fanotify: report name info for FAN_DIR_MODIFY event

Report event FAN_DIR_MODIFY with name in a variable length record similar
to how fid's are reported. With name info reporting implemented, setting
FAN_DIR_MODIFY in mark mask is now allowed.

When events are reported with name, the reported fid identifies the
directory and the name follows the fid. The info record type for this
event info is FAN_EVENT_INFO_TYPE_DFID_NAME.

For now, all reported events have at most one info record which is
either FAN_EVENT_INFO_TYPE_FID or FAN_EVENT_INFO_TYPE_DFID_NAME (for
FAN_DIR_MODIFY). Later on, events "on child" will report both records.

There are several ways that an application can use this information:

1. When watching a single directory, the name is always relative to
the watched directory, so application need to fstatat(2) the name
relative to the watched directory.

2. When watching a set of directories, the application could keep a map
of dirfd for all watched directories and hash the map by fid obtained
with name_to_handle_at(2). When getting a name event, the fid in the
event info could be used to lookup the base dirfd in the map and then
call fstatat(2) with that dirfd.

3. When watching a filesystem (FAN_MARK_FILESYSTEM) or a large set of
directories, the application could use open_by_handle_at(2) with the fid
in event info to obtain dirfd for the directory where event happened and
call fstatat(2) with this dirfd.

The last option scales better for a large number of watched directories.
The first two options may be available in the future also for non
privileged fanotify watchers, because open_by_handle_at(2) requires
the CAP_DAC_READ_SEARCH capability.

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Amir Goldstein <[e-mail]>
Signed-off-by: Jan Kara <[e-mail]>

fs/notify/fanotify/fanotify.c

···
 	BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
 	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20);
 
 	mask = fanotify_group_event_mask(group, iter_info, mask, data,
 					 data_type);

fs/notify/fanotify/fanotify_user.c

···
 struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
 
 #define FANOTIFY_EVENT_ALIGN 4
+#define FANOTIFY_INFO_HDR_LEN \
+	(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
 
-static int fanotify_fid_info_len(int fh_len)
+static int fanotify_fid_info_len(int fh_len, int name_len)
 {
-	return roundup(sizeof(struct fanotify_event_info_fid) +
-		       sizeof(struct file_handle) + fh_len,
-		       FANOTIFY_EVENT_ALIGN);
+	int info_len = fh_len;
+
+	if (name_len)
+		info_len += name_len + 1;
+
+	return roundup(FANOTIFY_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN);
 }
 
 static int fanotify_event_info_len(struct fanotify_event *event)
 {
+	int info_len = 0;
 	int fh_len = fanotify_event_object_fh_len(event);
 
-	if (!fh_len)
-		return 0;
+	if (fh_len)
+		info_len += fanotify_fid_info_len(fh_len, 0);
 
-	return fanotify_fid_info_len(fh_len);
+	if (fanotify_event_name_len(event)) {
+		struct fanotify_name_event *fne = FANOTIFY_NE(event);
+
+		info_len += fanotify_fid_info_len(fne->dir_fh.len,
+						  fne->name_len);
+	}
+
+	return info_len;
 }
 
 /*
···
 	return -ENOENT;
 }
 
-static int copy_fid_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
-			    char __user *buf)
+static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
+			     const char *name, size_t name_len,
+			     char __user *buf, size_t count)
 {
 	struct fanotify_event_info_fid info = { };
 	struct file_handle handle = { };
 	unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf;
 	size_t fh_len = fh ? fh->len : 0;
-	size_t len = fanotify_fid_info_len(fh_len);
+	size_t info_len = fanotify_fid_info_len(fh_len, name_len);
+	size_t len = info_len;
 
-	if (!len)
+	pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
+		 __func__, fh_len, name_len, info_len, count);
+
+	if (!fh_len || (name && !name_len))
 		return 0;
 
-	if (WARN_ON_ONCE(len < sizeof(info) + sizeof(handle) + fh_len))
+	if (WARN_ON_ONCE(len < sizeof(info) || len > count))
 		return -EFAULT;
 
