linux-kernel - [PATCH 4.10 084/167] mei: remove support for broken parallel read

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20170310084001.601478500@linuxfoundation.org>
Date:   Fri, 10 Mar 2017 10:08:47 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org,
        Alexander Usyskin <alexander.usyskin@...el.com>,
        Tomas Winkler <tomas.winkler@...el.com>
Subject: [PATCH 4.10 084/167] mei: remove support for broken parallel read

4.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alexander Usyskin <alexander.usyskin@...el.com>

commit cb97fbbcac15982406e0c74cd5512a8b6fcf10b3 upstream.

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.

Fixes: ff1586a7ea57 ("mei: enqueue consecutive reads")
Signed-off-by: Alexander Usyskin <alexander.usyskin@...el.com>
Signed-off-by: Tomas Winkler <tomas.winkler@...el.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 drivers/misc/mei/main.c |   48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -182,32 +182,36 @@ static ssize_t mei_read(struct file *fil
 		goto out;
 	}
 
-	if (rets == -EBUSY &&
-	    !mei_cl_enqueue_ctrl_wr_cb(cl, length, MEI_FOP_READ, file)) {
-		rets = -ENOMEM;
-		goto out;
+
+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);
 
-	do {
-		mutex_unlock(&dev->device_lock);
+	if (!mei_cl_is_connected(cl)) {
+		rets = -ENODEV;
+		goto out;
+	}
 
-		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 (!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 */