[PATCH 3.16 014/294] net: bcmgenet: fix dev->stats.tx_bytes accounting

[Ben Hutchings]

3.16.50-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Petri Gynther <pgynther@xxxxxxxxxx>

commit 55868120a3e5420bf5aa26a816c07d691579c9e6 upstream.

1. Add bytes_compl local variable to __bcmgenet_tx_reclaim() to collect
   transmitted bytes. dev->stats updates can then be moved outside the
   while-loop. bytes_compl is also needed for future BQL support.
2. When bcmgenet device uses Tx checksum offload, each transmitted skb
   gets an extra 64-byte header prepended to it. Before this header is
   prepended to the skb, we need to save the skb "wire" length in
   GENET_CB(skb)->bytes_sent, so that proper Tx bytes accounting can
   be done in __bcmgenet_tx_reclaim().
3. skb->len covers the entire length of skb, whether it is linear or
   fragmented. Thus, when we clean the fragments, do not increase
   transmitted bytes.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Petri Gynther <pgynther@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
[bwh: Backported to 3.16:
 - Also update tx_packets accounting, as done in upstream commit 4092e6acf5cb
   "net: bcmgenet: fix throughtput regression"
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -948,6 +948,8 @@ static void __bcmgenet_tx_reclaim(struct
 	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
+	unsigned int pkts_compl = 0;
+	unsigned int bytes_compl = 0;
 	unsigned int c_index;
 	unsigned int txbds_ready;
 	unsigned int txbds_processed = 0;
@@ -969,16 +971,14 @@ static void __bcmgenet_tx_reclaim(struct
 	while (txbds_processed < txbds_ready) {
 		tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr];
 		if (tx_cb_ptr->skb) {
-			dev->stats.tx_packets++;
-			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
+			pkts_compl++;
+			bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent;
 			dma_unmap_single(kdev,
 					dma_unmap_addr(tx_cb_ptr, dma_addr),
 					dma_unmap_len(tx_cb_ptr, dma_len),
 					DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
-			dev->stats.tx_bytes +=
-				dma_unmap_len(tx_cb_ptr, dma_len);
 			dma_unmap_page(kdev,
 					dma_unmap_addr(tx_cb_ptr, dma_addr),
 					dma_unmap_len(tx_cb_ptr, dma_len),
@@ -996,6 +996,9 @@ static void __bcmgenet_tx_reclaim(struct
 	ring->free_bds += txbds_processed;
 	ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK;
 
+	dev->stats.tx_packets += pkts_compl;
+	dev->stats.tx_bytes += bytes_compl;
+
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1))
 		ring->int_disable(priv, ring);
 
@@ -1215,6 +1218,11 @@ static netdev_tx_t bcmgenet_xmit(struct
 		goto out;
 	}
 
+	/* Retain how many bytes will be sent on the wire, without TSB inserted
+	 * by transmit checksum offload
+	 */
+	GENET_CB(skb)->bytes_sent = skb->len;
+
 	/* set the SKB transmit checksum */
 	if (priv->desc_64b_en) {
 		ret = bcmgenet_put_tx_csum(dev, skb);
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -504,6 +504,12 @@ struct bcmgenet_hw_params {
 	u32		flags;
 };
 
+struct bcmgenet_skb_cb {
+	unsigned int bytes_sent;	/* bytes on the wire (no TSB) */
+};
+
+#define GENET_CB(skb)	((struct bcmgenet_skb_cb *)((skb)->cb))
+
 struct bcmgenet_tx_ring {
 	spinlock_t	lock;		/* ring lock */
 	unsigned int	index;		/* ring index */