--- zzzz-none-000/linux-5.4.213/fs/notify/fanotify/fanotify_user.c 2022-09-15 10:04:56.000000000 +0000 +++ miami-7690-761/linux-5.4.213/fs/notify/fanotify/fanotify_user.c 2024-05-29 11:20:02.000000000 +0000 @@ -46,32 +46,61 @@ extern const struct fsnotify_ops fanotify_fsnotify_ops; struct kmem_cache *fanotify_mark_cache __read_mostly; -struct kmem_cache *fanotify_event_cachep __read_mostly; +struct kmem_cache *fanotify_fid_event_cachep __read_mostly; +struct kmem_cache *fanotify_path_event_cachep __read_mostly; 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_event_info_len(struct fanotify_event *event) +static int fanotify_fid_info_len(int fh_len, int name_len) { - if (!fanotify_event_has_fid(event)) - return 0; + int info_len = fh_len; + + if (name_len) + info_len += name_len + 1; - return roundup(sizeof(struct fanotify_event_info_fid) + - sizeof(struct file_handle) + event->fh_len, - FANOTIFY_EVENT_ALIGN); + return roundup(FANOTIFY_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN); +} + +static int fanotify_event_info_len(unsigned int fid_mode, + struct fanotify_event *event) +{ + struct fanotify_info *info = fanotify_event_info(event); + int dir_fh_len = fanotify_event_dir_fh_len(event); + int fh_len = fanotify_event_object_fh_len(event); + int info_len = 0; + int dot_len = 0; + + if (dir_fh_len) { + info_len += fanotify_fid_info_len(dir_fh_len, info->name_len); + } else if ((fid_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) { + /* + * With group flag FAN_REPORT_NAME, if name was not recorded in + * event on a directory, we will report the name ".". + */ + dot_len = 1; + } + + if (fh_len) + info_len += fanotify_fid_info_len(fh_len, dot_len); + + return info_len; } /* - * Get an fsnotify notification event if one exists and is small + * Get an fanotify notification event if one exists and is small * enough to fit in "count". Return an error pointer if the count * is not large enough. When permission event is dequeued, its state is * updated accordingly. */ -static struct fsnotify_event *get_one_event(struct fsnotify_group *group, +static struct fanotify_event *get_one_event(struct fsnotify_group *group, size_t count) { size_t event_size = FAN_EVENT_METADATA_LEN; - struct fsnotify_event *fsn_event = NULL; + struct fanotify_event *event = NULL; + unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); pr_debug("%s: group=%p count=%zd\n", __func__, group, count); @@ -79,32 +108,29 @@ if (fsnotify_notify_queue_is_empty(group)) goto out; - if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { - event_size += fanotify_event_info_len( + if (fid_mode) { + event_size += fanotify_event_info_len(fid_mode, FANOTIFY_E(fsnotify_peek_first_event(group))); } if (event_size > count) { - fsn_event = ERR_PTR(-EINVAL); + event = ERR_PTR(-EINVAL); goto out; } - fsn_event = fsnotify_remove_first_event(group); - if (fanotify_is_perm_event(FANOTIFY_E(fsn_event)->mask)) - FANOTIFY_PE(fsn_event)->state = FAN_EVENT_REPORTED; + event = FANOTIFY_E(fsnotify_remove_first_event(group)); + if (fanotify_is_perm_event(event->mask)) + FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED; out: spin_unlock(&group->notification_lock); - return fsn_event; + return event; } -static int create_fd(struct fsnotify_group *group, - struct fanotify_event *event, +static int create_fd(struct fsnotify_group *group, struct path *path, struct file **file) { int client_fd; struct file *new_file; - pr_debug("%s: group=%p event=%p\n", __func__, group, event); - client_fd = get_unused_fd_flags(group->fanotify_data.f_flags); if (client_fd < 0) return client_fd; @@ -113,14 +139,9 @@ * we need a new file handle for the userspace program so it can read even if it was * originally opened O_WRONLY. */ - /* it's possible this event was an overflow event. in that case dentry and mnt - * are NULL; That's fine, just don't call dentry open */ - if (event->path.dentry && event->path.mnt) - new_file = dentry_open(&event->path, - group->fanotify_data.f_flags | FMODE_NONOTIFY, - current_cred()); - else - new_file = ERR_PTR(-EOVERFLOW); + new_file = dentry_open(path, + group->fanotify_data.f_flags | FMODE_NONOTIFY, + current_cred()); if (IS_ERR(new_file)) { /* * we still send an event