Merge branch 'add-more-feautues-for-enetc-v4-round-1'

Wei Fang says:

====================
Add more feautues for ENETC v4 - round 1

Compared to ENETC v1 (LS1028A), ENETC v4 (i.MX95) adds more features, and
some features are configured completely differently from v1. In order to
more fully support ENETC v4, these features will be added through several
rounds of patch sets. This round adds these features, such as Tx and Rx
checksum offload, increase maximum chained Tx BD number and Large send
offload (LSO).

v1 Link: https://lore.kernel.org/20241107033817.1654163-1-wei.fang@nxp.com
v2 Link: https://lore.kernel.org/20241111015216.1804534-1-wei.fang@nxp.com
v3 Link: https://lore.kernel.org/20241112091447.1850899-1-wei.fang@nxp.com
v4 Link: https://lore.kernel.org/20241115024744.1903377-1-wei.fang@nxp.com
v5 Link: https://lore.kernel.org/20241118060630.1956134-1-wei.fang@nxp.com
v6 Link: https://lore.kernel.org/20241119082344.2022830-1-wei.fang@nxp.com
v6 RESEND Link: https://lore.kernel.org/20241204052932.112446-1-wei.fang@nxp.com
v7 Link: https://lore.kernel.org/20241211063752.744975-1-wei.fang@nxp.com
v8 Link: https://lore.kernel.org/20241213021731.1157535-1-wei.fang@nxp.com
====================

Link: https://patch.msgid.link/20241219054755.1615626-1-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 403 insertions, 30 deletions

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 535969fa0fdb..6a6fc819dfde 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -146,6 +146,27 @@ static int enetc_ptp_parse(struct sk_buff *skb, u8 *udp,
 	return 0;
 }
 
+static bool enetc_tx_csum_offload_check(struct sk_buff *skb)
+{
+	switch (skb->csum_offset) {
+	case offsetof(struct tcphdr, check):
+	case offsetof(struct udphdr, check):
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool enetc_skb_is_ipv6(struct sk_buff *skb)
+{
+	return vlan_get_protocol(skb) == htons(ETH_P_IPV6);
+}
+
+static bool enetc_skb_is_tcp(struct sk_buff *skb)
+{
+	return skb->csum_offset == offsetof(struct tcphdr, check);
+}
+
 static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
 	bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
@@ -163,6 +184,29 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 	dma_addr_t dma;
 	u8 flags = 0;
 
+	enetc_clear_tx_bd(&temp_bd);
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		/* Can not support TSD and checksum offload at the same time */
+		if (priv->active_offloads & ENETC_F_TXCSUM &&
+		    enetc_tx_csum_offload_check(skb) && !tx_ring->tsd_enable) {
+			temp_bd.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START,
+						     skb_network_offset(skb));
+			temp_bd.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN,
+						     skb_network_header_len(skb) / 4);
+			temp_bd.l3_aux1 |= FIELD_PREP(ENETC_TX_BD_L3T,
+						      enetc_skb_is_ipv6(skb));
+			if (enetc_skb_is_tcp(skb))
+				temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T,
+							    ENETC_TXBD_L4T_TCP);
+			else
+				temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T,
+							    ENETC_TXBD_L4T_UDP);
+			flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS;
+		} else if (skb_checksum_help(skb)) {
+			return 0;
+		}
+	}
+
 	i = tx_ring->next_to_use;
 	txbd = ENETC_TXBD(*tx_ring, i);
 	prefetchw(txbd);
@@ -173,7 +217,6 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 
 	temp_bd.addr = cpu_to_le64(dma);
 	temp_bd.buf_len = cpu_to_le16(len);
-	temp_bd.lstatus = 0;
 
 	tx_swbd = &tx_ring->tx_swbd[i];
 	tx_swbd->dma = dma;
@@ -489,8 +532,233 @@ static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso
 	}
 }
 
