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 4.9-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-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From cb97fbbcac15982406e0c74cd5512a8b6fcf10b3 Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@xxxxxxxxx>
Date: Wed, 8 Feb 2017 00:41:45 +0200
Subject: mei: remove support for broken parallel read
From: Alexander Usyskin <alexander.usyskin@xxxxxxxxx>
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@xxxxxxxxx>
Signed-off-by: Tomas Winkler <tomas.winkler@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
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 */
Patches currently in stable-queue which might be from alexander.usyskin@xxxxxxxxx are
queue-4.9/mei-remove-support-for-broken-parallel-read.patch