From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755532AbdBGWln (ORCPT ); Tue, 7 Feb 2017 17:41:43 -0500 Received: from mga06.intel.com ([134.134.136.31]:23605 "EHLO mga06.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752868AbdBGWlm (ORCPT ); Tue, 7 Feb 2017 17:41:42 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.33,346,1477983600"; d="scan'208";a="41170613" From: Tomas Winkler To: Greg Kroah-Hartman Cc: Alexander Usyskin , linux-kernel@vger.kernel.org, "#4 . 9" , Tomas Winkler Subject: [char-misc-next] mei: remove support for broken parallel read Date: Wed, 8 Feb 2017 00:41:45 +0200 Message-Id: <1486507305-19620-1-git-send-email-tomas.winkler@intel.com> X-Mailer: git-send-email 2.7.4 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Alexander Usyskin Parallel reads from multiple threads on a file descriptor are not well defined and racy. It is safer to return to original behavior and simply fail the additional read. The solution is to remove request for next read credit. Cc: #4.9 Fixes: ff1586a7ea57 ("mei: enqueue consecutive reads") Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler --- drivers/misc/mei/main.c | 48 ++++++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 22 deletions(-) diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index e1bf54481fd6..9d0b7050c79a 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -182,32 +182,36 @@ static ssize_t mei_read(struct file *file, char __user *ubuf, goto out; } - if (rets == -EBUSY && - !mei_cl_enqueue_ctrl_wr_cb(cl, length, MEI_FOP_READ, file)) { - rets = -ENOMEM; - goto out; - } - do { - mutex_unlock(&dev->device_lock); - - if (wait_event_interruptible(cl->rx_wait, - (!list_empty(&cl->rd_completed)) || - (!mei_cl_is_connected(cl)))) { +again: + mutex_unlock(&dev->device_lock); + if (wait_event_interruptible(cl->rx_wait, + !list_empty(&cl->rd_completed) || + !mei_cl_is_connected(cl))) { + if (signal_pending(current)) + return -EINTR; + return -ERESTARTSYS; + } + mutex_lock(&dev->device_lock); - if (signal_pending(current)) - return -EINTR; - return -ERESTARTSYS; - } + if (!mei_cl_is_connected(cl)) { + rets = -ENODEV; + goto out; + } - mutex_lock(&dev->device_lock); - if (!mei_cl_is_connected(cl)) { - rets = -ENODEV; - goto out; - } + cb = mei_cl_read_cb(cl, file); + if (!cb) { + /* + * For amthif all the waiters are woken up, + * but only fp with matching cb->fp get the cb, + * the others have to return to wait on read. + */ + if (cl == &dev->iamthif_cl) + goto again; - cb = mei_cl_read_cb(cl, file); - } while (!cb); + rets = 0; + goto out; + } copy_buffer: /* now copy the data to user space */ -- 2.7.4