+static int enetc_lso_count_descs(const struct sk_buff *skb)
+{
+	/* 4 BDs: 1 BD for LSO header + 1 BD for extended BD + 1 BD
+	 * for linear area data but not include LSO header, namely
+	 * skb_headlen(skb) - lso_hdr_len (it may be 0, but that's
+	 * okay, we only need to consider the worst case). And 1 BD
+	 * for gap.
+	 */
+	return skb_shinfo(skb)->nr_frags + 4;
+}
+
+static int enetc_lso_get_hdr_len(const struct sk_buff *skb)
+{
+	int hdr_len, tlen;
+
+	tlen = skb_is_gso_tcp(skb) ? tcp_hdrlen(skb) : sizeof(struct udphdr);
+	hdr_len = skb_transport_offset(skb) + tlen;
+
+	return hdr_len;
+}
+
+static void enetc_lso_start(struct sk_buff *skb, struct enetc_lso_t *lso)
+{
+	lso->lso_seg_size = skb_shinfo(skb)->gso_size;
+	lso->ipv6 = enetc_skb_is_ipv6(skb);
+	lso->tcp = skb_is_gso_tcp(skb);
+	lso->l3_hdr_len = skb_network_header_len(skb);
+	lso->l3_start = skb_network_offset(skb);
+	lso->hdr_len = enetc_lso_get_hdr_len(skb);
+	lso->total_len = skb->len - lso->hdr_len;
+}
+
+static void enetc_lso_map_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+			      int *i, struct enetc_lso_t *lso)
+{
+	union enetc_tx_bd txbd_tmp, *txbd;
+	struct enetc_tx_swbd *tx_swbd;
+	u16 frm_len, frm_len_ext;
+	u8 flags, e_flags = 0;
+	dma_addr_t addr;
+	char *hdr;
+
+	/* Get the first BD of the LSO BDs chain */
+	txbd = ENETC_TXBD(*tx_ring, *i);
+	tx_swbd = &tx_ring->tx_swbd[*i];
+	prefetchw(txbd);
+
+	/* Prepare LSO header: MAC + IP + TCP/UDP */
+	hdr = tx_ring->tso_headers + *i * TSO_HEADER_SIZE;
+	memcpy(hdr, skb->data, lso->hdr_len);
+	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
+
+	/* {frm_len_ext, frm_len} indicates the total length of
+	 * large transmit data unit. frm_len contains the 16 least
+	 * significant bits and frm_len_ext contains the 4 most
+	 * significant bits.
+	 */
+	frm_len = lso->total_len & 0xffff;
+	frm_len_ext = (lso->total_len >> 16) & 0xf;
+
+	/* Set the flags of the first BD */
+	flags = ENETC_TXBD_FLAGS_EX | ENETC_TXBD_FLAGS_CSUM_LSO |
+		ENETC_TXBD_FLAGS_LSO | ENETC_TXBD_FLAGS_L4CS;
+
+	enetc_clear_tx_bd(&txbd_tmp);
+	txbd_tmp.addr = cpu_to_le64(addr);
+	txbd_tmp.hdr_len = cpu_to_le16(lso->hdr_len);
+
+	/* first BD needs frm_len and offload flags set */
+	txbd_tmp.frm_len = cpu_to_le16(frm_len);
+	txbd_tmp.flags = flags;
+
+	txbd_tmp.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START, lso->l3_start);
+	/* l3_hdr_size in 32-bits (4 bytes) */
+	txbd_tmp.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN,
+				      lso->l3_hdr_len / 4);
+	if (lso->ipv6)
+		txbd_tmp.l3_aux1 |= ENETC_TX_BD_L3T;
+	else
+		txbd_tmp.l3_aux0 |= ENETC_TX_BD_IPCS;
+
+	txbd_tmp.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, lso->tcp ?
+				     ENETC_TXBD_L4T_TCP : ENETC_TXBD_L4T_UDP);
+
+	/* For the LSO header we do not set the dma address since
+	 * we do not want it unmapped when we do cleanup. We still
+	 * set len so that we count the bytes sent.
+	 */
+	tx_swbd->len = lso->hdr_len;
+	tx_swbd->do_twostep_tstamp = false;
+	tx_swbd->check_wb = false;
+
+	/* Actually write the header in the BD */
+	*txbd = txbd_tmp;
+
+	/* Get the next BD, and the next BD is extended BD */
+	enetc_bdr_idx_inc(tx_ring, i);
+	txbd = ENETC_TXBD(*tx_ring, *i);
+	tx_swbd = &tx_ring->tx_swbd[*i];
+	prefetchw(txbd);
