[openib-general] Re: LLTX and netif_stop_queue

[jamal]

On Sun, 2004-12-19 at 14:31, jamal wrote:

> How about releasing the qlock only when the LLTX transmit lock is
> grabbed? That should bring it to par with what it was originally.

Something like two attached patches... one showing how to do it for
e1000. untested (not even compiled)

cheers,
jamal
-------------- next part --------------
--- a/net/sched/bak.sch_generic.c	2004-12-19 13:46:19.799356432 -0500
+++ b/net/sched/sch_generic.c	2004-12-19 13:49:14.384815408 -0500
@@ -128,12 +128,11 @@
 			}
 			/* Remember that the driver is grabbed by us. */
 			dev->xmit_lock_owner = smp_processor_id();
+			/* And release queue */
+			spin_unlock(&dev->queue_lock);
 		}
 		
 		{
-			/* And release queue */
-			spin_unlock(&dev->queue_lock);
-
 			if (!netif_queue_stopped(dev)) {
 				int ret;
 				if (netdev_nit)
@@ -141,15 +140,14 @@
 
 				ret = dev->hard_start_xmit(skb, dev);
 				if (ret == NETDEV_TX_OK) { 
+					dev->xmit_lock_owner = -1;
 					if (!nolock) {
-						dev->xmit_lock_owner = -1;
 						spin_unlock(&dev->xmit_lock);
 					}
 					spin_lock(&dev->queue_lock);
 					return -1;
 				}
 				if (ret == NETDEV_TX_LOCKED && nolock) {
-					spin_lock(&dev->queue_lock);
 					goto collision; 
 				}
 			}
-------------- next part --------------
--- a/drivers/net/e1000/b.e1000_main.c	2004-12-19 13:50:59.481838232 -0500
+++ b/drivers/net/e1000/e1000_main.c	2004-12-19 13:53:34.326298296 -0500
@@ -1809,6 +1809,10 @@
  		return NETDEV_TX_LOCKED; 
  	} 
 
+	/* new from sch_generic for LLTX */
+	spin_unlock(&dev->queue_lock);
+	dev->xmit_lock_owner = smp_processor_id();
+
 	/* need: count + 2 desc gap to keep tail from touching
 	 * head, otherwise try next time */
 	if(E1000_DESC_UNUSED(&adapter->tx_ring) < count + 2) {