1 files changed, 126 insertions, 8 deletions
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index f976949d2634..e2b4f17a48bb 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -28,6 +28,11 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
 	fsnotify_clear_marks_by_mount(mnt);
 }
 
+void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{
+	fsnotify_clear_marks_by_mntns(mntns);
+}
+
 /**
  * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
  * @sb: superblock being unmounted.
@@ -193,7 +198,7 @@ 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 +208,24 @@ 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
@@ -402,7 +425,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
 				     file_name, cookie, iter_info);
 }
 
-static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
+static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp)
 {
 	struct fsnotify_mark_connector *conn;
 	struct hlist_node *node = NULL;
@@ -520,14 +543,15 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 {
 	const struct path *path = fsnotify_data_path(data, data_type);
 	struct super_block *sb = fsnotify_data_sb(data, data_type);
-	struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+	const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
+	struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL;
 	struct fsnotify_iter_info iter_info = {};
 	struct mount *mnt = NULL;
 	struct inode *inode2 = NULL;
 	struct dentry *moved;
 	int inode2_type;
 	int ret = 0;
-	__u32 test_mask, marks_mask;
+	__u32 test_mask, marks_mask = 0;
 
 	if (path)
 		mnt = real_mount(path->mnt);
@@ -560,17 +584,20 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 	if ((!sbinfo || !sbinfo->sb_marks) &&
 	    (!mnt || !mnt->mnt_fsnotify_marks) &&
 	    (!inode || !inode->i_fsnotify_marks) &&
-	    (!inode2 || !inode2->i_fsnotify_marks))
+	    (!inode2 || !inode2->i_fsnotify_marks) &&
+	    (!mnt_data || !mnt_data->ns->n_fsnotify_marks))
 		return 0;
 
-	marks_mask = READ_ONCE(sb->s_fsnotify_mask);
+	if (sb)
+		marks_mask |= READ_ONCE(sb->s_fsnotify_mask);
 	if (mnt)
 		marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask);
 	if (inode)
 		marks_mask |= READ_ONCE(inode->i_fsnotify_mask);
 	if (inode2)
 		marks_mask |= READ_ONCE(inode2->i_fsnotify_mask);
-
+	if (mnt_data)
+		marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask);
 
 	/*
 	 * If this is a modify event we may need to clear some ignore masks.
@@ -600,6 +627,10 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		iter_info.marks[inode2_type] =
 			fsnotify_first_mark(&inode2->i_fsnotify_marks);
 	}
+	if (mnt_data) {
+		iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] =
+			fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks);
+	}
 
 	/*
 	 * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
@@ -623,11 +654,98 @@ 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_from_watchers(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_set_fsnotify_mode(file, 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_set_fsnotify_mode(file, 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))) {
+		/* Enable pre-content events */
+		file_set_fsnotify_mode(file, 0);
+		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) {
+			/* Enable pre-content events */
+			file_set_fsnotify_mode(file, 0);
+			return;
+		}
+	}
+	/* Nobody watching for pre-content events from this file */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
+}
+#endif
+
+void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	struct fsnotify_mnt data = {
+		.ns = ns,
+		.mnt_id = real_mount(mnt)->mnt_id_unique,
+	};
+
+	if (WARN_ON_ONCE(!ns))
+		return;
+
+	/*
+	 * This is an optimization as well as making sure fsnotify_init() has
+	 * been called.
+	 */
+	if (!ns->n_fsnotify_marks)
+		return;
+
+	fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0);
+}
+
 static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)