+
+	enetc_clear_tx_bd(&txbd_tmp);
+	if (skb_vlan_tag_present(skb)) {
+		/* Setup the VLAN fields */
+		txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb));
+		txbd_tmp.ext.tpid = ENETC_TPID_8021Q;
+		e_flags = ENETC_TXBD_E_FLAGS_VLAN_INS;
+	}
+
+	/* Write the BD */
+	txbd_tmp.ext.e_flags = e_flags;
+	txbd_tmp.ext.lso_sg_size = cpu_to_le16(lso->lso_seg_size);
+	txbd_tmp.ext.frm_len_ext = cpu_to_le16(frm_len_ext);
+	*txbd = txbd_tmp;
+}
+
+static int enetc_lso_map_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+			      int *i, struct enetc_lso_t *lso, int *count)
+{
+	union enetc_tx_bd txbd_tmp, *txbd = NULL;
+	struct enetc_tx_swbd *tx_swbd;
+	skb_frag_t *frag;
+	dma_addr_t dma;
+	u8 flags = 0;
+	int len, f;
+
+	len = skb_headlen(skb) - lso->hdr_len;
+	if (len > 0) {
+		dma = dma_map_single(tx_ring->dev, skb->data + lso->hdr_len,
+				     len, DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			return -ENOMEM;
+
+		enetc_bdr_idx_inc(tx_ring, i);
+		txbd = ENETC_TXBD(*tx_ring, *i);
+		tx_swbd = &tx_ring->tx_swbd[*i];
+		prefetchw(txbd);
+		*count += 1;
+
+		enetc_clear_tx_bd(&txbd_tmp);
+		txbd_tmp.addr = cpu_to_le64(dma);
+		txbd_tmp.buf_len = cpu_to_le16(len);
+
+		tx_swbd->dma = dma;
+		tx_swbd->len = len;
+		tx_swbd->is_dma_page = 0;
+		tx_swbd->dir = DMA_TO_DEVICE;
+	}
+
+	frag = &skb_shinfo(skb)->frags[0];
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++, frag++) {
+		if (txbd)
+			*txbd = txbd_tmp;
+
+		len = skb_frag_size(frag);
+		dma = skb_frag_dma_map(tx_ring->dev, frag);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			return -ENOMEM;
+
+		/* Get the next BD */
+		enetc_bdr_idx_inc(tx_ring, i);
+		txbd = ENETC_TXBD(*tx_ring, *i);
+		tx_swbd = &tx_ring->tx_swbd[*i];
+		prefetchw(txbd);
+		*count += 1;
+
+		enetc_clear_tx_bd(&txbd_tmp);
+		txbd_tmp.addr = cpu_to_le64(dma);
+		txbd_tmp.buf_len = cpu_to_le16(len);
+
+		tx_swbd->dma = dma;
+		tx_swbd->len = len;
+		tx_swbd->is_dma_page = 1;
+		tx_swbd->dir = DMA_TO_DEVICE;
+	}
+
+	/* Last BD needs 'F' bit set */
+	flags |= ENETC_TXBD_FLAGS_F;
+	txbd_tmp.flags = flags;
+	*txbd = txbd_tmp;
+
+	tx_swbd->is_eof = 1;
+	tx_swbd->skb = skb;
+
+	return 0;
+}
+
+static int enetc_lso_hw_offload(struct enetc_bdr *tx_ring, struct sk_buff *skb)
+{
+	struct enetc_tx_swbd *tx_swbd;
+	struct enetc_lso_t lso = {0};
+	int err, i, count = 0;
+
+	/* Initialize the LSO handler */
+	enetc_lso_start(skb, &lso);
+	i = tx_ring->next_to_use;
+
+	enetc_lso_map_hdr(tx_ring, skb, &i, &lso);
+	/* First BD and an extend BD */
+	count += 2;
+
+	err = enetc_lso_map_data(tx_ring, skb, &i, &lso, &count);
+	if (err)
+		goto dma_err;
+
+	/* Go to the next BD */
+	enetc_bdr_idx_inc(tx_ring, &i);
+	tx_ring->next_to_use = i;
+	enetc_update_tx_ring_tail(tx_ring);
+
+	return count;
+
+dma_err:
+	do {
+		tx_swbd = &tx_ring->tx_swbd[i];
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	} while (--count);
+
+	return 0;
+}
+
 static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
+	struct enetc_ndev_priv *priv = netdev_priv(tx_ring->ndev);
 	int hdr_len, total_len, data_len;
 	struct enetc_tx_swbd *tx_swbd;
 	union enetc_tx_bd *txbd;
@@ -556,7 +824,7 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 			bd_data_num++;
 			tso_build_data(skb, &tso, size);
 
