Merge tag 'fsnotify_hsm_for_v6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify pre-content notification support from Jan Kara:
 "This introduces a new fsnotify event (FS_PRE_ACCESS) that gets
  generated before a file contents is accessed.

  The event is synchronous so if there is listener for this event, the
  kernel waits for reply. On success the execution continues as usual,
  on failure we propagate the error to userspace. This allows userspace
  to fill in file content on demand from slow storage. The context in
  which the events are generated has been picked so that we don't hold
  any locks and thus there's no risk of a deadlock for the userspace
  handler.

  The new pre-content event is available only for users with global
  CAP_SYS_ADMIN capability (similarly to other parts of fanotify
  functionality) and it is an administrator responsibility to make sure
  the userspace event handler doesn't do stupid stuff that can DoS the
  system.

  Based on your feedback from the last submission, fsnotify code has
  been improved and now file->f_mode encodes whether pre-content event
  needs to be generated for the file so the fast path when nobody wants
  pre-content event for the file just grows the additional file->f_mode
  check. As a bonus this also removes the checks whether the old
  FS_ACCESS event needs to be generated from the fast path. Also the
  place where the event is generated during page fault has been moved so
  now filemap_fault() generates the event if and only if there is no
  uptodate folio in the page cache.

  Also we have dropped FS_PRE_MODIFY event as current real-world users
  of the pre-content functionality don't really use it so let's start
  with the minimal useful feature set"

* tag 'fsnotify_hsm_for_v6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (21 commits)
  fanotify: Fix crash in fanotify_init(2)
  fs: don't block write during exec on pre-content watched files
  fs: enable pre-content events on supported file systems
  ext4: add pre-content fsnotify hook for DAX faults
  btrfs: disable defrag on pre-content watched files
  xfs: add pre-content fsnotify hook for DAX faults
  fsnotify: generate pre-content permission event on page fault
  mm: don't allow huge faults for files with pre content watches
  fanotify: disable readahead if we have pre-content watches
  fanotify: allow to set errno in FAN_DENY permission response
  fanotify: report file range info with pre-content events
  fanotify: introduce FAN_PRE_ACCESS permission event
  fsnotify: generate pre-content permission event on truncate
  fsnotify: pass optional file access range in pre-content event
  fsnotify: introduce pre-content permission events
  fanotify: reserve event bit of deprecated FAN_DIR_MODIFY
  fanotify: rename a misnamed constant
  fanotify: don't skip extra event info if no info_mode is set
  fsnotify: check if file is actually being watched for pre-content events on open
  fsnotify: opt-in for permission events at file open time
  ...

4 files changed, 240 insertions, 39 deletions

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 24c7c5df4998..95646f7c46ca 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -223,7 +223,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
 				 struct fanotify_perm_event *event,
 				 struct fsnotify_iter_info *iter_info)
 {
-	int ret;
+	int ret, errno;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
@@ -262,14 +262,23 @@ static int fanotify_get_response(struct fsnotify_group *group,
 		ret = 0;
 		break;
 	case FAN_DENY:
+		/* Check custom errno from pre-content events */
+		errno = fanotify_get_response_errno(event->response);
+		if (errno) {
+			ret = -errno;
+			break;
+		}
+		fallthrough;
 	default:
 		ret = -EPERM;
 	}
 
 	/* Check if the response should be audited */
-	if (event->response & FAN_AUDIT)
-		audit_fanotify(event->response & ~FAN_AUDIT,
-			       &event->audit_rule);
+	if (event->response & FAN_AUDIT) {
+		u32 response = event->response &
+			(FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS);
+		audit_fanotify(response & ~FAN_AUDIT, &event->audit_rule);
+	}
 
 	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
 		 group, event, ret);
@@ -548,9 +557,13 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
 	return &pevent->fae;
 }
 
