atm/br2684: netif_stop_queue() when atm device busy and netif_wake_queue() when we can send packets again.

This patch removes the call to dev_kfree_skb() when the atm device is busy.
Calling dev_kfree_skb() causes heavy packet loss then the device is under
heavy load, the more correct behavior should be to stop the upper layers,
then when the lower device can queue packets again wake the upper layers.

Signed-off-by: Karl Hiramoto <karl@hiramoto.org>
Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>
---
 net/atm/br2684.c |   37 +++++++++++++++++++++++++++----------
 1 files changed, 27 insertions(+), 10 deletions(-)

  * the way for multiple vcc's per itf.  Returns true if we can send,
@@ -200,20 +216,19 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct n
et_device *dev,
 
 	ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev);
-	if (!atm_may_send(atmvcc, skb->truesize)) {
-		/*
-		 * We free this here for now, because we cannot know in a highe
r
-		 * layer whether the skb pointer it supplied wasn't freed yet.
-		 * Now, it always is.
-		 */
-		dev_kfree_skb(skb);
-		return 0;
-	}
 	atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
 	ATM_SKB(skb)->atm_options = atmvcc->atm_options;
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 	atmvcc->send(atmvcc, skb);
+
+	if (!atm_may_send(atmvcc, 0)) {
+		netif_stop_queue(brvcc->device);
+		/*check for race with br2684_pop*/
+		if (atm_may_send(atmvcc, 0))
+			netif_start_queue(brvcc->device);
+	}
+
 	return 1;
 }
 
@@ -503,8 +518,10 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __u
ser * arg)
 	atmvcc->user_back = brvcc;
 	brvcc->encaps = (enum br2684_encaps)be.encaps;
 	brvcc->old_push = atmvcc->push;
+	brvcc->old_pop = atmvcc->pop;
 	barrier();
 	atmvcc->push = br2684_push;
+	atmvcc->pop = br2684_pop;
 
 	__skb_queue_head_init(&queue);
 	rq = &sk_atm(atmvcc)->sk_receive_queue;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

From: "Chas Williams (CONTRACTOR)" <chas@cmf.nrl.navy.mil>
Date: Mon, 31 Aug 2009 10:29:47 -0400

> This patch removes the call to dev_kfree_skb() when the atm device is busy.
> Calling dev_kfree_skb() causes heavy packet loss then the device is under
> heavy load, the more correct behavior should be to stop the upper layers,
> then when the lower device can queue packets again wake the upper layers.
> 
> Signed-off-by: Karl Hiramoto <karl@hiramoto.org>
> Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>

Applied to net-next-2.6, but Chas your email client corrupted
the patch by breaking up long lines:

> @@ -142,6 +142,22 @@ static struct net_device *br2684_find_dev(const struct br
> 2684_if_spec *s)

Like that.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

In message <20090902.232707.93089975.davem@davemloft.net>,David Miller writes:
>Applied to net-next-2.6, but Chas your email client corrupted
>the patch by breaking up long lines:

grr.... i will fix it (again).  thanks.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html