1 files changed, 273 insertions, 42 deletions

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index f8acddcf54fb..454d8e466958 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -17,6 +17,25 @@
 #include <linux/slab.h>
 #include <linux/bug.h>
 
+/* Are there any inode/mount/sb objects watched with priority prio or above? */
+static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb,
+						     int prio)
+{
+	struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+
+	/* Were any marks ever added to any object on this sb? */
+	if (!sbinfo)
+		return false;
+
+	return atomic_long_read(&sbinfo->watched_objects[prio]);
+}
+
+/* Are there any inode/mount/sb objects that are being watched at all? */
+static inline bool fsnotify_sb_has_watchers(struct super_block *sb)
+{
+	return fsnotify_sb_has_priority_watchers(sb, 0);
+}
+
 /*
  * Notify this @dir inode about a change in a child directory entry.
  * The directory entry may have turned positive or negative or its inode may
@@ -26,21 +45,27 @@
  * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only
  * the child is interested and not the parent.
  */
-static inline void fsnotify_name(struct inode *dir, __u32 mask,
-				 struct inode *child,
-				 const struct qstr *name, u32 cookie)
+static inline int fsnotify_name(__u32 mask, const void *data, int data_type,
+				struct inode *dir, const struct qstr *name,
+				u32 cookie)
 {
-	fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie);
+	if (!fsnotify_sb_has_watchers(dir->i_sb))
+		return 0;
+
+	return fsnotify(mask, data, data_type, dir, name, NULL, cookie);
 }
 
 static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 				   __u32 mask)
 {
-	fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0);
+	fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0);
 }
 
 static inline void fsnotify_inode(struct inode *inode, __u32 mask)
 {
+	if (!fsnotify_sb_has_watchers(inode->i_sb))
+		return;
+
 	if (S_ISDIR(inode->i_mode))
 		mask |= FS_ISDIR;
 
@@ -53,6 +78,9 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 {
 	struct inode *inode = d_inode(dentry);
 
+	if (!fsnotify_sb_has_watchers(inode->i_sb))
+		return 0;
+
 	if (S_ISDIR(inode->i_mode)) {
 		mask |= FS_ISDIR;
 
@@ -77,44 +105,161 @@ notify_child:
  */
 static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
 {
-	fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE);
+	fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY);
+}
+
+static inline int fsnotify_path(const struct path *path, __u32 mask)
+{
+	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
 static inline int fsnotify_file(struct file *file, __u32 mask)
 {
-	const struct path *path = &file->f_path;
+	/*
+	 * FMODE_NONOTIFY are fds generated by fanotify itself which should not
+	 * generate new events. We also don't want to generate events for
+	 * FMODE_PATH fds (involves open & close events) as they are just
+	 * handle creation / destruction events and not "real" file events.
+	 */
+	if (FMODE_FSNOTIFY_NONE(file->f_mode))
+		return 0;
+
+	return fsnotify_path(&file->f_path, mask);
+}
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+
+void file_set_fsnotify_mode_from_watchers(struct file *file);
+
+/*
+ * fsnotify_file_area_perm - permission hook before access to file range
+ */
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	/*
+	 * filesystem may be modified in the context of permission events
+	 * (e.g. by HSM filling a file on access), so sb freeze protection
+	 * must not be held.
+	 */
+	lockdep_assert_once(file_write_not_started(file));
+
+	if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS)))
+		return 0;
 
-	if (file->f_mode & FMODE_NONOTIFY)
+	if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
 		return 0;
 
-	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
+	/*
+	 * read()/write() and other types of access generate pre-content events.
+	 */
+	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) {
+		int ret = fsnotify_pre_content(&file->f_path, ppos, count);
+
+		if (ret)
+			return ret;
+	}
+
+	if (!(perm_mask & MAY_READ))
+		return 0;
+
+	/*
+	 * read() also generates the legacy FS_ACCESS_PERM event, so content
+	 * scanners can inspect the content filled by pre-content event.
+	 */
+	return fsnotify_path(&file->f_path, FS_ACCESS_PERM);
 }
 
-/* Simple call site for access decisions */
-static inline int fsnotify_perm(struct file *file, int mask)
+/*
+ * fsnotify_mmap_perm - permission hook before mmap of file range
+ */
+static inline int fsnotify_mmap_perm(struct file *file, int prot,
+				     const loff_t off, size_t len)
 {
-	int ret;
-	__u32 fsnotify_mask = 0;
+	/*
+	 * mmap() generates only pre-content events.
+	 */
+	if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode)))
+		return 0;
+
+	return fsnotify_pre_content(&file->f_path, &off, len);
+}
+
+/*
+ * fsnotify_truncate_perm - permission hook before file truncate
+ */
+static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
+{
+	struct inode *inode = d_inode(path->dentry);
 
-	if (!(mask & (MAY_READ | MAY_OPEN)))
+	if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) ||
+	    !fsnotify_sb_has_priority_watchers(inode->i_sb,
+					       FSNOTIFY_PRIO_PRE_CONTENT))
 		return 0;
 
-	if (mask & MAY_OPEN) {
-		fsnotify_mask = FS_OPEN_PERM;
+	return fsnotify_pre_content(path, &length, 0);
+}
+
+/*
+ * fsnotify_file_perm - permission hook before file access (unknown range)
+ */
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return fsnotify_file_area_perm(file, perm_mask, NULL, 0);
+}
+
+/*
+ * fsnotify_open_perm - permission hook before file open
+ */
+static inline int fsnotify_open_perm(struct file *file)
+{
+	int ret;
 
-		if (file->f_flags & __FMODE_EXEC) {
-			ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+	if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
+		return 0;
 