-			if (unlikely(bd_data_num >= ENETC_MAX_SKB_FRAGS && data_len))
+			if (unlikely(bd_data_num >= priv->max_frags && data_len))
 				goto err_chained_bd;
 		}
 
@@ -594,7 +862,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_bdr *tx_ring;
-	int count, err;
+	int count;
 
 	/* Queue one-step Sync packet if already locked */
 	if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) {
@@ -608,16 +876,28 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 	tx_ring = priv->tx_ring[skb->queue_mapping];
 
 	if (skb_is_gso(skb)) {
-		if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) {
-			netif_stop_subqueue(ndev, tx_ring->index);
-			return NETDEV_TX_BUSY;
-		}
+		/* LSO data unit lengths of up to 256KB are supported */
+		if (priv->active_offloads & ENETC_F_LSO &&
+		    (skb->len - enetc_lso_get_hdr_len(skb)) <=
+		    ENETC_LSO_MAX_DATA_LEN) {
+			if (enetc_bd_unused(tx_ring) < enetc_lso_count_descs(skb)) {
+				netif_stop_subqueue(ndev, tx_ring->index);
+				return NETDEV_TX_BUSY;
+			}
 
-		enetc_lock_mdio();
-		count = enetc_map_tx_tso_buffs(tx_ring, skb);
-		enetc_unlock_mdio();
+			count = enetc_lso_hw_offload(tx_ring, skb);
+		} else {
+			if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) {
+				netif_stop_subqueue(ndev, tx_ring->index);
+				return NETDEV_TX_BUSY;
+			}
+
+			enetc_lock_mdio();
+			count = enetc_map_tx_tso_buffs(tx_ring, skb);
+			enetc_unlock_mdio();
+		}
 	} else {
-		if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS))
+		if (unlikely(skb_shinfo(skb)->nr_frags > priv->max_frags))
 			if (unlikely(skb_linearize(skb)))
 				goto drop_packet_err;
 
@@ -627,11 +907,6 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 			return NETDEV_TX_BUSY;
 		}
 
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			err = skb_checksum_help(skb);
-			if (err)
-				goto drop_packet_err;
-		}
 		enetc_lock_mdio();
 		count = enetc_map_tx_buffs(tx_ring, skb);
 		enetc_unlock_mdio();
@@ -640,7 +915,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 	if (unlikely(!count))
 		goto drop_packet_err;
 
-	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED)
+	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED(priv->max_frags))
 		netif_stop_subqueue(ndev, tx_ring->index);
 
 	return NETDEV_TX_OK;
@@ -908,7 +1183,8 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
 	if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) &&
 		     __netif_subqueue_stopped(ndev, tx_ring->index) &&
 		     !test_bit(ENETC_TX_DOWN, &priv->flags) &&
-		     (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) {
+		     (enetc_bd_unused(tx_ring) >=
+		      ENETC_TXBDS_MAX_NEEDED(priv->max_frags)))) {
 		netif_wake_subqueue(ndev, tx_ring->index);
 	}
 
