Skip to contentSkip to conversation

Patch "mei: remove support for broken parallel read" has been added to the 4.10-stable tree

PATCH [email protected] 1 participant 1 message Mar 8, 2017

Subsystems (3)
lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

mei: remove support for broken parallel read

to the 4.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
mei-remove-support-for-broken-parallel-read.patch
and it can be found in the queue-4.10 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From cb97fbbcac15982406e0c74cd5512a8b6fcf10b3 Mon Sep 17 00:00:00 2001

From: Alexander Usyskin <[email protected]>
Date: Wed, 8 Feb 2017 00:41:45 +0200
Subject: mei: remove support for broken parallel read

From: Alexander Usyskin <[email protected]>

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

Patches currently in stable-queue which might be from [email protected] are

queue-4.10/mei-remove-support-for-broken-parallel-read.patch