-	/* Copy event info fid header followed by vaiable sized file handle */
-	info.hdr.info_type = FAN_EVENT_INFO_TYPE_FID;
+	/*
+	 * Copy event info fid header followed by variable sized file handle
+	 * and optionally followed by variable sized filename.
+	 */
+	info.hdr.info_type = name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
+					FAN_EVENT_INFO_TYPE_FID;
 	info.hdr.len = len;
 	info.fsid = *fsid;
 	if (copy_to_user(buf, &info, sizeof(info)))
···
 
 	buf += sizeof(info);
 	len -= sizeof(info);
+	if (WARN_ON_ONCE(len < sizeof(handle)))
+		return -EFAULT;
+
 	handle.handle_type = fh->type;
 	handle.handle_bytes = fh_len;
 	if (copy_to_user(buf, &handle, sizeof(handle)))
···
 
 	buf += sizeof(handle);
 	len -= sizeof(handle);
+	if (WARN_ON_ONCE(len < fh_len))
+		return -EFAULT;
+
 	/*
-	 * For an inline fh, copy through stack to exclude the copy from
-	 * usercopy hardening protections.
+	 * For an inline fh and inline file name, copy through stack to exclude
+	 * the copy from usercopy hardening protections.
 	 */
 	fh_buf = fanotify_fh_buf(fh);
 	if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
···
 	if (copy_to_user(buf, fh_buf, fh_len))
 		return -EFAULT;
 
-	/* Pad with 0's */
 	buf += fh_len;
 	len -= fh_len;
+
+	if (name_len) {
+		/* Copy the filename with terminating null */
+		name_len++;
+		if (WARN_ON_ONCE(len < name_len))
+			return -EFAULT;
+
+		if (copy_to_user(buf, name, name_len))
+			return -EFAULT;
+
+		buf += name_len;
+		len -= name_len;
+	}
+
+	/* Pad with 0's */
 	WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN);
 	if (len > 0 && clear_user(buf, len))
 		return -EFAULT;
 
-	return 0;
+	return info_len;
 }
 
 static ssize_t copy_event_to_user(struct fsnotify_group *group,
···
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	metadata.event_len = FAN_EVENT_METADATA_LEN;
+	metadata.event_len = FAN_EVENT_METADATA_LEN +
+					fanotify_event_info_len(event);
 	metadata.metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata.vers = FANOTIFY_METADATA_VERSION;
 	metadata.reserved = 0;
 	metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
 	metadata.pid = pid_vnr(event->pid);
 
-	if (fanotify_event_object_fh(event)) {
-		metadata.event_len += fanotify_event_info_len(event);
-	} else if (path && path->mnt && path->dentry) {
+	if (path && path->mnt && path->dentry) {
 		fd = create_fd(group, path, &f);
 		if (fd < 0)
 			return fd;
···
 	if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
 		goto out_close_fd;
 
+	buf += FAN_EVENT_METADATA_LEN;
+	count -= FAN_EVENT_METADATA_LEN;
+
 	if (fanotify_is_perm_event(event->mask))
 		FANOTIFY_PERM(event)->fd = fd;
 
-	if (f) {
+	if (f)
 		fd_install(fd, f);
-	} else if (fanotify_event_object_fh(event)) {
-		ret = copy_fid_to_user(fanotify_event_fsid(event),
-				       fanotify_event_object_fh(event),
-				       buf + FAN_EVENT_METADATA_LEN);
+
+	/* Event info records order is: dir fid + name, child fid */
+	if (fanotify_event_name_len(event)) {
+		struct fanotify_name_event *fne = FANOTIFY_NE(event);
+
+		ret = copy_info_to_user(fanotify_event_fsid(event),
+					fanotify_event_dir_fh(event),
+					fne->name, fne->name_len,
+					buf, count);
 		if (ret < 0)
 			return ret;
+
+		buf += ret;
+		count -= ret;
+	}
+
+	if (fanotify_event_object_fh_len(event)) {
+		ret = copy_info_to_user(fanotify_event_fsid(event),
+					fanotify_event_object_fh(event),
+					NULL, 0, buf, count);
+		if (ret < 0)
+			return ret;
+
+		buf += ret;
+		count -= ret;
 	}
 
 	return metadata.event_len;

include/linux/fanotify.h

···
  * Directory entry modification events - reported only to directory
  * where entry is modified and not to a watching parent.
  */
-#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE)
+#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE | \
+				 FAN_DIR_MODIFY)
 
 /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */
 #define FANOTIFY_INODE_EVENTS	(FANOTIFY_DIRENT_EVENTS | \

include/uapi/linux/fanotify.h

···
 };
 
 #define FAN_EVENT_INFO_TYPE_FID		1
+#define FAN_EVENT_INFO_TYPE_DFID_NAME	2
 
 /* Variable length info record following event metadata */
 struct fanotify_event_info_header {
···
 	__u16 len;
 };
 
-/* Unique file identifier info record */
+/*
+ * Unique file identifier info record. This is used both for
+ * FAN_EVENT_INFO_TYPE_FID records and for FAN_EVENT_INFO_TYPE_DFID_NAME
+ * records. For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null
+ * terminated name immediately after the file handle.
+ */
 struct fanotify_event_info_fid {
 	struct fanotify_event_info_header hdr;
 	__kernel_fsid_t fsid;