+ errno = parent->ops->create(parent, dnode, itype);
+ if (errno) {
+ return errno;
+ }
+
+ return 0;
+}
+
+struct file_locator {
+ struct v_dnode* dir;
+ struct v_dnode* file;
+ bool fresh;
+};
+
+/**
+ * @brief unlock the file locator (floc) if possible.
+ * If the file to be located if not exists, and
+ * any FLOC_*MKNAME flag is set, then the parent
+ * dnode will be locked until the file has been properly
+ * finalised by subsequent logic.
+ *
+ * @param floc
+ */
+static inline void
+__floc_try_unlock(struct file_locator* floc)
+{
+ if (floc->fresh) {
+ assert(floc->dir);
+ unlock_dnode(floc->dir);
+ }
+}
+
+static int
+__vfs_try_locate_file(const char* path,
+ struct file_locator* floc,
+ int options)
+{
+ char name_str[VFS_NAME_MAXLEN];
+ struct v_dnode *fdir, *file;
+ struct hstr name = HSTR(name_str, 0);
+ int errno, woption = 0;
+
+ if ((options & FLOC_NOFOLLOW)) {
+ woption |= VFS_WALK_NOFOLLOW;
+ options &= ~FLOC_NOFOLLOW;
+ }
+
+ floc->fresh = false;
+ name_str[0] = 0;
+ errno = vfs_walk_proc(path, &fdir, &name, woption | VFS_WALK_PARENT);
+ if (errno) {
+ return errno;
+ }
+
+ errno = vfs_walk(fdir, name.value, &file, NULL, woption);
+
+ if (errno && errno != ENOENT) {
+ goto done;
+ }
+
+ if (!errno) {
+ if ((options & FLOC_MKNAME)) {
+ errno = EEXIST;
+ }
+ goto done;
+ }
+
+ // errno == ENOENT
+ if (!options) {
+ goto done;
+ }
+
+ errno = vfs_check_writable(fdir);
+ if (errno) {
+ goto done;
+ }
+
+ floc->fresh = true;
+
+ file = vfs_d_alloc(fdir, &name);
+
+ if (!file) {
+ return ENOMEM;
+ }
+
+ lock_dnode(fdir);
+
+ vfs_dcache_add(fdir, file);
+
+done:
+ floc->dir = fdir;
+ floc->file = file;
+
+ return errno;
+}
+
+int
+vfs_do_open(const char* path, int options)
+{
+ int errno, fd, loptions = 0;
+ struct v_dnode *dentry, *file;
+ struct v_file* ofile = NULL;
+ struct file_locator floc;
+ struct v_inode* inode;
+
+ if ((options & FO_CREATE)) {
+ loptions |= FLOC_MAYBE_MKNAME;
+ } else if ((options & FO_NOFOLLOW)) {
+ loptions |= FLOC_NOFOLLOW;
+ }
+
+ errno = __vfs_try_locate_file(path, &floc, loptions);
+
+ if (errno || (errno = vfs_alloc_fdslot(&fd))) {
+ return errno;
+ }
+
+ file = floc.file;
+ dentry = floc.dir;
+
+ if (floc.fresh) {
+ errno = __vfs_mknod(dentry->inode, file, VFS_IFFILE, NULL);
+ if (errno) {
+ vfs_d_free(file);
+ __floc_try_unlock(&floc);
+ return errno;
+ }
+
+ __floc_try_unlock(&floc);
+ }
+
+
+ if ((errno = vfs_open(file, &ofile))) {
+ return errno;
+ }
+
+ inode = ofile->inode;
+ lock_inode(inode);
+
+ struct v_fd* fd_s = cake_grab(fd_pile);
+ memset(fd_s, 0, sizeof(*fd_s));
+
+ if ((options & O_TRUNC)) {
+ file->inode->fsize = 0;
+ }
+
+ if (vfs_get_dtype(inode->itype) == DT_DIR) {
+ ofile->f_pos = 0;
+ }
+
+ fd_s->file = ofile;
+ fd_s->flags = options;
+ __current->fdtable->fds[fd] = fd_s;
+
+ unlock_inode(inode);
+
+ return fd;
+}
+
+__DEFINE_LXSYSCALL2(int, open, const char*, path, int, options)
+{
+ int errno = vfs_do_open(path, options);
+ return DO_STATUS_OR_RETURN(errno);
+}
+
+__DEFINE_LXSYSCALL1(int, close, int, fd)
+{
+ struct v_fd* fd_s;
+ int errno = 0;
+ if ((errno = vfs_getfd(fd, &fd_s))) {
+ goto done_err;
+ }
+
+ if ((errno = vfs_close(fd_s->file))) {