-static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
+static struct fanotify_event *fanotify_alloc_perm_event(const void *data,
+							int data_type,
 							gfp_t gfp)
 {
+	const struct path *path = fsnotify_data_path(data, data_type);
+	const struct file_range *range =
+			    fsnotify_data_file_range(data, data_type);
 	struct fanotify_perm_event *pevent;
 
 	pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
@@ -564,6 +577,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
 	pevent->hdr.len = 0;
 	pevent->state = FAN_EVENT_INIT;
 	pevent->path = *path;
+	/* NULL ppos means no range info */
+	pevent->ppos = range ? &range->pos : NULL;
+	pevent->count = range ? range->count : 0;
 	path_get(path);
 
 	return &pevent->fae;
@@ -801,7 +817,7 @@ static struct fanotify_event *fanotify_alloc_event(
 	old_memcg = set_active_memcg(group->memcg);
 
 	if (fanotify_is_perm_event(mask)) {
-		event = fanotify_alloc_perm_event(path, gfp);
+		event = fanotify_alloc_perm_event(data, data_type, gfp);
 	} else if (fanotify_is_error_event(mask)) {
 		event = fanotify_alloc_error_event(group, fsid, data,
 						   data_type, &hash);
@@ -909,8 +925,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
 	BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
 	BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
+	BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22);
 
 	mask = fanotify_group_event_mask(group, iter_info, &match_mask,
 					 mask, data, data_type, dir);
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index e5ab33cae6a7..c12cbc270539 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -425,6 +425,8 @@ FANOTIFY_PE(struct fanotify_event *event)
 struct fanotify_perm_event {
 	struct fanotify_event fae;
 	struct path path;
+	const loff_t *ppos;		/* optional file range info */
+	size_t count;
 	u32 response;			/* userspace answer to the event */
 	unsigned short state;		/* state of the event */
 	int fd;		/* fd we passed to userspace for this event */
@@ -446,6 +448,14 @@ static inline bool fanotify_is_perm_event(u32 mask)
 		mask & FANOTIFY_PERM_EVENTS;
 }
 
+static inline bool fanotify_event_has_access_range(struct fanotify_event *event)
+{
+	if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS))
+		return false;
+
+	return FANOTIFY_PERM(event)->ppos;
+}
+
 static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
 {
 	return container_of(fse, struct fanotify_event, fse);
@@ -518,3 +528,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
 
 	return mflags;
 }
+
+static inline u32 fanotify_get_response_errno(int res)
+{
+	return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK;
+}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 2d85c71717d6..6ff94e312232 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -100,8 +100,7 @@ static void __init fanotify_sysctls_init(void)
  *
  * Internal and external open flags are stored together in field f_flags of
  * struct file. Only external open flags shall be allowed in event_f_flags.
- * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
- * excluded.
+ * Internal flags like FMODE_EXEC shall be excluded.
  */
 #define	FANOTIFY_INIT_ALL_EVENT_F_BITS				( \
 		O_ACCMODE	| O_APPEND	| O_NONBLOCK	| \
@@ -118,10 +117,12 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init;
 #define FANOTIFY_EVENT_ALIGN 4
 #define FANOTIFY_FID_INFO_HDR_LEN \
 	(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
-#define FANOTIFY_PIDFD_INFO_HDR_LEN \
+#define FANOTIFY_PIDFD_INFO_LEN \
 	sizeof(struct fanotify_event_info_pidfd)
 #define FANOTIFY_ERROR_INFO_LEN \
 	(sizeof(struct fanotify_event_info_error))
+#define FANOTIFY_RANGE_INFO_LEN \
+	(sizeof(struct fanotify_event_info_range))
 
 static int fanotify_fid_info_len(int fh_len, int name_len)
 {
@@ -159,9 +160,6 @@ static size_t fanotify_event_len(unsigned int info_mode,
 	int fh_len;
 	int dot_len = 0;
 
-	if (!info_mode)
-		return event_len;
-
 	if (fanotify_is_error_event(event->mask))
 		event_len += FANOTIFY_ERROR_INFO_LEN;
 
@@ -176,14 +174,17 @@ static size_t fanotify_event_len(unsigned int info_mode,
 		dot_len = 1;
 	}
 
-	if (info_mode & FAN_REPORT_PIDFD)
-		event_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
-
 	if (fanotify_event_has_object_fh(event)) {
 		fh_len = fanotify_event_object_fh_len(event);
 		event_len += fanotify_fid_info_len(fh_len, dot_len);
 	}
 
