[PATCH net-next v3 15/15] bnxt_en: Add kTLS retransmission support

[Michael Chan <michael.chan@broadcom.com>]

If TCP retransmits a TLS packet that requires encryption by the NIC, the
TCP sequence number will go backwards and the hardware will require some
assistance from the driver.  The driver needs to retrieve the TLS record
that covers the byte sequence of the retransmitted packet.  If the
retransmitted packet does not include the tag, the hardware can simply
encrypt the packet using the informtaion in the TLS record.

The driver provides the TLS record information for the retransmitted
packet in the presync TX BD.  The presync TX BD introduced in the last
patch is treated very much like a TX push BD with inline data.  The only
exception is that no SKB will be stored for the presync TX BD.

Retransmission that includes the TLS tag will be handled in future
patches.

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
v3:
Unwind the TX ring properly if the TLS packet cannot be sent.

Improve the OOO TLS counters.

Fix endianness of the record sequence number.

Check valid return address from skb_frag_address_safe().

v2:
https://lore.kernel.org/netdev/20260512212105.3488258-16-michael.chan@broadcom.com/
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  14 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |   4 +
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c |   4 +
 .../net/ethernet/broadcom/bnxt/bnxt_ktls.c    | 152 +++++++++++++++++-
 .../net/ethernet/broadcom/bnxt/bnxt_ktls.h    |   2 +
 5 files changed, 167 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ce3175721be2..2e4d11977407 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -482,9 +482,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int length, pad = 0;
 	u32 len, free_size, vlan_tag_flags, cfa_action, flags;
 	struct bnxt_ktls_offload_ctx_tx *kctx_tx = NULL;
+	u16 prod, start_prod, last_frag, txts_prod;
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	struct pci_dev *pdev = bp->pdev;
-	u16 prod, last_frag, txts_prod;
 	struct bnxt_tx_ring_info *txr;
 	struct bnxt_sw_tx_bd *tx_buf;
 	__le32 lflags = 0;
@@ -500,7 +500,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	txq = netdev_get_tx_queue(dev, i);
 	txr = &bp->tx_ring[bp->tx_ring_map[i]];
-	prod = txr->tx_prod;
 
 #if (MAX_SKB_FRAGS > TX_MAX_FRAGS)
 	if (skb_shinfo(skb)->nr_frags > TX_MAX_FRAGS) {
@@ -529,12 +528,14 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NETDEV_TX_BUSY;
 	}
 
+	start_prod = txr->tx_prod;
 	skb = bnxt_ktls_xmit(bp, txr, skb, &lflags, &kid, &kctx_tx);
 	if (unlikely(!skb)) {
 		dev_core_stats_tx_dropped_inc(dev);
 		return NETDEV_TX_OK;
 	}
 
+	prod = txr->tx_prod;
 	length = skb->len;
 	len = skb_headlen(skb);
 	last_frag = skb_shinfo(skb)->nr_frags;
@@ -817,9 +818,16 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			/* set SKB to err so PTP worker will clean up */
 			ptp->txts_req[txts_prod].tx_skb = ERR_PTR(-EIO);
 	}
+	txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
+	/* Unwind any kTLS presync BDs */
+	if (unlikely(txr->tx_prod != start_prod)) {
+		tx_buf = &txr->tx_buf_ring[RING_TX(bp, start_prod)];
+		tx_buf->is_push = 0;
+		tx_buf->inline_data_bds = 0;
+		WRITE_ONCE(txr->tx_prod, start_prod);
+	}
 	if (txr->kick_pending)
 		bnxt_txr_db_kick(bp, txr, txr->tx_prod);
-	txr->tx_buf_ring[RING_TX(bp, txr->tx_prod)].skb = NULL;
 	dev_core_stats_tx_dropped_inc(dev);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 500bb9171274..339f5bdf2f20 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1191,6 +1191,10 @@ struct bnxt_cmn_sw_stats {
 enum bnxt_ktls_data_counters {
 	BNXT_KTLS_TX_PKTS = 0,
 	BNXT_KTLS_TX_BYTES,
+	BNXT_KTLS_TX_OOO_PKTS,
+	BNXT_KTLS_TX_OOO_FALLBACK_NO_SYNC,
+	BNXT_KTLS_TX_OOO_FALLBACK_NO_SPACE,
+	BNXT_KTLS_TX_OOO_FALLBACK_NO_HDR,
 
