[RFC: DMA_PMD 21/22] net/bnxt: Use DMA_PMD memory for tx header bounce buffers

[Luigi Rizzo]

When dev->dma_pmd_tx_hdrs is enabled, allocate a MAX_TCP_HEADER
bounce buffer per TX ring slot out of the DMA_PMD arena. When the
linear portion of a transmitted packet is at most MAX_TCP_HEADER bytes,
copy it into the pre-mapped bounce buffer instead of calling
dma_map_single()/dma_unmap_single() on every packet.

Signed-off-by: Luigi Rizzo <lrizzo@xxxxxxxxxx>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 45 ++++++++++++++++++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 +
 2 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d7728d0c5b6e6..b9c91eb3aaddd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -680,13 +680,22 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		length = BNXT_MIN_PKT_SIZE;
 	}
 
-	mapping = dma_map_single(&pdev->dev, skb->data, len, DMA_TO_DEVICE);
-
-	if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
-		goto tx_free;
-
-	dma_unmap_addr_set(tx_buf, mapping, mapping);
-	dma_unmap_len_set(tx_buf, len, len);
+	if (txr->tx_hdr_bufs && len + pad <= MAX_TCP_HEADER) {
+		u32 off = RING_TX(bp, prod) * MAX_TCP_HEADER;
+
+		memcpy(txr->tx_hdr_bufs + off, skb->data, len);
+		if (pad && !last_frag)
+			memset(txr->tx_hdr_bufs + off + len, 0, pad);
+		mapping = txr->tx_hdr_bufs_dma + off;
+		dma_unmap_len_set(tx_buf, len, 0);
+	} else {
+		mapping = dma_map_single(&pdev->dev, skb->data, len,
+					 DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(&pdev->dev, mapping)))
+			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);
 
@@ -800,8 +809,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* start back at beginning and unmap skb */
 	prod = txr->tx_prod;
 	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
-	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),
+				 skb_headlen(skb), DMA_TO_DEVICE);
 	prod = NEXT_TX(prod);
 
 	/* unmap remaining mapped pages */
@@ -885,7 +895,6 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 			dma_unmap_single(&pdev->dev, dma_addr, dma_len,
 					 DMA_TO_DEVICE);
 		}
-
 		last = tx_buf->nr_frags;
 
 		for (j = 0; j < last; j++) {
@@ -4111,6 +4120,15 @@ static void bnxt_free_tx_rings(struct bnxt *bp)
 
 		ring = &txr->tx_ring_struct;
 
+		if (txr->tx_hdr_bufs) {
+			dma_free_coherent(&pdev->dev,
+					  ring->ring_mem.nr_pages *
+					  TX_DESC_CNT * MAX_TCP_HEADER,
+					  txr->tx_hdr_bufs,
+					  txr->tx_hdr_bufs_dma);
+			txr->tx_hdr_bufs = NULL;
+		}
+
 		bnxt_free_ring(bp, &ring->ring_mem);
 	}
 }
@@ -4181,6 +4199,13 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 			if (rc)
 				return rc;
 		}
+		if (pdev->dev.dma_pmd_tx_hdrs && i >= bp->tx_nr_rings_xdp)
+			txr->tx_hdr_bufs =
+				dma_alloc_coherent(&pdev->dev,
+						   ring->ring_mem.nr_pages *
+						   TX_DESC_CNT * MAX_TCP_HEADER,
+						   &txr->tx_hdr_bufs_dma,
+						   GFP_KERNEL | __GFP_NOWARN);
 		qidx = bp->tc_to_qidx[j];
 		ring->queue_id = bp->q_info[qidx].queue_id;
 		spin_lock_init(&txr->xdp_tx_lock);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index c673b2ce4a0d2..b42bbabc0eb98 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1003,6 +1003,8 @@ struct bnxt_tx_ring_info {
 	struct tx_push_buffer	*tx_push;
 	dma_addr_t		tx_push_mapping;
 	__le64			data_mapping;
+	void			*tx_hdr_bufs;
+	dma_addr_t		tx_hdr_bufs_dma;
 
 	void			*tx_inline_buf;
 	dma_addr_t		tx_inline_dma;
-- 
2.56.0.rc1.315.gc6ed9934b7-goog