sfc: Add TX merged completion counter

Add a counter for TX merged completion events.

This is implemented in the common TX path, because the NIC event
handlers only know how many descriptors were completed, not how many
packets.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 0b8ffdf..6354693 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -65,6 +65,7 @@
 			 unsigned int, efx_get_uint_stat)
 
 static const struct efx_sw_stat_desc efx_sw_stat_desc[] = {
+	EFX_ETHTOOL_UINT_TXQ_STAT(merge_events),
 	EFX_ETHTOOL_UINT_TXQ_STAT(tso_bursts),
 	EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers),
 	EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets),
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 481e412..f52b38c 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -186,6 +186,7 @@
  *	variable indicates that the queue is empty.  This is to
  *	avoid cache-line ping-pong between the xmit path and the
  *	completion path.
+ * @merge_events: Number of TX merged completion events
  * @insert_count: Current insert pointer
  *	This is the number of buffers that have been added to the
  *	software ring.
@@ -222,6 +223,7 @@
 	/* Members used mainly on the completion path */
 	unsigned int read_count ____cacheline_aligned_in_smp;
 	unsigned int old_write_count;
+	unsigned int merge_events;
 
 	/* Members used only on the xmit path */
 	unsigned int insert_count ____cacheline_aligned_in_smp;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 4903c4f..85ee647 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -437,6 +437,9 @@
 	efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
 	netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl);
 
+	if (pkts_compl > 1)
+		++tx_queue->merge_events;
+
 	/* See if we need to restart the netif queue.  This memory
 	 * barrier ensures that we write read_count (inside
 	 * efx_dequeue_buffers()) before reading the queue status.