 	BNXT_KTLS_MAX_DATA_COUNTERS,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9b2bc38236d7..8d2ee1976e1a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -359,6 +359,10 @@ static const char *const bnxt_ring_drv_stats_arr[] = {
 static const char *const bnxt_ktls_data_stats[] = {
 	[BNXT_KTLS_TX_PKTS]		= "tx_tls_encrypted_packets",
 	[BNXT_KTLS_TX_BYTES]		= "tx_tls_encrypted_bytes",
+	[BNXT_KTLS_TX_OOO_PKTS]			= "tx_tls_ooo_packets",
+	[BNXT_KTLS_TX_OOO_FALLBACK_NO_SYNC]	= "tx_tls_ooo_fallback_no_sync",
+	[BNXT_KTLS_TX_OOO_FALLBACK_NO_SPACE]	= "tx_tls_ooo_fallback_no_space",
+	[BNXT_KTLS_TX_OOO_FALLBACK_NO_HDR]	= "tx_tls_ooo_fallback_no_hdr",
 };
 
 /* kTLS control plane counter strings indexed by enum bnxt_ktls_ctrl_counters */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.c
index 298fb08e7b9b..4ed2d9d8e10c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.c
@@ -339,7 +339,8 @@ int bnxt_ktls_init(struct bnxt *bp)
 	return 0;
 }
 
-static void bnxt_ktls_inc_tx_stats(struct bnxt_tx_ring_info *txr, u32 bytes)
+static void bnxt_ktls_inc_tx_stats(struct bnxt_tx_ring_info *txr, u32 bytes,
+				   bool ooo)
 {
 	struct bnxt_tls_sw_stats *ring_stats = txr->tls_stats;
 