+	if (info_mode & FAN_REPORT_PIDFD)
+		event_len += FANOTIFY_PIDFD_INFO_LEN;
+
+	if (fanotify_event_has_access_range(event))
+		event_len += FANOTIFY_RANGE_INFO_LEN;
+
 	return event_len;
 }
 
@@ -258,12 +259,11 @@ static int create_fd(struct fsnotify_group *group, const struct path *path,
 		return client_fd;
 
 	/*
-	 * we need a new file handle for the userspace program so it can read even if it was
-	 * originally opened O_WRONLY.
+	 * We provide an fd for the userspace program, so it could access the
+	 * file without generating fanotify events itself.
 	 */
-	new_file = dentry_open(path,
-			       group->fanotify_data.f_flags | __FMODE_NONOTIFY,
-			       current_cred());
+	new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags,
+					current_cred());
 	if (IS_ERR(new_file)) {
 		put_unused_fd(client_fd);
 		client_fd = PTR_ERR(new_file);
@@ -327,11 +327,12 @@ static int process_access_response(struct fsnotify_group *group,
 	struct fanotify_perm_event *event;
 	int fd = response_struct->fd;
 	u32 response = response_struct->response;
+	int errno = fanotify_get_response_errno(response);
 	int ret = info_len;
 	struct fanotify_response_info_audit_rule friar;
 
-	pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__,
-		 group, fd, response, info, info_len);
+	pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n",
+		 __func__, group, fd, response, errno, info, info_len);
 	/*
 	 * make sure the response is valid, if invalid we do nothing and either
 	 * userspace can send a valid response or we will clean it up after the
@@ -342,7 +343,31 @@ static int process_access_response(struct fsnotify_group *group,
 
 	switch (response & FANOTIFY_RESPONSE_ACCESS) {
 	case FAN_ALLOW:
+		if (errno)
+			return -EINVAL;
+		break;
 	case FAN_DENY:
+		/* Custom errno is supported only for pre-content groups */
+		if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT)
+			return -EINVAL;
+
+		/*
+		 * Limit errno to values expected on open(2)/read(2)/write(2)
+		 * of regular files.
+		 */
+		switch (errno) {
+		case 0:
+		case EIO:
+		case EPERM:
+		case EBUSY:
+		case ETXTBSY:
+		case EAGAIN:
+		case ENOSPC:
+		case EDQUOT:
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;
@@ -506,7 +531,7 @@ static int copy_pidfd_info_to_user(int pidfd,
 				   size_t count)
 {
 	struct fanotify_event_info_pidfd info = { };
-	size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN;
+	size_t info_len = FANOTIFY_PIDFD_INFO_LEN;
 
 	if (WARN_ON_ONCE(info_len > count))
 		return -EFAULT;
@@ -521,6 +546,30 @@ static int copy_pidfd_info_to_user(int pidfd,
 	return info_len;
 }
 
+static size_t copy_range_info_to_user(struct fanotify_event *event,
+				      char __user *buf, int count)
+{
+	struct fanotify_perm_event *pevent = FANOTIFY_PERM(event);
+	struct fanotify_event_info_range info = { };
+	size_t info_len = FANOTIFY_RANGE_INFO_LEN;
+
+	if (WARN_ON_ONCE(info_len > count))
+		return -EFAULT;
+
+	if (WARN_ON_ONCE(!pevent->ppos))
+		return -EINVAL;
+
+	info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE;
+	info.hdr.len = info_len;
+	info.offset = *(pevent->ppos);
+	info.count = pevent->count;
+
+	if (copy_to_user(buf, &info, info_len))
+		return -EFAULT;
+
+	return info_len;
+}
+
 static int copy_info_records_to_user(struct fanotify_event *event,
 				     struct fanotify_info *info,
 				     unsigned int info_mode, int pidfd,
@@ -642,6 +691,15 @@ static int copy_info_records_to_user(struct fanotify_event *event,
 		total_bytes += ret;
 	}
 
+	if (fanotify_event_has_access_range(event)) {
+		ret = copy_range_info_to_user(event, buf, count);
+		if (ret < 0)
+			return ret;
+		buf += ret;
+		count -= ret;
+		total_bytes += ret;
+	}
+
 	return total_bytes;
 }
 