@@ -1759,6 +2035,9 @@ void enetc_get_si_caps(struct enetc_si *si)
 		rss = enetc_rd(hw, ENETC_SIRSSCAPR);
 		si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(rss);
 	}
+
+	if (val & ENETC_SIPCAPR0_LSO)
+		si->hw_features |= ENETC_SI_F_LSO;
 }
 EXPORT_SYMBOL_GPL(enetc_get_si_caps);
 
@@ -2055,6 +2334,14 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
 	return 0;
 }
 
+static void enetc_set_lso_flags_mask(struct enetc_hw *hw)
+{
+	enetc_wr(hw, ENETC4_SILSOSFMR0,
+		 SILSOSFMR0_VAL_SET(ENETC4_TCP_NL_SEG_FLAGS_DMASK,
+				    ENETC4_TCP_NL_SEG_FLAGS_DMASK));
+	enetc_wr(hw, ENETC4_SILSOSFMR1, 0);
+}
+
 int enetc_configure_si(struct enetc_ndev_priv *priv)
 {
 	struct enetc_si *si = priv->si;
@@ -2068,6 +2355,9 @@ int enetc_configure_si(struct enetc_ndev_priv *priv)
 	/* enable SI */
 	enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN);
 
+	if (si->hw_features & ENETC_SI_F_LSO)
+		enetc_set_lso_flags_mask(hw);
+
 	/* TODO: RSS support for i.MX95 will be supported later, and the
 	 * is_enetc_rev1() condition will be removed
 	 */
@@ -3269,17 +3559,21 @@ EXPORT_SYMBOL_GPL(enetc_pci_remove);
 static const struct enetc_drvdata enetc_pf_data = {
 	.sysclk_freq = ENETC_CLK_400M,
 	.pmac_offset = ENETC_PMAC_OFFSET,
+	.max_frags = ENETC_MAX_SKB_FRAGS,
 	.eth_ops = &enetc_pf_ethtool_ops,
 };
 
 static const struct enetc_drvdata enetc4_pf_data = {
 	.sysclk_freq = ENETC_CLK_333M,
+	.tx_csum = true,
+	.max_frags = ENETC4_MAX_SKB_FRAGS,
 	.pmac_offset = ENETC4_PMAC_OFFSET,
 	.eth_ops = &enetc4_pf_ethtool_ops,
 };
 
 static const struct enetc_drvdata enetc_vf_data = {
 	.sysclk_freq = ENETC_CLK_400M,
+	.max_frags = ENETC_MAX_SKB_FRAGS,
 	.eth_ops = &enetc_vf_ethtool_ops,
 };
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 72fa03dbc2dd..4ad4eb5c5a74 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -41,6 +41,18 @@ struct enetc_tx_swbd {
 	u8 qbv_en:1;
 };
 
+struct enetc_lso_t {
+	bool	ipv6;
+	bool	tcp;
+	u8	l3_hdr_len;
+	u8	hdr_len; /* LSO header length */
+	u8	l3_start;
+	u16	lso_seg_size;
+	int	total_len; /* total data length, not include LSO header */
+};
+
+#define ENETC_LSO_MAX_DATA_LEN		SZ_256K
+
 #define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
 #define ENETC_RXB_TRUESIZE	2048 /* PAGE_SIZE >> 1 */
 #define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
@@ -59,9 +71,16 @@ struct enetc_rx_swbd {
 
