[RFC net-next 08/10] net: bnxt: Implement software USO

[Joe Damato <joe@dama.to>]

Implement bnxt_sw_udp_gso_xmit() using the core tso_dma_map API and
the pre-allocated TX inline buffer for per-segment headers.

The xmit path:
1. Calls tso_start() to initialize TSO state
2. Stack-allocates a tso_dma_map and calls tso_dma_map_init() to
   DMA-map the linear payload and all frags upfront.
3. For each segment:
   - Copies and patches headers via tso_build_hdr() into the
     pre-allocated tx_inline_buf (DMA-synced per segment)
   - Counts payload BDs via tso_dma_map_count()
   - Emits long BD (header) + ext BD + payload BDs
   - Payload BDs use tso_dma_map_next() which yields (dma_addr,
     chunk_len, mapping_len) tuples; mapping_len is set as
     dma_unmap_len on the first BD of each DMA mapping so the
     completion path can unmap per-BD

Header BDs set dma_unmap_len=0 since the inline buffer is pre-allocated
and unmapped only at ring teardown.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Joe Damato <joe@dama.to>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c | 158 ++++++++++++++++++
 1 file changed, 158 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c
index b296769ee4fe..fe1f791681e1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_gso.c
@@ -19,11 +19,169 @@
 #include "bnxt.h"
 #include "bnxt_gso.h"
 