@@ -756,12 +814,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	buf += FAN_EVENT_METADATA_LEN;
 	count -= FAN_EVENT_METADATA_LEN;
 
-	if (info_mode) {
-		ret = copy_info_records_to_user(event, info, info_mode, pidfd,
-						buf, count);
-		if (ret < 0)
-			goto out_close_fd;
-	}
+	ret = copy_info_records_to_user(event, info, info_mode, pidfd,
+					buf, count);
+	if (ret < 0)
+		goto out_close_fd;
 
 	if (f)
 		fd_install(fd, f);
@@ -1294,7 +1350,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group)
 }
 
 static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
-					      unsigned int fan_flags)
+					     __u32 mask, unsigned int fan_flags)
 {
 	/*
 	 * Non evictable mark cannot be downgraded to evictable mark.
@@ -1321,6 +1377,11 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
 	    fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
 		return -EEXIST;
 
+	/* For now pre-content events are not generated for directories */
+	mask |= fsn_mark->mask;
+	if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR)
+		return -EEXIST;
+
 	return 0;
 }
 
@@ -1347,7 +1408,7 @@ static int fanotify_add_mark(struct fsnotify_group *group,
 	/*
 	 * Check if requested mark flags conflict with an existing mark flags.
 	 */
-	ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags);
+	ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags);
 	if (ret)
 		goto out;
 
@@ -1409,6 +1470,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
 	unsigned int class = flags & FANOTIFY_CLASS_BITS;
 	unsigned int internal_flags = 0;
+	struct file *file;
 
 	pr_debug("%s: flags=%x event_f_flags=%x\n",
 		 __func__, flags, event_f_flags);
@@ -1477,7 +1539,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	    (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID)))
 		return -EINVAL;
 
-	f_flags = O_RDWR | __FMODE_NONOTIFY;
+	f_flags = O_RDWR;
 	if (flags & FAN_CLOEXEC)
 		f_flags |= O_CLOEXEC;
 	if (flags & FAN_NONBLOCK)
@@ -1555,10 +1617,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 			goto out_destroy_group;
 	}
 
-	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
+	fd = get_unused_fd_flags(f_flags);
 	if (fd < 0)
 		goto out_destroy_group;
 
+	file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group,
+					f_flags, FMODE_NONOTIFY);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		fd = PTR_ERR(file);
+		goto out_destroy_group;
+	}
+	fd_install(fd, file);
 	return fd;
 
 out_destroy_group:
@@ -1638,12 +1708,24 @@ static int fanotify_events_supported(struct fsnotify_group *group,
 				     unsigned int flags)
 {
 	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+	bool is_dir = d_is_dir(path->dentry);
 	/* Strict validation of events in non-dir inode mask with v5.17+ APIs */
 	bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) ||
 				 (mask & FAN_RENAME) ||
 				 (flags & FAN_MARK_IGNORE);
 
 	/*
+	 * Filesystems need to opt-into pre-content evnets (a.k.a HSM)
+	 * and they are only supported on regular files and directories.
+	 */
+	if (mask & FANOTIFY_PRE_CONTENT_EVENTS) {
+		if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM))
+			return -EOPNOTSUPP;
+		if (!is_dir && !d_is_reg(path->dentry))
+			return -EINVAL;
+	}
+
+	/*
 	 * Some filesystems such as 'proc' acquire unusual locks when opening
 	 * files. For them fanotify permission events have high chances of
 	 * deadlocking the system - open done when reporting fanotify event
@@ -1675,7 +1757,7 @@ static int fanotify_events_supported(struct fsnotify_group *group,
 	 * but because we always allowed it, error only when using new APIs.
 	 */
 	if (strict_dir_events && mark_type == FAN_MARK_INODE &&
-	    !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
+	    !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
 		return -ENOTDIR;
 
 	return 0;
@@ -1776,10 +1858,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 		return -EPERM;
 