even if we can't open the file. this @@ -204,90 +225,134 @@ return -ENOENT; } -static int copy_fid_to_user(struct fanotify_event *event, char __user *buf) +static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, + int info_type, 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; - size_t fh_len = event->fh_len; - size_t len = fanotify_event_info_len(event); + unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf; + size_t fh_len = fh ? fh->len : 0; + size_t info_len = fanotify_fid_info_len(fh_len, name_len); + size_t len = info_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 (!len) + if (!fh_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 variable sized file handle + * and optionally followed by variable sized filename. + */ + switch (info_type) { + case FAN_EVENT_INFO_TYPE_FID: + case FAN_EVENT_INFO_TYPE_DFID: + if (WARN_ON_ONCE(name_len)) + return -EFAULT; + break; + case FAN_EVENT_INFO_TYPE_DFID_NAME: + if (WARN_ON_ONCE(!name || !name_len)) + return -EFAULT; + break; + default: return -EFAULT; + } - /* Copy event info fid header followed by vaiable sized file handle */ - info.hdr.info_type = FAN_EVENT_INFO_TYPE_FID; + info.hdr.info_type = info_type; info.hdr.len = len; - info.fsid = event->fid.fsid; + info.fsid = *fsid; if (copy_to_user(buf, &info, sizeof(info))) return -EFAULT; buf += sizeof(info); len -= sizeof(info); - handle.handle_type = event->fh_type; + 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))) return -EFAULT; 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 = fanotify_event_fh(event); + fh_buf = fanotify_fh_buf(fh); if (fh_len <= FANOTIFY_INLINE_FH_LEN) { - memcpy(bounce, fh, fh_len); - fh = bounce; + memcpy(bounce, fh_buf, fh_len); + fh_buf = bounce; } - if (copy_to_user(buf, fh, 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, - struct fsnotify_event *fsn_event, + struct fanotify_event *event, char __user *buf, size_t count) { struct fanotify_event_metadata metadata; - struct fanotify_event *event; + struct path *path = fanotify_event_path(event); + struct fanotify_info *info = fanotify_event_info(event); + unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); struct file *f = NULL; int ret, fd = FAN_NOFD; + int info_type = 0; - pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event); + pr_debug("%s: group=%p event=%p\n", __func__, group, event); - event = container_of(fsn_event, struct fanotify_event, fse); - metadata.event_len = FAN_EVENT_METADATA_LEN; + metadata.event_len = FAN_EVENT_METADATA_LEN + + fanotify_event_info_len(fid_mode, 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_has_path(event)) { - fd = create_fd(group, event, &f); + if (path && path->mnt && path->dentry) { + fd = create_fd(group, path, &f); if (fd < 0) return fd; - } else if (fanotify_event_has_fid(event)) { - metadata.event_len += fanotify_event_info_len(event); } metadata.fd = fd; ret = -EFAULT; /* * Sanity check copy size in case get_one_event() and - * fill_event_metadata() event_len sizes ever get out of sync. + * event_len sizes ever get out of sync. */ if (WARN_ON_ONCE(metadata.event_len > count)) goto out_close_fd; @@ -295,15 +360,76 @@ 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_PE(fsn_event)->fd = fd; + FANOTIFY_PERM(event)->fd = fd; - if (fanotify_event_has_path(event)) { + if (f) fd_install(fd, f); - } else if (fanotify_event_has_fid(event)) { - ret = copy_fid_to_user(event, buf + FAN_EVENT_METADATA_LEN); + + /* Event info records order is: dir fid + name, child fid */ + if (fanotify_event_dir_fh_len(event)) { + info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME : + FAN_EVENT_INFO_TYPE_DFID; + ret = copy_info_to_user(fanotify_event_fsid(event), + fanotify_info_dir_fh(info), + info_type, fanotify_info_name(info), + info->name_len, buf, count); + if (ret < 0) + return ret; + + buf += ret; + count -= ret; + } + + if (fanotify_event_object_fh_len(event)) { + const char *dot = NULL; + int dot_len = 0; + + if (fid_mode == FAN_REPORT_FID || info_type) { + /* + * With only group flag FAN_REPORT_FID only type FID is + * reported. Second info record type is always FID. + */ + info_type = FAN_EVENT_INFO_TYPE_FID; + } else if ((fid_mode & FAN_REPORT_NAME) && + (event->mask & FAN_ONDIR)) { + /* + * With group flag FAN_REPORT_NAME, if name was not + * recorded in an event on a directory, report the + * name "." with info type DFID_NAME. + */ + info_type = FAN_EVENT_INFO_TYPE_DFID_NAME; + dot = "."; + dot_len = 1; + } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) || + (event->mask & FAN_ONDIR)) { + /* + * With group flag FAN_REPORT_DIR_FID, a single info + * record has type DFID for directory entry modification + * event and for event on a directory. + */ + info_type = FAN_EVENT_INFO_TYPE_DFID; + } else { + /* + * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID, + * a single info record has type FID for event on a + * non-directory, when there is no directory to report. + * For example, on FAN_DELETE_SELF event. + */ + info_type = FAN_EVENT_INFO_TYPE_FID; + } + + ret = copy_info_to_user(fanotify_event_fsid(event), + fanotify_event_object_fh(event), + info_type, dot, dot_len, buf, count); if (ret < 0) return ret; + + buf += ret; + count -= ret; } return metadata.event_len; @@ -335,7 +461,7 @@ size_t count, loff_t *pos) { struct fsnotify_group *group; - struct fsnotify_event *kevent; + struct fanotify_event *event; char __user *start; int ret; DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -347,13 +473,18 @@ add_wait_queue(&group->notification_waitq, &wait); while (1) { - kevent = get_one_event(group, count); - if (IS_ERR(kevent)) { - ret = PTR_ERR(kevent); + /* + * User can supply arbitrarily large buffer. Avoid softlockups + * in case there are lots of available events. + */ + cond_resched(); + event = get_one_event(group, count); + if (IS_ERR(event)) { + ret = PTR_ERR(event); break; } - if (!kevent) { + if (!event) { ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; @@ -369,7 +500,7 @@ continue; } - ret = copy_event_to_user(group, kevent, buf, count); + ret = copy_event_to_user(group, event, buf, count); if (unlikely(ret == -EOPENSTALE)) { /* * We cannot report events with stale fd so drop it. @@ -384,17 +515,17 @@ * Permission events get queued to wait for response. Other * events can be destroyed now. */ - if (!fanotify_is_perm_event(FANOTIFY_E(kevent)->mask)) { - fsnotify_destroy_event(group, kevent); + if (!fanotify_is_perm_event(event->mask)) { + fsnotify_destroy_event(group, &event->fse); } else { if (ret <= 0) { spin_lock(&group->notification_lock); finish_permission_event(group, - FANOTIFY_PE(kevent), FAN_DENY); + FANOTIFY_PERM(event), FAN_DENY); wake_up(&group->fanotify_data.access_waitq); } else { spin_lock(&group->notification_lock); - list_add_tail(&kevent->list, + list_add_tail(&event->fse.list, &group->fanotify_data.access_list); spin_unlock(&group->notification_lock); } @@ -422,8 +553,10 @@ group = file->private_data; - if (count > sizeof(response)) - count = sizeof(response); + if (count < sizeof(response)) + return -EINVAL; + + count = sizeof(response); pr_debug("%s: group=%p count=%zu\n", __func__, group, count); @@ -440,8 +573,6 @@ static int fanotify_release(struct inode *ignored, struct file *file) { struct fsnotify_group *group = file->private_data; - struct fanotify_perm_event *event; - struct fsnotify_event *fsn_event; /* * Stop new events from arriving in the notification queue. since @@ -456,6 +587,8 @@ */ spin_lock(&group->notification_lock); while (!list_empty(&group->fanotify_data.access_list)) { + struct fanotify_perm_event *event; + event = list_first_entry(&group->fanotify_data.access_list, struct fanotify_perm_event, fae.fse.list); list_del_init(&event->fae.fse.list); @@ -469,12 +602,14 @@ * response is consumed and fanotify_get_response() returns. */ while (!fsnotify_notify_queue_is_empty(group)) { - fsn_event = fsnotify_remove_first_event(group); - if (!(FANOTIFY_E(fsn_event)->mask & FANOTIFY_PERM_EVENTS)) { + struct fanotify_event *event; + + event = FANOTIFY_E(fsnotify_remove_first_event(group)); + if (!