 /* ENETC overhead: optional extension BD + 1 BD gap */
 #define ENETC_TXBDS_NEEDED(val)	((val) + 2)
-/* max # of chained Tx BDs is 15, including head and extension BD */
+/* For LS1028A, max # of chained Tx BDs is 15, including head and
+ * extension BD.
+ */
 #define ENETC_MAX_SKB_FRAGS	13
-#define ENETC_TXBDS_MAX_NEEDED	ENETC_TXBDS_NEEDED(ENETC_MAX_SKB_FRAGS + 1)
+/* For ENETC v4 and later versions, max # of chained Tx BDs is 63,
+ * including head and extension BD, but the range of MAX_SKB_FRAGS
+ * is 17 ~ 45, so set ENETC4_MAX_SKB_FRAGS to MAX_SKB_FRAGS.
+ */
+#define ENETC4_MAX_SKB_FRAGS		MAX_SKB_FRAGS
+#define ENETC_TXBDS_MAX_NEEDED(x)	ENETC_TXBDS_NEEDED((x) + 1)
 
 struct enetc_ring_stats {
 	unsigned int packets;
@@ -231,9 +250,12 @@ enum enetc_errata {
 #define ENETC_SI_F_PSFP BIT(0)
 #define ENETC_SI_F_QBV  BIT(1)
 #define ENETC_SI_F_QBU  BIT(2)
+#define ENETC_SI_F_LSO	BIT(3)
 
 struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
+	u8 tx_csum:1;
+	u8 max_frags;
 	u64 sysclk_freq;
 	const struct ethtool_ops *eth_ops;
 };
@@ -341,6 +363,8 @@ enum enetc_active_offloads {
 	ENETC_F_QBV			= BIT(9),
 	ENETC_F_QCI			= BIT(10),
 	ENETC_F_QBU			= BIT(11),
+	ENETC_F_TXCSUM			= BIT(12),
+	ENETC_F_LSO			= BIT(13),
 };
 
 enum enetc_flags_bit {
@@ -375,6 +399,7 @@ struct enetc_ndev_priv {
 	u16 msg_enable;
 
 	u8 preemptible_tcs;
+	u8 max_frags; /* The maximum number of BDs for fragments */
 
 	enum enetc_active_offloads active_offloads;
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 26b220677448..695cb07c74bc 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -12,6 +12,29 @@
 #define NXP_ENETC_VENDOR_ID		0x1131
 #define NXP_ENETC_PF_DEV_ID		0xe101
 
