9 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
 	}
 
 	dwords = fh_len >> 2;
-	type = exportfs_encode_inode_fh(inode, buf, &dwords, NULL);
+	type = exportfs_encode_fid(inode, buf, &dwords);
 	err = -EINVAL;
-	if (!type || type == FILEID_INVALID || fh_len != dwords << 2)
+	if (type <= 0 || type == FILEID_INVALID || fh_len != dwords << 2)
 		goto out_err;
 
 	fh->type = type;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 22fb1cf7e1fc..95d7d8790bc3 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1591,11 +1591,10 @@ static int fanotify_test_fid(struct dentry *dentry)
 	 * We need to make sure that the file system supports at least
 	 * encoding a file handle so user can use name_to_handle_at() to
 	 * compare fid returned with event to the file handle of watched
-	 * objects. However, name_to_handle_at() requires that the
-	 * filesystem also supports decoding file handles.
+	 * objects. However, even the relaxed AT_HANDLE_FID flag requires
+	 * at least empty export_operations for ecoding unique file ids.
 	 */
-	if (!dentry->d_sb->s_export_op ||
-	    !dentry->d_sb->s_export_op->fh_to_dentry)
+	if (!dentry->d_sb->s_export_op)
 		return -EOPNOTSUPP;
 
 	return 0;
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 55081ae3a6ec..5c430736ec12 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -50,7 +50,7 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
 	f.handle.handle_bytes = sizeof(f.pad);
 	size = f.handle.handle_bytes >> 2;
 
-	ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, NULL);
+	ret = exportfs_encode_fid(inode, (struct fid *)f.handle.f_handle, &size);
 	if ((ret == FILEID_INVALID) || (ret < 0)) {
 		WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
 		return;
diff --git a/fs/open.c b/fs/open.c
index fb07b2840eb4..0c55c8e7f837 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -963,6 +963,11 @@ static int do_dentry_open(struct file *f,
 		}
 	}
 
+	/*
+	 * Once we return a file with FMODE_OPENED, __fput() will call
+	 * fsnotify_close(), so we need fsnotify_open() here for symmetry.
+	 */
+	fsnotify_open(f);
 	return 0;
 
 cleanup_all:
@@ -1404,7 +1409,6 @@ static long do_sys_openat2(int dfd, const char __user *filename,
 			put_unused_fd(fd);
 			fd = PTR_ERR(f);
 		} else {
-			fsnotify_open(f);
 			fd_install(fd, f);
 		}
 	}
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 9edb29101ec8..11fbd0ee1370 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -135,6 +135,9 @@ struct fid {
 	};
 };
 
+#define EXPORT_FH_CONNECTABLE	0x1 /* Encode file handle with parent */
+#define EXPORT_FH_FID		0x2 /* File handle may be non-decodeable */
+
 /**
  * struct export_operations - for nfsd to communicate with file systems
  * @encode_fh:      encode a file handle fragment from a dentry
@@ -150,7 +153,7 @@ struct fid {
  * encode_fh:
  *    @encode_fh should store in the file handle fragment @fh (using at most
  *    @max_len bytes) information that can be used by @decode_fh to recover the
- *    file referred to by the &struct dentry @de.  If the @connectable flag is
+ *    file referred to by the &struct dentry @de.  If @flag has CONNECTABLE bit
  *    set, the encode_fh() should store sufficient information so that a good
  *    attempt can be made to find not only the file but also it's place in the
  *    filesystem.   This typically means storing a reference to de->d_parent in
@@ -225,9 +228,18 @@ struct export_operations {
 };
 
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
-				    int *max_len, struct inode *parent);
+				    int *max_len, struct inode *parent,
+				    int flags);
 extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
-	int *max_len, int connectable);
+			      int *max_len, int flags);
+
+static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid,
+				      int *max_len)
+{
+	return exportfs_encode_inode_fh(inode, fid, max_len, NULL,
+					EXPORT_FH_FID);
+}
+
 extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt,
 					     struct fid *fid, int fh_len,
 					     int fileid_type,
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index e8c07da58c9f..6c80f96049bd 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -112,4 +112,9 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
+/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
+#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
+					compare object identity and may not
+					be usable to open_by_handle_at(2) */
+
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index a1b98c81a52d..10ca57f5bd24 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -150,7 +150,6 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
 
 	if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set)
 		file->f_flags &= ~O_NONBLOCK;
-	fsnotify_open(file);
 
 	if (!fixed)
 		fd_install(ret, file);