(event->mask & FANOTIFY_PERM_EVENTS)) { spin_unlock(&group->notification_lock); - fsnotify_destroy_event(group, fsn_event); + fsnotify_destroy_event(group, &event->fse); } else { - finish_permission_event(group, FANOTIFY_PE(fsn_event), + finish_permission_event(group, FANOTIFY_PERM(event), FAN_ALLOW); } spin_lock(&group->notification_lock); @@ -582,12 +717,13 @@ } static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, - __u32 mask, - unsigned int flags, - int *destroy) + __u32 mask, unsigned int flags, + __u32 umask, int *destroy) { __u32 oldmask = 0; + /* umask bits cannot be removed by user */ + mask &= ~umask; spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { oldmask = fsn_mark->mask; @@ -595,7 +731,13 @@ } else { fsn_mark->ignored_mask &= ~mask; } - *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask); + /* + * We need to keep the mark around even if remaining mask cannot + * result in any events (e.g. mask == FAN_ONDIR) to support incremenal + * changes to the mask. + * Destroy mark when only umask bits remain. + */ + *destroy = !((fsn_mark->mask | fsn_mark->ignored_mask) & ~umask); spin_unlock(&fsn_mark->lock); return mask & oldmask; @@ -603,7 +745,7 @@ static int fanotify_remove_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, __u32 mask, - unsigned int flags) + unsigned int flags, __u32 umask) { struct fsnotify_mark *fsn_mark = NULL; __u32 removed; @@ -617,7 +759,7 @@ } removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags, - &destroy_mark); + umask, &destroy_mark); if (removed & fsnotify_conn_mask(fsn_mark->connector)) fsnotify_recalc_mask(fsn_mark->connector); if (destroy_mark) @@ -633,25 +775,26 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt, __u32 mask, - unsigned int flags) + unsigned int flags, __u32 umask) { return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks, - mask, flags); + mask, flags, umask); } static int fanotify_remove_sb_mark(struct fsnotify_group *group, - struct super_block *sb, __u32 mask, - unsigned int flags) + struct super_block *sb, __u32 mask, + unsigned int flags, __u32 umask) { - return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask, flags); + return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask, + flags, umask); } static int fanotify_remove_inode_mark(struct fsnotify_group *group, struct inode *inode, __u32 mask, - unsigned int flags) + unsigned int flags, __u32 umask) { return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask, - flags); + flags, umask); } static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, @@ -762,13 +905,28 @@ FSNOTIFY_OBJ_TYPE_INODE, mask, flags, fsid); } +static struct fsnotify_event *fanotify_alloc_overflow_event(void) +{ + struct fanotify_event *oevent; + + oevent = kmalloc(sizeof(*oevent), GFP_KERNEL_ACCOUNT); + if (!oevent) + return NULL; + + fanotify_init_event(oevent, 0, FS_Q_OVERFLOW); + oevent->type = FANOTIFY_EVENT_TYPE_OVERFLOW; + + return &oevent->fse; +} + /* fanotify syscalls */ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) { struct fsnotify_group *group; int f_flags, fd; struct user_struct *user; - struct fanotify_event *oevent; + unsigned int fid_mode = flags & FANOTIFY_FID_BITS; + unsigned int class = flags & FANOTIFY_CLASS_BITS; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -795,8 +953,14 @@ return -EINVAL; } - if ((flags & FAN_REPORT_FID) && - (flags & FANOTIFY_CLASS_BITS) != FAN_CLASS_NOTIF) + if (fid_mode && class != FAN_CLASS_NOTIF) + return -EINVAL; + + /* + * Child name is reported with parent fid so requires dir fid. + * We can report both child fid and dir fid with or without name. + */ + if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID)) return -EINVAL; user = get_current_user(); @@ -823,20 +987,18 @@ atomic_inc(&user->fanotify_listeners); group->memcg = get_mem_cgroup_from_mm(current->mm); - oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL, - FSNOTIFY_EVENT_NONE, NULL); - if (unlikely(!oevent)) { + group->overflow_event = fanotify_alloc_overflow_event(); + if (unlikely(!group->overflow_event)) { fd = -ENOMEM; goto out_destroy_group; } - group->overflow_event = &oevent->fse; if (force_o_largefile()) event_f_flags |= O_LARGEFILE; group->fanotify_data.f_flags = event_f_flags; init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - switch (flags & FANOTIFY_CLASS_BITS) { + switch (class) { case FAN_CLASS_NOTIF: group->priority = FS_PRIO_0; break; @@ -886,16 +1048,15 @@ return fd; } -/* Check if filesystem can encode a unique fid */ -static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) +static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) { __kernel_fsid_t