Browse Source

[media] lirc_zilog: Don't acquire the rx->buf_lock in the poll() function

There is no need to take the rx->buf_lock in the the poll() function
as all the underling calls made on objects in the rx->buf lirc_buffer object
are protected by spinlocks.

Corrected a bad error return value in poll(): return POLLERR instead
of -ENODEV.

Added some comments to poll() for when, in the future, I forget what
poll() and poll_wait() are supposed to do.

[Jarod: minor debug spew fix]

Signed-off-by: Andy Walls <awalls@md.metrocast.net>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Andy Walls 14 years ago
parent
commit
915e54733d
1 changed files with 14 additions and 7 deletions
  1. 14 7
      drivers/staging/lirc/lirc_zilog.c

+ 14 - 7
drivers/staging/lirc/lirc_zilog.c

@@ -985,19 +985,26 @@ static unsigned int poll(struct file *filep, poll_table *wait)
 	unsigned int ret;
 
 	dprintk("poll called\n");
-	if (rx == NULL)
-		return -ENODEV;
 
-	mutex_lock(&rx->buf_lock);
+	if (rx == NULL) {
+		/*
+		 * Revisit this, if our poll function ever reports writeable
+		 * status for Tx
+		 */
+		dprintk("poll result = POLLERR\n");
+		return POLLERR;
+	}
 
+	/*
+	 * Add our lirc_buffer's wait_queue to the poll_table. A wake up on
+	 * that buffer's wait queue indicates we may have a new poll status.
+	 */
 	poll_wait(filep, &rx->buf.wait_poll, wait);
 
-	dprintk("poll result = %s\n",
-		lirc_buffer_empty(&rx->buf) ? "0" : "POLLIN|POLLRDNORM");
-
+	/* Indicate what ops could happen immediately without blocking */
 	ret = lirc_buffer_empty(&rx->buf) ? 0 : (POLLIN|POLLRDNORM);
 
-	mutex_unlock(&rx->buf_lock);
+	dprintk("poll result = %s\n", ret ? "POLLIN|POLLRDNORM" : "none");
 	return ret;
 }