Add per-ring pre-allocated inline buffer fields (tx_inline_buf,
tx_inline_dma, tx_inline_size) to bnxt_tx_ring_info and helpers to
allocate and free them. A producer and consumer (tx_inline_prod,
tx_inline_cons) are added to track which slot(s) of the inline buffer
are in-use.

The inline buffer will be used by the SW USO path for pre-allocated,
pre-DMA-mapped per-segment header copies. In the future, this
could be extended to support TX copybreak.

Allocation helper is marked __maybe_unused in this commit because it
will be wired in later.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Joe Damato <joe@dama.to>
---
 v5:
   - Added Pavan's Reviewed-by. No functional changes.

 rfcv2:
   - Added a producer and consumer to correctly track the in use header slots.

 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 35 +++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  6 ++++
 2 files changed, 41 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2ab588f8de84..9e3a74ce5b75 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3985,6 +3985,39 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 	return rc;
 }
 
+static void bnxt_free_tx_inline_buf(struct bnxt_tx_ring_info *txr,
+				    struct pci_dev *pdev)
+{
+	if (!txr->tx_inline_buf)
+		return;
+
+	dma_unmap_single(&pdev->dev, txr->tx_inline_dma,
+			 txr->tx_inline_size, DMA_TO_DEVICE);
+	kfree(txr->tx_inline_buf);
+	txr->tx_inline_buf = NULL;
+	txr->tx_inline_size = 0;
+}
+
+static int __maybe_unused bnxt_alloc_tx_inline_buf(struct bnxt_tx_ring_info *txr,
+						   struct pci_dev *pdev,
+						   unsigned int size)
+{
+	txr->tx_inline_buf = kmalloc(size, GFP_KERNEL);
+	if (!txr->tx_inline_buf)
+		return -ENOMEM;
+
+	txr->tx_inline_dma = dma_map_single(&pdev->dev, txr->tx_inline_buf,
+					    size, DMA_TO_DEVICE);
+	if (dma_mapping_error(&pdev->dev, txr->tx_inline_dma)) {
+		kfree(txr->tx_inline_buf);
+		txr->tx_inline_buf = NULL;
+		return -ENOMEM;
+	}
+	txr->tx_inline_size = size;
+
+	return 0;
+}
+
 static void bnxt_free_tx_rings(struct bnxt *bp)
 {
 	int i;
@@ -4003,6 +4036,8 @@ static void bnxt_free_tx_rings(struct bnxt *bp)
 			txr->tx_push = NULL;
 		}
 
+		bnxt_free_tx_inline_buf(txr, pdev);
+
 		ring = &txr->tx_ring_struct;
 
 		bnxt_free_ring(bp, &ring->ring_mem);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a6b04652600e..751dbc055fdd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -994,6 +994,12 @@ struct bnxt_tx_ring_info {
 	dma_addr_t		tx_push_mapping;
 	__le64			data_mapping;
 
+	void			*tx_inline_buf;
+	dma_addr_t		tx_inline_dma;
+	unsigned int		tx_inline_size;
+	u16			tx_inline_prod;
+	u16			tx_inline_cons;
+
 #define BNXT_DEV_STATE_CLOSING	0x1
 	u32			dev_state;
 
-- 
2.52.0