+ goto done_err;
+ }
+
+ cake_release(fd_pile, fd_s);
+ __current->fdtable->fds[fd] = 0;
+
+done_err:
+ return DO_STATUS(errno);
+}
+
+void
+__vfs_readdir_callback(struct dir_context* dctx,
+ const char* name,
+ const int len,
+ const int dtype)
+{
+ struct lx_dirent* dent = (struct lx_dirent*)dctx->cb_data;
+ strncpy(dent->d_name, name, MIN(len, DIRENT_NAME_MAX_LEN));
+ dent->d_nlen = len;
+ dent->d_type = dtype;
+}
+
+__DEFINE_LXSYSCALL2(int, sys_readdir, int, fd, struct lx_dirent*, dent)
+{
+ struct v_fd* fd_s;
+ int errno;
+
+ if ((errno = vfs_getfd(fd, &fd_s))) {
+ goto done;
+ }
+
+ struct v_inode* inode = fd_s->file->inode;
+
+ lock_inode(inode);
+
+ if (!check_directory_node(inode)) {
+ errno = ENOTDIR;
+ goto unlock;
+ }
+
+ struct dir_context dctx = (struct dir_context) {
+ .cb_data = dent,
+ .read_complete_callback = __vfs_readdir_callback
+ };
+
+ if ((errno = fd_s->file->ops->readdir(fd_s->file, &dctx)) != 1) {
+ goto unlock;
+ }
+ dent->d_offset++;
+ fd_s->file->f_pos++;
+
+unlock:
+ unlock_inode(inode);
+
+done:
+ return DO_STATUS_OR_RETURN(errno);
+}
+
+__DEFINE_LXSYSCALL3(int, read, int, fd, void*, buf, size_t, count)
+{
+ int errno = 0;
+ struct v_fd* fd_s;
+ if ((errno = vfs_getfd(fd, &fd_s))) {
+ goto done;
+ }
+
+ struct v_file* file = fd_s->file;
+ if (check_directory_node(file->inode)) {
+ errno = EISDIR;
+ goto done;
+ }
+
+ lock_inode(file->inode);
+
+ file->inode->atime = clock_unixtime();
+
+ if (check_seqdev_node(file->inode) || (fd_s->flags & FO_DIRECT)) {
+ errno = file->ops->read(file->inode, buf, count, file->f_pos);
+ } else {
+ errno = pcache_read(file->inode, buf, count, file->f_pos);
+ }
+
+ if (errno > 0) {
+ file->f_pos += errno;
+ unlock_inode(file->inode);
+ return errno;
+ }
+
+ unlock_inode(file->inode);
+
+done:
+ return DO_STATUS(errno);
+}
+
+__DEFINE_LXSYSCALL3(int, write, int, fd, void*, buf, size_t, count)
+{
+ int errno = 0;
+ struct v_fd* fd_s;
+ if ((errno = vfs_getfd(fd, &fd_s))) {
+ goto done;
+ }
+
+ struct v_inode* inode;
+ struct v_file* file = fd_s->file;
+
+ if ((errno = vfs_check_writable(file->dnode))) {
+ goto done;
+ }
+
+ if (check_directory_node(file->inode)) {
+ errno = EISDIR;
+ goto done;
+ }
+
+ inode = file->inode;
+ lock_inode(inode);
+
+ inode->mtime = clock_unixtime();
+ if ((fd_s->flags & O_APPEND)) {
+ file->f_pos = inode->fsize;
+ }
+
+ if (check_seqdev_node(inode) || (fd_s->flags & FO_DIRECT)) {
+ errno = file->ops->write(inode, buf, count, file->f_pos);
+ } else {
+ errno = pcache_write(inode, buf, count, file->f_pos);
+ }
+
+ if (errno > 0) {
+ file->f_pos += errno;
+ inode->fsize = MAX(inode->fsize, file->f_pos);
+
+ unlock_inode(inode);
+ return errno;
+ }
+
+ unlock_inode(inode);
+
+done:
+ return DO_STATUS(errno);
+}
+
+__DEFINE_LXSYSCALL3(int, lseek, int, fd, int, offset, int, options)
+{
+ int errno = 0;
+ struct v_fd* fd_s;
+ if ((errno = vfs_getfd(fd, &fd_s))) {
+ goto done;
+ }
+
+ struct v_file* file = fd_s->file;
+ struct v_inode* inode = file->inode;
+
+ if (!file->ops->seek) {
+ errno = ENOTSUP;
+ goto done;
+ }
+
+ lock_inode(inode);
+
+ int overflow = 0;
+ int fpos = file->f_pos;
+