 	/*
-	 * Permission events require minimum priority FAN_CLASS_CONTENT.
+	 * Permission events are not allowed for FAN_CLASS_NOTIF.
+	 * Pre-content permission events are not allowed for FAN_CLASS_CONTENT.
 	 */
 	if (mask & FANOTIFY_PERM_EVENTS &&
-	    group->priority < FSNOTIFY_PRIO_CONTENT)
+	    group->priority == FSNOTIFY_PRIO_NORMAL)
+		return -EINVAL;
+	else if (mask & FANOTIFY_PRE_CONTENT_EVENTS &&
+		 group->priority == FSNOTIFY_PRIO_CONTENT)
 		return -EINVAL;
 
 	if (mask & FAN_FS_ERROR &&
@@ -1814,6 +1900,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
 		return -EINVAL;
 
+	/* Pre-content events are not currently generated for directories. */
+	if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR)
+		return -EINVAL;
+
 	if (mark_cmd == FAN_MARK_FLUSH) {
 		if (mark_type == FAN_MARK_MOUNT)
 			fsnotify_clear_vfsmount_marks_by_group(group);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index f976949d2634..8ee495a58d0a 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -193,7 +193,7 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
 	return mask & marks_mask;
 }
 
-/* Are there any inode/mount/sb objects that are interested in this event? */
+/* Are there any inode/mount/sb objects that watch for these events? */
 static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
 					   __u32 mask)
 {
@@ -203,6 +203,24 @@ static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
 	return mask & marks_mask & ALL_FSNOTIFY_EVENTS;
 }
 
+/* Report pre-content event with optional range info */
+int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
+			 size_t count)
+{
+	struct file_range range;
+
+	/* Report page aligned range only when pos is known */
+	if (!ppos)
+		return fsnotify_path(path, FS_PRE_ACCESS);
+
+	range.path = path;
+	range.pos = PAGE_ALIGN_DOWN(*ppos);
+	range.count = PAGE_ALIGN(*ppos + count) - range.pos;
+
+	return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range,
+			       FSNOTIFY_EVENT_FILE_RANGE);
+}
+
 /*
  * Notify this dentry's parent about a child's events with child name info
  * if parent is watching or if inode/sb/mount are interested in events with
@@ -623,11 +641,72 @@ out:
 }
 EXPORT_SYMBOL_GPL(fsnotify);
 
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+/*
+ * At open time we check fsnotify_sb_has_priority_watchers() and set the
+ * FMODE_NONOTIFY_ mode bits accordignly.
+ * Later, fsnotify permission hooks do not check if there are permission event
+ * watches, but that there were permission event watches at open time.
+ */
+void file_set_fsnotify_mode(struct file *file)
+{
+	struct dentry *dentry = file->f_path.dentry, *parent;
+	struct super_block *sb = dentry->d_sb;
+	__u32 mnt_mask, p_mask;
+
+	/* Is it a file opened by fanotify? */
+	if (FMODE_FSNOTIFY_NONE(file->f_mode))
+		return;
+
+	/*
+	 * Permission events is a super set of pre-content events, so if there
+	 * are no permission event watchers, there are also no pre-content event
+	 * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit.
+	 */
+	if (likely(!fsnotify_sb_has_priority_watchers(sb,
+						FSNOTIFY_PRIO_CONTENT))) {
+		file->f_mode |= FMODE_NONOTIFY_PERM;
+		return;
+	}
+
+	/*
+	 * If there are permission event watchers but no pre-content event
+	 * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
+	 */
+	if ((!d_is_dir(dentry) && !d_is_reg(dentry)) ||
+	    likely(!fsnotify_sb_has_priority_watchers(sb,
+						FSNOTIFY_PRIO_PRE_CONTENT))) {
+		file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
+		return;
+	}
+
+	/*
+	 * OK, there are some pre-content watchers. Check if anybody is
+	 * watching for pre-content events on *this* file.
+	 */
+	mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
+	if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask,
+				     FSNOTIFY_PRE_CONTENT_EVENTS)))
+		return;
+
+	/* Is parent watching for pre-content events on this file? */
+	if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
+		parent = dget_parent(dentry);
+		p_mask = fsnotify_inode_watches_children(d_inode(parent));
+		dput(parent);
+		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)
+			return;
+	}
+	/* Nobody watching for pre-content events from this file */
+	file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
+}
+#endif
+
 static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)