@@ -347,6 +348,128 @@ static void bnxt_ktls_inc_tx_stats(struct bnxt_tx_ring_info *txr, u32 bytes)
 		return;
 	ring_stats->counters[BNXT_KTLS_TX_PKTS]++;
 	ring_stats->counters[BNXT_KTLS_TX_BYTES] += bytes;
+	if (ooo)
+		ring_stats->counters[BNXT_KTLS_TX_OOO_PKTS]++;
+}
+
+static void bnxt_ktls_pre_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			       u32 kid, struct crypto_prefix_cmd *pre_cmd)
+{
+	struct bnxt_sw_tx_bd *tx_buf;
+	struct tx_bd_presync *psbd;
+	u32 bd_space, space;
+	u8 *pcmd;
+	u16 prod;
+
+	prod = txr->tx_prod;
+	tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
+
+	psbd = (void *)&txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
+	psbd->tx_bd_len_flags_type = CRYPTO_PRESYNC_BD_CMD;
+	psbd->tx_bd_kid = cpu_to_le32(BNXT_KID_HW(kid));
+	psbd->tx_bd_opaque =
+		SET_TX_OPAQUE(bp, txr, prod, CRYPTO_PREFIX_CMD_BDS + 1);
+
+	prod = NEXT_TX(prod);
+	pcmd = (void *)&txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
+	bd_space = TX_DESC_CNT - TX_IDX(prod);
+	space = bd_space * sizeof(struct tx_bd);
+	if (space >= CRYPTO_PREFIX_CMD_SIZE) {
+		memcpy(pcmd, pre_cmd, CRYPTO_PREFIX_CMD_SIZE);
+		prod += CRYPTO_PREFIX_CMD_BDS;
+	} else {
+		memcpy(pcmd, pre_cmd, space);
+		prod += bd_space;
+		pcmd = (void *)&txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
+		memcpy(pcmd, (u8 *)pre_cmd + space,
+		       CRYPTO_PREFIX_CMD_SIZE - space);
+		prod += CRYPTO_PREFIX_CMD_BDS - bd_space;
+	}
+	txr->tx_prod = prod;
+	tx_buf->is_push = 1;
+	/* Minus 1 since the header psbd is a single entry short BD */
+	tx_buf->inline_data_bds = CRYPTO_PREFIX_CMD_BDS - 1;
+}
+
+static int bnxt_ktls_tx_ooo(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			    struct sk_buff *skb, u32 payload_len, u32 seq,
+			    struct tls_context *tls_ctx)
+{
+	struct bnxt_tls_sw_stats *ring_stats = txr->tls_stats;
+	struct tls_offload_context_tx *tx_tls_ctx;
+	struct bnxt_ktls_offload_ctx_tx *kctx_tx;
+	u32 hdr_tcp_seq, end_seq, total_bds;
+	struct crypto_prefix_cmd pcmd = {};
+	struct tls_record_info *record;
+	unsigned long flags;
+	bool fwd = false;
+	__le64 le_rec_sn;
+	u64 rec_sn;
+	u8 *hdr;
+	int rc;
+
+	tx_tls_ctx = tls_offload_ctx_tx(tls_ctx);
+	kctx_tx = bnxt_get_ktls_ctx_tx(tls_ctx);
+	end_seq = seq + skb->len - skb_tcp_all_headers(skb);
+	if (unlikely(after(seq, kctx_tx->tcp_seq_no) ||
+		     after(end_seq, kctx_tx->tcp_seq_no))) {
+		fwd = true;
+		pcmd.flags = CRYPTO_PREFIX_CMD_FLAGS_UPDATE_IN_ORDER_VAR_LE;
+	}
+
+	spin_lock_irqsave(&tx_tls_ctx->lock, flags);
+	record = tls_get_record(tx_tls_ctx, seq, &rec_sn);
+	if (!record || !record->num_frags) {
+		rc = -EPROTO;
+		ring_stats->counters[BNXT_KTLS_TX_OOO_FALLBACK_NO_SYNC]++;
+		goto unlock_exit;
+	}
+	hdr_tcp_seq = tls_record_start_seq(record);
+	hdr = skb_frag_address_safe(&record->frags[0]);
+
+	total_bds = CRYPTO_PRESYNC_BDS + skb_shinfo(skb)->nr_frags + 2;
+	if (bnxt_tx_avail(bp, txr) < total_bds) {
+		rc = -ENOSPC;
+		ring_stats->counters[BNXT_KTLS_TX_OOO_FALLBACK_NO_SPACE]++;
+		goto unlock_exit;
+	}
+
+	if (before(record->end_seq - tls_ctx->prot_info.tag_size,
+		   seq + payload_len)) {
+		/* retransmission includes tag bytes */
+		rc = -EOPNOTSUPP;
+		goto unlock_exit;
+	}
+	pcmd.header_tcp_seq_num = cpu_to_le32(hdr_tcp_seq);
+	pcmd.start_tcp_seq_num = cpu_to_le32(seq);
+	pcmd.end_tcp_seq_num = cpu_to_le32(seq + payload_len - 1);
+	if (tls_ctx->prot_info.version == TLS_1_2_VERSION) {
+		u32 nonce_bytes = tls_ctx->prot_info.iv_size;
+		u32 retrans_off = seq - hdr_tcp_seq;
+
+		if (!hdr) {
+			rc = -ENOBUFS;
+			ring_stats->counters[BNXT_KTLS_TX_OOO_FALLBACK_NO_HDR]++;
+			goto unlock_exit;
+		}
+		if (retrans_off > 5 && retrans_off < 5 + nonce_bytes)
+			nonce_bytes = retrans_off - 5;
+		memcpy(pcmd.explicit_nonce, hdr + 5, nonce_bytes);
+	}
+	le_rec_sn = cpu_to_le64(rec_sn);
+	memcpy(&pcmd.record_seq_num[0], &le_rec_sn, sizeof(le_rec_sn));
+
+	rc = 0;
+	bnxt_ktls_pre_xmit(bp, txr, kctx_tx->kid, &pcmd);
+
+	if (fwd) {
+		kctx_tx->next_tcp_seq_no = end_seq;
+		kctx_tx->pending_fwd = 1;
+	}
+
+unlock_exit:
+	spin_unlock_irqrestore(&tx_tls_ctx->lock, flags);
+	return rc;
 }
 
