Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1596818

[PATCH 4.9 077/153] mei: remove support for broken parallel read

Show all headers | View raw

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

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

From: Alexander Usyskin <alexander.usyskin@intel.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@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.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 */

Back to linux.kernel | Previous | Next | Find similar | Unroll thread

Thread

[PATCH 4.9 077/153] mei: remove support for broken parallel read Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2017-03-10 10:30 +0100

csiph-web