-			if (ret)
-				return ret;
-		}
-	} else if (mask & MAY_READ) {
-		fsnotify_mask = FS_ACCESS_PERM;
+	if (file->f_flags & __FMODE_EXEC) {
+		ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
+		if (ret)
+			return ret;
 	}
 
-	return fsnotify_file(file, fsnotify_mask);
+	return fsnotify_path(&file->f_path, FS_OPEN_PERM);
+}
+
+#else
+static inline void file_set_fsnotify_mode_from_watchers(struct file *file)
+{
+}
+
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	return 0;
 }
 
+static inline int fsnotify_mmap_perm(struct file *file, int prot,
+				     const loff_t off, size_t len)
+{
+	return 0;
+}
+
+static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
+{
+	return 0;
+}
+
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return 0;
+}
+
+static inline int fsnotify_open_perm(struct file *file)
+{
+	return 0;
+}
+#endif
+
 /*
  * fsnotify_link_count - inode's link count changed
  */
@@ -135,18 +280,23 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 	u32 fs_cookie = fsnotify_get_cookie();
 	__u32 old_dir_mask = FS_MOVED_FROM;
 	__u32 new_dir_mask = FS_MOVED_TO;
+	__u32 rename_mask = FS_RENAME;
 	const struct qstr *new_name = &moved->d_name;
 
-	if (old_dir == new_dir)
-		old_dir_mask |= FS_DN_RENAME;
-
 	if (isdir) {
 		old_dir_mask |= FS_ISDIR;
 		new_dir_mask |= FS_ISDIR;
+		rename_mask |= FS_ISDIR;
 	}
 
-	fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie);
-	fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie);
+	/* Event with information about both old and new parent+name */
+	fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY,
+		      old_dir, old_name, 0);
+
+	fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE,
+		      old_dir, old_name, fs_cookie);
+	fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE,
+		      new_dir, new_name, fs_cookie);
 
 	if (target)
 		fsnotify_link_count(target);
@@ -170,6 +320,11 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt)
 	__fsnotify_vfsmount_delete(mnt);
 }
 
+static inline void fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{
+	__fsnotify_mntns_delete(mntns);
+}
+
 /*
  * fsnotify_inoderemove - an inode is going away
  */
@@ -181,16 +336,22 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 
 /*
  * fsnotify_create - 'name' was linked in
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate
+ * ->d_inode later
  */
-static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
+static inline void fsnotify_create(struct inode *dir, struct dentry *dentry)
 {
-	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+	audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_dirent(inode, dentry, FS_CREATE);
+	fsnotify_dirent(dir, dentry, FS_CREATE);
 }
 
 /*
  * fsnotify_link - new hardlink in 'inode' directory
+ *
+ * Caller must make sure that new_dentry->d_name is stable.
  * Note: We have to pass also the linked inode ptr as some filesystems leave
  *   new_dentry->d_inode NULL and instantiate inode pointer later
  */
@@ -200,7 +361,45 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode,
 	fsnotify_link_count(inode);
 	audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0);
+	fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE,
+		      dir, &new_dentry->d_name, 0);
+}
+
+/*
+ * fsnotify_delete - @dentry was unlinked and unhashed
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ *
+ * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode
+ * as this may be called after d_delete() and old_dentry may be negative.
+ */
+static inline void fsnotify_delete(struct inode *dir, struct inode *inode,
+				   struct dentry *dentry)
+{
+	__u32 mask = FS_DELETE;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
+
+	fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name,
+		      0);
+}
+
+/**
+ * d_delete_notify - delete a dentry and call fsnotify_delete()
+ * @dentry: The dentry to delete
+ *
+ * This helper is used to guaranty that the unlinked inode cannot be found
+ * by lookup of this name after fsnotify_delete() event has been delivered.
+ */
+static inline void d_delete_notify(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+
+	ihold(inode);
+	d_delete(dentry);
+	fsnotify_delete(dir, inode, dentry);
+	iput(inode);
 }
 
 /*
@@ -210,20 +409,24 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode,
  */
 static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry)
 {
-	/* Expected to be called before d_delete() */
-	WARN_ON_ONCE(d_is_negative(dentry));
+	if (WARN_ON_ONCE(d_is_negative(dentry)))
+		return;
 
-	fsnotify_dirent(dir, dentry, FS_DELETE);
+	fsnotify_delete(dir, d_inode(dentry), dentry);
 }
 
 /*
  * fsnotify_mkdir - directory 'name' was created
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate
+ * ->d_inode later
  */
-static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
+static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry)
 {
-	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+	audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR);
+	fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR);
 }
 
 /*
@@ -233,10 +436,10 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
  */
 static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	/* Expected to be called before d_delete() */
-	WARN_ON_ONCE(d_is_negative(dentry));
+	if (WARN_ON_ONCE(d_is_negative(dentry)))
+		return;
 
-	fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR);
+	fsnotify_delete(dir, d_inode(dentry), dentry);
 }
 
 /*
@@ -317,4 +520,32 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 		fsnotify_dentry(dentry, mask);
 }
 
+static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
+				    int error)
+{
+	struct fs_error_report report = {
+		.error = error,
+		.inode = inode,
+		.sb = sb,
+	};
+
+	return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR,
+			NULL, NULL, NULL, 0);
+}
+
+static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	fsnotify_mnt(FS_MNT_ATTACH, ns, mnt);
+}
+
+static inline void fsnotify_mnt_detach(struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	fsnotify_mnt(FS_MNT_DETACH, ns, mnt);
+}
+
+static inline void fsnotify_mnt_move(struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	fsnotify_mnt(FS_MNT_MOVE, ns, mnt);
+}
+
 #endif	/* _LINUX_FS_NOTIFY_H */