 struct sk_buff *bnxt_ktls_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
@@ -357,6 +480,7 @@ struct sk_buff *bnxt_ktls_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	struct bnxt_ktls_offload_ctx_tx *kctx_tx;
 	struct tls_context *tls_ctx;
 	u32 seq, payload_len;
+	int rc;
 
 	if (!IS_ENABLED(CONFIG_TLS_DEVICE) || !ktls ||
 	    !tls_is_skb_tx_device_offloaded(skb))
@@ -375,14 +499,25 @@ struct sk_buff *bnxt_ktls_xmit(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 		 */
 		kctx_tx->next_tcp_seq_no = seq + payload_len;
 		kctx_tx->pending_bytes = payload_len;
+		kctx_tx->pending_ooo = 0;
+		kctx_tx->pending_fwd = 1;
 		*kid = BNXT_KID_HW(kctx_tx->kid);
 		*kctx_tx_p = kctx_tx;
 		*lflags |= cpu_to_le32(TX_BD_FLAGS_CRYPTO_EN |
 				       BNXT_TX_KID_LO(*kid));
 	} else {
-		skb = tls_encrypt_skb(skb);
-		if (!skb)
-			return NULL;
+		kctx_tx->pending_fwd = 0;
+		rc = bnxt_ktls_tx_ooo(bp, txr, skb, payload_len, seq, tls_ctx);
+		if (rc)
+			return tls_encrypt_skb(skb);
+
+		kctx_tx->pending_bytes = payload_len;
+		kctx_tx->pending_ooo = 1;
+		*kid = BNXT_KID_HW(kctx_tx->kid);
+		*kctx_tx_p = kctx_tx;
+		*lflags |= cpu_to_le32(TX_BD_FLAGS_CRYPTO_EN |
+				       BNXT_TX_KID_LO(*kid));
+		return skb;
 	}
 	return skb;
 }
@@ -392,8 +527,13 @@ void bnxt_ktls_xmit_commit(struct bnxt_tx_ring_info *txr,
 {
 	if (!kctx_tx)
 		return;
-	kctx_tx->tcp_seq_no = kctx_tx->next_tcp_seq_no;
-	bnxt_ktls_inc_tx_stats(txr, kctx_tx->pending_bytes);
+	if (kctx_tx->pending_fwd)
+		kctx_tx->tcp_seq_no = kctx_tx->next_tcp_seq_no;
+	bnxt_ktls_inc_tx_stats(txr, kctx_tx->pending_bytes,
+			       kctx_tx->pending_ooo);
+	kctx_tx->pending_bytes = 0;
+	kctx_tx->pending_fwd = 0;
+	kctx_tx->pending_ooo = 0;
 }
 
 int bnxt_ktls_alloc_tx_ring_stats(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.h
index 1c935e0d413d..40b94bbf5a38 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ktls.h
@@ -43,6 +43,8 @@ struct bnxt_ktls_offload_ctx_tx {
 	u32		next_tcp_seq_no;/* staged tcp seq no */
 	u32		kid;
 	u32		pending_bytes;	/* staged payload bytes */
+	u32		pending_fwd:1;
+	u32		pending_ooo:1;
 };
 
 struct bnxt_ktls_tx_driver_state {
-- 
2.51.0