net: pktgen: packet bursting via skb->xmit_more

This patch demonstrates the effect of delaying update of HW tailptr.
(based on earlier patch by Jesper)

burst=1 is the default. It sends one packet with xmit_more=false
burst=2 sends one packet with xmit_more=true and
2nd copy of the same packet with xmit_more=false
burst=3 sends two copies of the same packet with xmit_more=true and
3rd copy with xmit_more=false

Performance with ixgbe (usec 30):
burst=1 tx:9.2 Mpps
burst=2 tx:13.5 Mpps
burst=3 tx:14.5 Mpps full 10G line rate

Signed-off-by: Alexei Starovoitov <[e-mail]>
Signed-off-by: Eric Dumazet <[e-mail]>
Acked-by: Jesper Dangaard Brouer <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/pktgen.txt

···
 
  pgset "clone_skb 1"     sets the number of copies of the same packet
  pgset "clone_skb 0"     use single SKB for all transmits
+ pgset "burst 8"         uses xmit_more API to queue 8 copies of the same
+                         packet and update HW tx queue tail pointer once.
+                         "burst 1" is the default
  pgset "pkt_size 9014"   sets packet size to 9014
  pgset "frags 5"         packet will consist of 5 fragments
  pgset "count 200000"    sets number of packets to send, set to zero

net/core/pktgen.c

···
 	u16 queue_map_min;
 	u16 queue_map_max;
 	__u32 skb_priority;	/* skb priority field */
+	unsigned int burst;	/* number of duplicated packets to burst */
 	int node;               /* Memory node */
 
 #ifdef CONFIG_XFRM
···
 
 	if (pkt_dev->traffic_class)
 		seq_printf(seq, "     traffic_class: 0x%02x\n", pkt_dev->traffic_class);
+
+	if (pkt_dev->burst > 1)
+		seq_printf(seq, "     burst: %d\n", pkt_dev->burst);
 
 	if (pkt_dev->node >= 0)
 		seq_printf(seq, "     node: %d\n", pkt_dev->node);
···
 		}
 		sprintf(pg_result, "OK: dst_mac_count=%d",
 			pkt_dev->dst_mac_count);
+		return count;
+	}
+	if (!strcmp(name, "burst")) {
+		len = num_arg(&user_buffer[i], 10, &value);
+		if (len < 0)
+			return len;
+
+		i += len;
+		pkt_dev->burst = value < 1 ? 1 : value;
+		sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
 		return count;
 	}
 	if (!strcmp(name, "node")) {
···
 
 static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 {
+	unsigned int burst = ACCESS_ONCE(pkt_dev->burst);
 	struct net_device *odev = pkt_dev->odev;
 	struct netdev_queue *txq;
 	int ret;
···
 		pkt_dev->last_ok = 0;
 		goto unlock;
 	}
-	atomic_inc(&(pkt_dev->skb->users));
-	ret = netdev_start_xmit(pkt_dev->skb, odev, txq, false);
+	atomic_add(burst, &pkt_dev->skb->users);
+
+xmit_more:
+	ret = netdev_start_xmit(pkt_dev->skb, odev, txq, --burst > 0);
 
 	switch (ret) {
 	case NETDEV_TX_OK:
···
 		pkt_dev->sofar++;
 		pkt_dev->seq_num++;
 		pkt_dev->tx_bytes += pkt_dev->last_pkt_size;
+		if (burst > 0 && !netif_xmit_frozen_or_drv_stopped(txq))
+			goto xmit_more;
 		break;
 	case NET_XMIT_DROP:
 	case NET_XMIT_CN:
···
 		atomic_dec(&(pkt_dev->skb->users));
 		pkt_dev->last_ok = 0;
 	}
+	if (unlikely(burst))
+		atomic_sub(burst, &pkt_dev->skb->users);
 unlock:
 	HARD_TX_UNLOCK(odev, txq);
 
···
 	pkt_dev->svlan_p = 0;
 	pkt_dev->svlan_cfi = 0;
 	pkt_dev->svlan_id = 0xffff;
+	pkt_dev->burst = 1;
 	pkt_dev->node = -1;
 
 	err = pktgen_setup_dev(t->net, pkt_dev, ifname);