[RFC net-next 05/10] net: bnxt: Use dma_unmap_len for TX completion unmapping

[Joe Damato]

Store the DMA mapping length in each TX buffer descriptor via
dma_unmap_len_set at submit time, and use dma_unmap_len at completion
time.

This is a no-op for normal packets but prepares for software USO,
where header BDs set dma_unmap_len to 0 because the header buffer
is unmapped collectively rather than per-segment.

Suggested-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Signed-off-by: Joe Damato <joe@xxxxxxx>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 51 ++++++++++++++---------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c52db7135ded..b801daf3f328 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -657,6 +657,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_free;
 
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
+	dma_unmap_len_set(tx_buf, len, len);
 	flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD |
 		TX_BD_CNT(last_frag + 2);
 
@@ -721,6 +722,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
 		netmem_dma_unmap_addr_set(skb_frag_netmem(frag), tx_buf,
 					  mapping, mapping);
+		dma_unmap_len_set(tx_buf, len, len);
 
 		txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
@@ -810,7 +812,8 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	u16 hw_cons = txr->tx_hw_cons;
 	unsigned int tx_bytes = 0;
 	u16 cons = txr->tx_cons;
-	skb_frag_t *frag;
+	unsigned int dma_len;
+	dma_addr_t dma_addr;
 	int tx_pkts = 0;
 	bool rc = false;
 
@@ -845,19 +848,27 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 			goto next_tx_int;
 		}
 
-		dma_unmap_single(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
-				 skb_headlen(skb), DMA_TO_DEVICE);
+		if (dma_unmap_len(tx_buf, len)) {
+			dma_addr = dma_unmap_addr(tx_buf, mapping);
+			dma_len = dma_unmap_len(tx_buf, len);
+
+			dma_unmap_single(&pdev->dev, dma_addr, dma_len,
+					 DMA_TO_DEVICE);
+		}
+
 		last = tx_buf->nr_frags;
 
 		for (j = 0; j < last; j++) {
-			frag = &skb_shinfo(skb)->frags[j];
 			cons = NEXT_TX(cons);
 			tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
-			netmem_dma_unmap_page_attrs(&pdev->dev,
-						    dma_unmap_addr(tx_buf,
-								   mapping),
-						    skb_frag_size(frag),
-						    DMA_TO_DEVICE, 0);
+			if (dma_unmap_len(tx_buf, len)) {
+				dma_addr = dma_unmap_addr(tx_buf, mapping);
+				dma_len = dma_unmap_len(tx_buf, len);
+
+				netmem_dma_unmap_page_attrs(&pdev->dev,
+							    dma_addr, dma_len,
+							    DMA_TO_DEVICE, 0);
+			}
 		}
 		if (unlikely(is_ts_pkt)) {
 			if (BNXT_CHIP_P5(bp)) {
@@ -3436,23 +3447,25 @@ static void bnxt_free_one_tx_ring_skbs(struct bnxt *bp,
 			continue;
 		}
 
-		dma_unmap_single(&pdev->dev,
-				 dma_unmap_addr(tx_buf, mapping),
-				 skb_headlen(skb),
-				 DMA_TO_DEVICE);
+		if (dma_unmap_len(tx_buf, len))
+			dma_unmap_single(&pdev->dev,
+					 dma_unmap_addr(tx_buf, mapping),
+					 dma_unmap_len(tx_buf, len),
+					 DMA_TO_DEVICE);
 
 		last = tx_buf->nr_frags;
 		i += 2;
 		for (j = 0; j < last; j++, i++) {
 			int ring_idx = i & bp->tx_ring_mask;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 
 			tx_buf = &txr->tx_buf_ring[ring_idx];
-			netmem_dma_unmap_page_attrs(&pdev->dev,
-						    dma_unmap_addr(tx_buf,
-								   mapping),
-						    skb_frag_size(frag),
-						    DMA_TO_DEVICE, 0);
+			if (dma_unmap_len(tx_buf, len))
+				netmem_dma_unmap_page_attrs(&pdev->dev,
+							    dma_unmap_addr(tx_buf,
+									   mapping),
+							    dma_unmap_len(tx_buf,
+									  len),
+							    DMA_TO_DEVICE, 0);
 		}
 		dev_kfree_skb(skb);
 	}
-- 
2.52.0