+static u32 bnxt_sw_gso_lhint(unsigned int len)
+{
+	if (len <= 512)
+		return TX_BD_FLAGS_LHINT_512_AND_SMALLER;
+	else if (len <= 1023)
+		return TX_BD_FLAGS_LHINT_512_TO_1023;
+	else if (len <= 2047)
+		return TX_BD_FLAGS_LHINT_1024_TO_2047;
+	else
+		return TX_BD_FLAGS_LHINT_2048_AND_LARGER;
+}
+
 netdev_tx_t bnxt_sw_udp_gso_xmit(struct bnxt *bp,
 				 struct bnxt_tx_ring_info *txr,
 				 struct netdev_queue *txq,
 				 struct sk_buff *skb)
 {
+	unsigned int hdr_len, mss, num_segs;
+	struct pci_dev *pdev = bp->pdev;
+	unsigned int total_payload;
+	struct tso_dma_map map;
+	u32 vlan_tag_flags = 0;
+	int i, bds_needed;
+	struct tso_t tso;
+	u16 cfa_action;
+	u16 prod;
+
+	hdr_len = tso_start(skb, &tso);
+	mss = skb_shinfo(skb)->gso_size;
+	total_payload = skb->len - hdr_len;
+	num_segs = DIV_ROUND_UP(total_payload, mss);
+
+	/* Zero the csum fields so tso_build_hdr will propagate zeroes into
+	 * every segment header. HW csum offload will recompute from scratch.
+	 */
+	udp_hdr(skb)->check = 0;
+	if (!tso.ipv6)
+		ip_hdr(skb)->check = 0;
+
+	if (unlikely(num_segs <= 1))
+		return NETDEV_TX_OK;
+
+	/* Upper bound on the number of descriptors needed.
+	 *
+	 * Each segment uses 1 long BD + 1 ext BD + payload BDs, which is
+	 * at most num_segs + nr_frags (each frag boundary crossing adds at
+	 * most 1 extra BD).
+	 */
+	bds_needed = 3 * num_segs + skb_shinfo(skb)->nr_frags + 1;
+
+	if (unlikely(bnxt_tx_avail(bp, txr) < bds_needed)) {
+		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
+				   bp->tx_wake_thresh);
+		return NETDEV_TX_BUSY;
+	}
+
+	if (unlikely(tso_dma_map_init(&map, &pdev->dev, skb, hdr_len)))
+		goto drop;
+
+	cfa_action = bnxt_xmit_get_cfa_action(skb);
+	if (skb_vlan_tag_present(skb)) {
+		vlan_tag_flags = TX_BD_CFA_META_KEY_VLAN |
+				 skb_vlan_tag_get(skb);
+		if (skb->vlan_proto == htons(ETH_P_8021Q))
+			vlan_tag_flags |= 1 << TX_BD_CFA_META_TPID_SHIFT;
+	}
+
+	prod = txr->tx_prod;
+
+	for (i = 0; i < num_segs; i++) {
+		unsigned int seg_payload = min_t(unsigned int, mss,
+						 total_payload - i * mss);
+		dma_addr_t this_hdr_dma = txr->tx_inline_dma + i * hdr_len;
+		void *this_hdr = txr->tx_inline_buf + i * hdr_len;
+		struct bnxt_sw_tx_bd *tx_buf;
+		unsigned int mapping_len;
+		unsigned int chunk_len;
+		dma_addr_t dma_addr;
+		struct tx_bd *txbd;
+		int bd_count;
+		__le32 csum;
+		bool last;
+		u32 flags;
+
+		last = (i == num_segs - 1);
+
+		tso_build_hdr(skb, this_hdr, &tso, seg_payload, last);
+
+		dma_sync_single_for_device(&pdev->dev, this_hdr_dma,
+					   hdr_len, DMA_TO_DEVICE);
+
+		bd_count = tso_dma_map_count(&map, seg_payload);
+
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
+		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
+
+		tx_buf->skb = skb;
+		tx_buf->nr_frags = bd_count;
+		tx_buf->is_push = 0;
+		tx_buf->is_ts_pkt = 0;
+
+		dma_unmap_addr_set(tx_buf, mapping, this_hdr_dma);
+		dma_unmap_len_set(tx_buf, len, 0);
+
+		tx_buf->is_sw_gso = last ? BNXT_SW_GSO_LAST : BNXT_SW_GSO_MID;
+
+		flags = (hdr_len << TX_BD_LEN_SHIFT) |
+			TX_BD_TYPE_LONG_TX_BD |
+			TX_BD_CNT(2 + bd_count);
+
+		flags |= bnxt_sw_gso_lhint(hdr_len + seg_payload);
+
+		txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
+		txbd->tx_bd_haddr = cpu_to_le64(this_hdr_dma);
+		txbd->tx_bd_opaque = SET_TX_OPAQUE(bp, txr, prod,
+						   2 + bd_count);
+
+		csum = cpu_to_le32(TX_BD_FLAGS_TCP_UDP_CHKSUM |
+				   TX_BD_FLAGS_IP_CKSUM);
+
+		prod = NEXT_TX(prod);
+		bnxt_init_ext_bd(bp, txr, prod, csum,
+				 vlan_tag_flags, cfa_action);
+
+		while (tso_dma_map_next(&map, &dma_addr, &chunk_len,
+					&mapping_len, seg_payload)) {
+			prod = NEXT_TX(prod);
+			txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
+			tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
+
+			txbd->tx_bd_haddr = cpu_to_le64(dma_addr);
+			dma_unmap_addr_set(tx_buf, mapping, dma_addr);
+			dma_unmap_len_set(tx_buf, len, mapping_len);
+			tx_buf->skb = NULL;
+			tx_buf->is_sw_gso = 0;
+
+			flags = chunk_len << TX_BD_LEN_SHIFT;
+			txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
+			txbd->tx_bd_opaque = 0;
+
+			seg_payload -= chunk_len;
+		}
+
+		txbd->tx_bd_len_flags_type |=
+			cpu_to_le32(TX_BD_FLAGS_PACKET_END);
+
+		prod = NEXT_TX(prod);
+	}
+
+	netdev_tx_sent_queue(txq, skb->len);
+
+	WRITE_ONCE(txr->tx_prod, prod);
+	/* Sync BDs before doorbell */
+	wmb();
+	bnxt_db_write(bp, &txr->tx_db, prod);
+
+	if (unlikely(bnxt_tx_avail(bp, txr) <= bp->tx_wake_thresh))
+		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
+				   bp->tx_wake_thresh);
+
+	return NETDEV_TX_OK;
+
+drop:
 	dev_kfree_skb_any(skb);
 	dev_core_stats_tx_dropped_inc(bp->dev);
 	return NETDEV_TX_OK;
-- 
2.52.0