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

Groups > linux.kernel > #1596818 > unrolled thread

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

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

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

#1596818 — [PATCH 4.9 077/153] mei: remove support for broken parallel read

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 */

[toc] | [standalone]

Back to top | Article view | linux.kernel

csiph-web