Merge branch 'mvneta-xmit_more-bql'

Marcin Wojtas says:

====================
mvneta xmit_more and bql support

This is a delayed v2 of short patchset, which introduces xmit_more and BQL
to mvneta driver. The only one change was added in xmit_more support -
condition check preventing excessive descriptors concatenation before
flushing in HW.

Any comments or feedback would be welcome.

Changelog:
v1 -> v2:

* Add checking condition that ensures too much descriptors are not
  concatenated before flushing in HW.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 3607d8f..6dcc951 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -224,6 +224,7 @@
 #define      MVNETA_TXQ_SENT_THRESH_MASK(coal)   ((coal) << 16)
 #define MVNETA_TXQ_UPDATE_REG(q)                 (0x3c60 + ((q) << 2))
 #define      MVNETA_TXQ_DEC_SENT_SHIFT           16
+#define      MVNETA_TXQ_DEC_SENT_MASK            0xff
 #define MVNETA_TXQ_STATUS_REG(q)                 (0x3c40 + ((q) << 2))
 #define      MVNETA_TXQ_SENT_DESC_SHIFT          16
 #define      MVNETA_TXQ_SENT_DESC_MASK           0x3fff0000
@@ -525,6 +526,7 @@
 	 * descriptor ring
 	 */
 	int count;
+	int pending;
 	int tx_stop_threshold;
 	int tx_wake_threshold;
 
@@ -818,8 +820,9 @@
 	/* Only 255 descriptors can be added at once ; Assume caller
 	 * process TX desriptors in quanta less than 256
 	 */
-	val = pend_desc;
+	val = pend_desc + txq->pending;
 	mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
+	txq->pending = 0;
 }
 
 /* Get pointer to next TX descriptor to be processed (send) by HW */
@@ -1756,8 +1759,10 @@
 
 /* Free tx queue skbuffs */
 static void mvneta_txq_bufs_free(struct mvneta_port *pp,
-				 struct mvneta_tx_queue *txq, int num)
+				 struct mvneta_tx_queue *txq, int num,
+				 struct netdev_queue *nq)
 {
+	unsigned int bytes_compl = 0, pkts_compl = 0;
 	int i;
 
 	for (i = 0; i < num; i++) {
@@ -1765,6 +1770,11 @@
 			txq->txq_get_index;
 		struct sk_buff *skb = txq->tx_skb[txq->txq_get_index];
 
+		if (skb) {
+			bytes_compl += skb->len;
+			pkts_compl++;
+		}
+
 		mvneta_txq_inc_get(txq);
 
 		if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr))
@@ -1775,6 +1785,8 @@
 			continue;
 		dev_kfree_skb_any(skb);
 	}
+
+	netdev_tx_completed_queue(nq, pkts_compl, bytes_compl);
 }
 
 /* Handle end of transmission */
@@ -1788,7 +1800,7 @@
 	if (!tx_done)
 		return;
 
-	mvneta_txq_bufs_free(pp, txq, tx_done);
+	mvneta_txq_bufs_free(pp, txq, tx_done, nq);
 
 	txq->count -= tx_done;
 
@@ -2398,12 +2410,18 @@
 		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 		struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
 
-		txq->count += frags;
-		mvneta_txq_pend_desc_add(pp, txq, frags);
+		netdev_tx_sent_queue(nq, len);
 
+		txq->count += frags;
 		if (txq->count >= txq->tx_stop_threshold)
 			netif_tx_stop_queue(nq);
 
+		if (!skb->xmit_more || netif_xmit_stopped(nq) ||
+		    txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
+			mvneta_txq_pend_desc_add(pp, txq, frags);
+		else
+			txq->pending += frags;
+
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
 		stats->tx_bytes  += len;
@@ -2422,9 +2440,10 @@
 				  struct mvneta_tx_queue *txq)
 
 {
+	struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
 	int tx_done = txq->count;
 
-	mvneta_txq_bufs_free(pp, txq, tx_done);
+	mvneta_txq_bufs_free(pp, txq, tx_done, nq);
 
 	/* reset txq */
 	txq->count = 0;
@@ -2950,6 +2969,8 @@
 static void mvneta_txq_deinit(struct mvneta_port *pp,
 			      struct mvneta_tx_queue *txq)
 {
+	struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
+
 	kfree(txq->tx_skb);
 
 	if (txq->tso_hdrs)
@@ -2961,6 +2982,8 @@
 				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
 				  txq->descs, txq->descs_phys);
 
+	netdev_tx_reset_queue(nq);
+
 	txq->descs             = NULL;
 	txq->last_desc         = 0;
 	txq->next_desc_to_proc = 0;