root_fsid; int err; /* - * Make sure path is not in filesystem with zero fsid (e.g. tmpfs). + * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse). */ - err = vfs_get_fsid(path->dentry, fsid); + err = vfs_get_fsid(dentry, fsid); if (err) return err; @@ -903,10 +1064,10 @@ return -ENODEV; /* - * Make sure path is not inside a filesystem subvolume (e.g. btrfs) + * Make sure dentry is not of a filesystem subvolume (e.g. btrfs) * which uses a different fsid than sb root. */ - err = vfs_get_fsid(path->dentry->d_sb->s_root, &root_fsid); + err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid); if (err) return err; @@ -914,15 +1075,20 @@ root_fsid.val[1] != fsid->val[1]) return -EXDEV; + return 0; +} + +/* Check if filesystem can encode a unique fid */ +static int fanotify_test_fid(struct dentry *dentry) +{ + const struct export_operations *nop = dentry->d_sb->s_export_op; + /* - * 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. + * We need to make sure that the filesystem supports encoding of + * file handles so user can use name_to_handle_at() to compare fids + * reported with events to the file handle of watched objects. */ - if (!path->dentry->d_sb->s_export_op || - !path->dentry->d_sb->s_export_op->fh_to_dentry) + if (!exportfs_can_encode_fid(nop)) return -EOPNOTSUPP; return 0; @@ -955,7 +1121,9 @@ __kernel_fsid_t __fsid, *fsid = NULL; u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS; unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; - unsigned int obj_type; + bool ignored = flags & FAN_MARK_IGNORED_MASK; + unsigned int obj_type, fid_mode; + u32 umask = 0; int ret; pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n", @@ -1002,6 +1170,10 @@ if (mask & ~valid_mask) return -EINVAL; + /* Event flags (ONDIR, ON_CHILD) are meaningless in ignored mask */ + if (ignored) + mask &= ~FANOTIFY_EVENT_FLAGS; + f = fdget(fanotify_fd); if (unlikely(!f.file)) return -EBADF; @@ -1028,9 +1200,9 @@ * inode events are not supported on a mount mark, because they do not * carry enough information (i.e. path) to be filtered by mount point. */ + fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); if (mask & FANOTIFY_INODE_EVENTS && - (!FAN_GROUP_FLAG(group, FAN_REPORT_FID) || - mark_type == FAN_MARK_MOUNT)) + (!fid_mode || mark_type == FAN_MARK_MOUNT)) goto fput_and_out; if (flags & FAN_MARK_FLUSH) { @@ -1055,8 +1227,12 @@ goto path_put_and_out; } - if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { - ret = fanotify_test_fid(&path, &__fsid); + if (fid_mode) { + ret = fanotify_test_fsid(path.dentry, &__fsid); + if (ret) + goto path_put_and_out; + + ret = fanotify_test_fid(path.dentry); if (ret) goto path_put_and_out; @@ -1069,6 +1245,19 @@ else mnt = path.mnt; + /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */ + if (mnt || !S_ISDIR(inode->i_mode)) { + mask &= ~FAN_EVENT_ON_CHILD; + umask = FAN_EVENT_ON_CHILD; + /* + * If group needs to report parent fid, register for getting + * events with parent/name info for non-directory. + */ + if ((fid_mode & FAN_REPORT_DIR_FID) && + (flags & FAN_MARK_ADD) && !ignored) + mask |= FAN_EVENT_ON_CHILD; + } + /* create/update an inode mark */ switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) { case FAN_MARK_ADD: @@ -1085,13 +1274,13 @@ case FAN_MARK_REMOVE: if (mark_type == FAN_MARK_MOUNT) ret = fanotify_remove_vfsmount_mark(group, mnt, mask, - flags); + flags, umask); else if (mark_type == FAN_MARK_FILESYSTEM) ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask, - flags); + flags, umask); else ret = fanotify_remove_inode_mark(group, inode, mask, - flags); + flags, umask); break; default: ret = -EINVAL; @@ -1134,12 +1323,15 @@ */ static int __init fanotify_user_setup(void) { - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 8); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); - fanotify_event_cachep = KMEM_CACHE(fanotify_event, SLAB_PANIC); + fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event, + SLAB_PANIC); + fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event, + SLAB_PANIC); if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) { fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);