net: Avoid enqueuing skb for default qdiscs

dev_queue_xmit enqueue's a skb and calls qdisc_run which
dequeue's the skb and xmits it. In most cases, the skb that
is enqueue'd is the same one that is dequeue'd (unless the
queue gets stopped or multiple cpu's write to the same queue
and ends in a race with qdisc_run). For default qdiscs, we
can remove the redundant enqueue/dequeue and simply xmit the
skb since the default qdisc is work-conserving.

The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the
default fast queue. The controversial part of the patch is
incrementing qlen when a skb is requeued - this is to avoid
checks like the second line below:

+  } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
>>         !q->gso_skb &&
+          !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {

Results of a 2 hour testing for multiple netperf sessions (1,
2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are
aggregate Mb/s across iterations tested with this version on
System-X boxes with Chelsio 10gbps cards:

----------------------------------
Size |  ORG BW          NEW BW   |
----------------------------------
128K |  156964          159381   |
256K |  158650          162042   |
----------------------------------

Changes from ver1:

1. Move sch_direct_xmit declaration from sch_generic.h to
   pkt_sched.h
2. Update qdisc basic statistics for direct xmit path.
3. Set qlen to zero in qdisc_reset.
4. Changed some function names to more meaningful ones.

Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 35 insertions, 13 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index f01a9c41f11..a0bc087616a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1786,6 +1786,40 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
 	return netdev_get_tx_queue(dev, queue_index);
 }
 
+static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
+				 struct net_device *dev,
+				 struct netdev_queue *txq)
+{
+	spinlock_t *root_lock = qdisc_lock(q);
+	int rc;
+
+	spin_lock(root_lock);
+	if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+		kfree_skb(skb);
+		rc = NET_XMIT_DROP;
+	} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
+		   !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
+		/*
+		 * This is a work-conserving queue; there are no old skbs
+		 * waiting to be sent out; and the qdisc is not running -
+		 * xmit the skb directly.
+		 */
+		__qdisc_update_bstats(q, skb->len);
+		if (sch_direct_xmit(skb, q, dev, txq, root_lock))
+			__qdisc_run(q);
+		else
+			clear_bit(__QDISC_STATE_RUNNING, &q->state);
+
+		rc = NET_XMIT_SUCCESS;
+	} else {
+		rc = qdisc_enqueue_root(skb, q);
+		qdisc_run(q);
+	}
+	spin_unlock(root_lock);
+
+	return rc;
+}
+
 /**
  *	dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
@@ -1859,19 +1893,7 @@ gso:
 	skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
 #endif
 	if (q->enqueue) {
-		spinlock_t *root_lock = qdisc_lock(q);
-
-		spin_lock(root_lock);
-
-		if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
-			kfree_skb(skb);
-			rc = NET_XMIT_DROP;
-		} else {
-			rc = qdisc_enqueue_root(skb, q);
-			qdisc_run(q);
-		}
-		spin_unlock(root_lock);
-
+		rc = __dev_xmit_skb(skb, q, dev, txq);
 		goto out;
 	}