+ if (vfs_get_dtype(inode->itype) == DT_DIR) {
+ options = (options != FSEEK_END) ? options : FSEEK_SET;
+ }
+
+ switch (options) {
+ case FSEEK_CUR:
+ overflow = sadd_of((int)file->f_pos, offset, &fpos);
+ break;
+ case FSEEK_END:
+ overflow = sadd_of((int)inode->fsize, offset, &fpos);
+ break;
+ case FSEEK_SET:
+ fpos = offset;
+ break;
+ }
+
+ if (overflow) {
+ errno = EOVERFLOW;
+ }
+ else {
+ errno = file->ops->seek(file, fpos);
+ }
+
+ unlock_inode(inode);
+
+done:
+ return DO_STATUS(errno);
+}
+
+int
+vfs_get_path(struct v_dnode* dnode, char* buf, size_t size, int depth)
+{
+ if (!dnode) {
+ return 0;
+ }
+
+ if (depth > 64) {
+ return ENAMETOOLONG;
+ }
+
+ size_t len = 0;
+
+ if (dnode->parent != dnode) {
+ len = vfs_get_path(dnode->parent, buf, size, depth + 1);
+ }
+
+ if (len >= size) {
+ return len;
+ }
+
+ if (!len || buf[len - 1] != VFS_PATH_DELIM) {
+ buf[len++] = VFS_PATH_DELIM;
+ }
+
+ size_t cpy_size = MIN(dnode->name.len, size - len);
+ strncpy(buf + len, dnode->name.value, cpy_size);
+ len += cpy_size;
+
+ return len;
+}
+
+int
+vfs_readlink(struct v_dnode* dnode, char* buf, size_t size)
+{
+ const char* link;
+ struct v_inode* inode = dnode->inode;
+
+ if (!check_symlink_node(inode)) {
+ return EINVAL;
+ }
+
+ if (!inode->ops->read_symlink) {
+ return ENOTSUP;
+ }
+
+ lock_inode(inode);
+
+ int errno = inode->ops->read_symlink(inode, &link);
+ if (errno >= 0) {
+ strncpy(buf, link, MIN(size, (size_t)errno));
+ }
+
+ unlock_inode(inode);
+ return errno;
+}
+
+int
+vfs_get_dtype(int itype)
+{
+ int dtype = DT_FILE;
+ if (check_itype(itype, VFS_IFSYMLINK)) {
+ dtype |= DT_SYMLINK;
+ }
+
+ if (check_itype(itype, VFS_IFDIR)) {
+ dtype |= DT_DIR;
+ return dtype;
+ }
+
+ // TODO other types
+
+ return dtype;
+}
+
+__DEFINE_LXSYSCALL3(int, realpathat, int, fd, char*, buf, size_t, size)
+{
+ int errno;
+ struct v_fd* fd_s;
+ if ((errno = vfs_getfd(fd, &fd_s))) {
+ goto done;
+ }
+
+ struct v_dnode* dnode;
+ errno = vfs_get_path(fd_s->file->dnode, buf, size, 0);
+
+ if (errno >= 0) {
+ return errno;
+ }
+
+done:
+ return DO_STATUS(errno);
+}
+
+__DEFINE_LXSYSCALL3(int, readlink, const char*, path, char*, buf, size_t, size)
+{
+ int errno;
+ struct v_dnode* dnode;
+ if (!(errno = vfs_walk_proc(path, &dnode, NULL, VFS_WALK_NOFOLLOW))) {
+ errno = vfs_readlink(dnode, buf, size);
+ }
+
+ if (errno >= 0) {
+ return errno;
+ }
+
+ return DO_STATUS(errno);
+}
+
+__DEFINE_LXSYSCALL4(
+ int, readlinkat, int, dirfd, const char*, pathname, char*, buf, size_t, size)
+{
+ int errno;
+ struct v_fd* fd_s;
+ if ((errno = vfs_getfd(dirfd, &fd_s))) {
+ goto done;
+ }
+
+ pathname = pathname ? pathname : "";
+
+ struct v_dnode* dnode;
+ if (!(errno = vfs_walk(
+ fd_s->file->dnode, pathname, &dnode, NULL, VFS_WALK_NOFOLLOW))) {
+ errno = vfs_readlink(fd_s->file->dnode, buf, size);
+ }
+
+ if (errno >= 0) {
+ return errno;
+ }
+
+done:
+ return DO_STATUS(errno);
+}
+
+/*
+ NOTE
+ When we perform operation that could affect the layout of
+ directory (i.e., rename, mkdir, rmdir). We must lock the parent dir
+ whenever possible. This will blocking any ongoing path walking to reach
+ it hence avoid any partial state.
