From patchwork Thu Mar 3 21:00:17 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alan Stern X-Patchwork-Id: 12768099 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id F07A5C433F5 for ; Thu, 3 Mar 2022 21:00:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234920AbiCCVBF (ORCPT ); Thu, 3 Mar 2022 16:01:05 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:36626 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231439AbiCCVBE (ORCPT ); Thu, 3 Mar 2022 16:01:04 -0500 Received: from netrider.rowland.org (netrider.rowland.org [192.131.102.5]) by lindbergh.monkeyblade.net (Postfix) with SMTP id 251C21CFD1 for ; Thu, 3 Mar 2022 13:00:18 -0800 (PST) Received: (qmail 1290092 invoked by uid 1000); 3 Mar 2022 16:00:17 -0500 Date: Thu, 3 Mar 2022 16:00:17 -0500 From: Alan Stern To: Greg KH Cc: USB mailing list , syzkaller-bugs@googlegroups.com Subject: [PATCH] usb: usbtmc: Fix bug in pipe direction for control transfers Message-ID: References: <000000000000054cc905d95672fa@google.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <000000000000054cc905d95672fa@google.com> Precedence: bulk List-ID: X-Mailing-List: linux-usb@vger.kernel.org The syzbot fuzzer reported a minor bug in the usbtmc driver: usb 5-1: BOGUS control dir, pipe 80001e80 doesn't match bRequestType 0 WARNING: CPU: 0 PID: 3813 at drivers/usb/core/urb.c:412 usb_submit_urb+0x13a5/0x1970 drivers/usb/core/urb.c:410 Modules linked in: CPU: 0 PID: 3813 Comm: syz-executor122 Not tainted 5.17.0-rc5-syzkaller-00306-g2293be58d6a1 #0 ... Call Trace: usb_start_wait_urb+0x113/0x530 drivers/usb/core/message.c:58 usb_internal_control_msg drivers/usb/core/message.c:102 [inline] usb_control_msg+0x2a5/0x4b0 drivers/usb/core/message.c:153 usbtmc_ioctl_request drivers/usb/class/usbtmc.c:1947 [inline] The problem is that usbtmc_ioctl_request() uses usb_rcvctrlpipe() for all of its transfers, whether they are in or out. It's easy to fix. Reported-and-tested-by: syzbot+a48e3d1a875240cab5de@syzkaller.appspotmail.com Signed-off-by: Alan Stern CC: --- [as1973] drivers/usb/class/usbtmc.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) Index: usb-devel/drivers/usb/class/usbtmc.c =================================================================== --- usb-devel.orig/drivers/usb/class/usbtmc.c +++ usb-devel/drivers/usb/class/usbtmc.c @@ -1919,6 +1919,7 @@ static int usbtmc_ioctl_request(struct u struct usbtmc_ctrlrequest request; u8 *buffer = NULL; int rv; + unsigned int is_in, pipe; unsigned long res; res = copy_from_user(&request, arg, sizeof(struct usbtmc_ctrlrequest)); @@ -1928,12 +1929,14 @@ static int usbtmc_ioctl_request(struct u if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + is_in = request.req.bRequestType & USB_DIR_IN; + if (request.req.wLength) { buffer = kmalloc(request.req.wLength, GFP_KERNEL); if (!buffer) return -ENOMEM; - if ((request.req.bRequestType & USB_DIR_IN) == 0) { + if (!is_in) { /* Send control data to device */ res = copy_from_user(buffer, request.data, request.req.wLength); @@ -1944,8 +1947,12 @@ static int usbtmc_ioctl_request(struct u } } + if (is_in) + pipe = usb_rcvctrlpipe(data->usb_dev, 0); + else + pipe = usb_sndctrlpipe(data->usb_dev, 0); rv = usb_control_msg(data->usb_dev, - usb_rcvctrlpipe(data->usb_dev, 0), + pipe, request.req.bRequest, request.req.bRequestType, request.req.wValue, @@ -1957,7 +1964,7 @@ static int usbtmc_ioctl_request(struct u goto exit; } - if (rv && (request.req.bRequestType & USB_DIR_IN)) { + if (rv && is_in) { /* Read control data from device */ res = copy_to_user(request.data, buffer, rv); if (res)