+*/
+
+__DEFINE_LXSYSCALL1(int, rmdir, const char*, pathname)
+{
+ int errno;
+ struct v_dnode* dnode;
+ if ((errno = vfs_walk_proc(pathname, &dnode, NULL, 0))) {
+ return DO_STATUS(errno);
+ }
+
+ lock_dnode(dnode);
+
+ if ((errno = vfs_check_writable(dnode))) {
+ goto done;
+ }
+
+ if ((dnode->super_block->fs->types & FSTYPE_ROFS)) {
+ errno = EROFS;
+ goto done;
+ }
+
+ if (dnode->ref_count > 1 || dnode->inode->open_count) {
+ errno = EBUSY;
+ goto done;
+ }
+
+ if (!llist_empty(&dnode->children)) {
+ errno = ENOTEMPTY;
+ goto done;
+ }
+
+ struct v_dnode* parent = dnode->parent;
+
+ if (!parent) {
+ errno = EINVAL;
+ goto done;
+ }
+
+ lock_dnode(parent);
+ lock_inode(parent->inode);
+
+ if (check_directory_node(dnode->inode)) {
+ errno = parent->inode->ops->rmdir(parent->inode, dnode);
+ if (!errno) {
+ vfs_dcache_remove(dnode);
+ }
+ } else {
+ errno = ENOTDIR;
+ }
+
+ unlock_inode(parent->inode);
+ unlock_dnode(parent);
+
+done:
+ unlock_dnode(dnode);
+ return DO_STATUS(errno);
+}
+
+__DEFINE_LXSYSCALL1(int, mkdir, const char*, path)
+{
+ int errno = 0;
+ struct v_dnode *parent, *dir;
+ char name_value[VFS_NAME_MAXLEN];
+ struct hstr name = HHSTR(name_value, 0, 0);
+
+ if ((errno = vfs_walk_proc(path, &parent, &name, VFS_WALK_PARENT))) {
+ goto done;
+ }
+
+ if (!(errno = vfs_walk(parent, name_value, &dir, NULL, 0))) {
+ errno = EEXIST;
+ goto done;
+ }
+
+ if ((errno = vfs_check_writable(parent))) {
+ goto done;
+ }
+
+ if (!(dir = vfs_d_alloc(parent, &name))) {
+ errno = ENOMEM;
+ goto done;
+ }
+
+ struct v_inode* inode = parent->inode;
+
+ lock_dnode(parent);
+ lock_inode(inode);
+
+ if ((parent->super_block->fs->types & FSTYPE_ROFS)) {
+ errno = ENOTSUP;
+ } else if (!inode->ops->mkdir) {
+ errno = ENOTSUP;
+ } else if (!check_directory_node(inode)) {
+ errno = ENOTDIR;
+ } else if (!(errno = inode->ops->mkdir(inode, dir))) {
+ vfs_dcache_add(parent, dir);
+ goto cleanup;
+ }
+
+ vfs_d_free(dir);
+
+cleanup:
+ unlock_inode(inode);
+ unlock_dnode(parent);
+done:
+ return DO_STATUS(errno);
+}
+
+int
+__vfs_do_unlink(struct v_dnode* dnode)
+{
+ int errno;
+ struct v_inode* inode = dnode->inode;
+
+ if (dnode->ref_count > 1) {
+ return EBUSY;
+ }
+
+ if ((errno = vfs_check_writable(dnode))) {