+/**********************Station interface registers************************/
+/* Station interface LSO segmentation flag mask register 0/1 */
+#define ENETC4_SILSOSFMR0		0x1300
+#define  SILSOSFMR0_TCP_MID_SEG		GENMASK(27, 16)
+#define  SILSOSFMR0_TCP_1ST_SEG		GENMASK(11, 0)
+#define  SILSOSFMR0_VAL_SET(first, mid)	(FIELD_PREP(SILSOSFMR0_TCP_MID_SEG, mid) | \
+					 FIELD_PREP(SILSOSFMR0_TCP_1ST_SEG, first))
+
+#define ENETC4_SILSOSFMR1		0x1304
+#define  SILSOSFMR1_TCP_LAST_SEG	GENMASK(11, 0)
+#define   ENETC4_TCP_FLAGS_FIN		BIT(0)
+#define   ENETC4_TCP_FLAGS_SYN		BIT(1)
+#define   ENETC4_TCP_FLAGS_RST		BIT(2)
+#define   ENETC4_TCP_FLAGS_PSH		BIT(3)
+#define   ENETC4_TCP_FLAGS_ACK		BIT(4)
+#define   ENETC4_TCP_FLAGS_URG		BIT(5)
+#define   ENETC4_TCP_FLAGS_ECE		BIT(6)
+#define   ENETC4_TCP_FLAGS_CWR		BIT(7)
+#define   ENETC4_TCP_FLAGS_NS		BIT(8)
+/* According to tso_build_hdr(), clear all special flags for not last packet. */
+#define ENETC4_TCP_NL_SEG_FLAGS_DMASK	(ENETC4_TCP_FLAGS_FIN | \
+					 ENETC4_TCP_FLAGS_RST | ENETC4_TCP_FLAGS_PSH)
+
 /***************************ENETC port registers**************************/
 #define ENETC4_ECAPR0			0x0
 #define  ECAPR0_RFS			BIT(2)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 55ba949230ff..4098f01479bc 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -25,6 +25,7 @@
 #define ENETC_SIPCAPR0	0x20
 #define ENETC_SIPCAPR0_RSS	BIT(8)
 #define ENETC_SIPCAPR0_RFS	BIT(2)
+#define ENETC_SIPCAPR0_LSO	BIT(1)
 #define ENETC_SIPCAPR1	0x24
 #define ENETC_SITGTGR	0x30
 #define ENETC_SIRBGCR	0x38
@@ -554,11 +555,23 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg)
 union enetc_tx_bd {
 	struct {
 		__le64 addr;
-		__le16 buf_len;
+		union {
+			__le16 buf_len;
+			__le16 hdr_len;	/* For LSO, ENETC 4.1 and later */
+		};
 		__le16 frm_len;
 		union {
 			struct {
-				u8 reserved[3];
+				u8 l3_aux0;
+#define ENETC_TX_BD_L3_START	GENMASK(6, 0)
+#define ENETC_TX_BD_IPCS	BIT(7)
+				u8 l3_aux1;
+#define ENETC_TX_BD_L3_HDR_LEN	GENMASK(6, 0)
+#define ENETC_TX_BD_L3T		BIT(7)
+				u8 l4_aux;
+#define ENETC_TX_BD_L4T		GENMASK(7, 5)
+#define ENETC_TXBD_L4T_UDP	1
+#define ENETC_TXBD_L4T_TCP	2
 				u8 flags;
 			}; /* default layout */
 			__le32 txstart;
@@ -569,23 +582,27 @@ union enetc_tx_bd {
 		__le32 tstamp;
 		__le16 tpid;
 		__le16 vid;
-		u8 reserved[6];
+		__le16 lso_sg_size; /* For ENETC 4.1 and later */
+		__le16 frm_len_ext; /* For ENETC 4.1 and later */
+		u8 reserved[2];
 		u8 e_flags;
 		u8 flags;
 	} ext; /* Tx BD extension */
 	struct {
 		__le32 tstamp;
-		u8 reserved[10];
+		u8 reserved[8];
+		__le16 lso_err_count; /* For ENETC 4.1 and later */
 		u8 status;
 		u8 flags;
 	} wb; /* writeback descriptor */
 };
 
 enum enetc_txbd_flags {
-	ENETC_TXBD_FLAGS_RES0 = BIT(0), /* reserved */
+	ENETC_TXBD_FLAGS_L4CS = BIT(0), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_TSE = BIT(1),
+	ENETC_TXBD_FLAGS_LSO = BIT(1), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_W = BIT(2),
-	ENETC_TXBD_FLAGS_RES3 = BIT(3), /* reserved */
+	ENETC_TXBD_FLAGS_CSUM_LSO = BIT(3), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_TXSTART = BIT(4),
 	ENETC_TXBD_FLAGS_EX = BIT(6),
 	ENETC_TXBD_FLAGS_F = BIT(7)
@@ -654,6 +671,8 @@ union enetc_rx_bd {
 #define ENETC_CBD_FLAGS_SF	BIT(7) /* short format */
 #define ENETC_CBD_STATUS_MASK	0xf
 
+#define ENETC_TPID_8021Q	0
+
 struct enetc_cmd_rfse {
 	u8 smac_h[6];
 	u8 smac_m[6];
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 0eecfc833164..3fd9b0727875 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -101,6 +101,7 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	priv->msg_enable = (NETIF_MSG_WOL << 1) - 1;
 	priv->sysclk_freq = si->drvdata->sysclk_freq;
+	priv->max_frags = si->drvdata->max_frags;
 	ndev->netdev_ops = ndev_ops;
 	enetc_set_ethtool_ops(ndev);
 	ndev->watchdog_timeo = 5 * HZ;
@@ -109,16 +110,24 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 			    NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK |
-			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			    NETIF_F_GSO_UDP_L4;
 	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
 			 NETIF_F_HW_VLAN_CTAG_TX |
 			 NETIF_F_HW_VLAN_CTAG_RX |
-			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			 NETIF_F_GSO_UDP_L4;
 	ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM |
 			      NETIF_F_TSO | NETIF_F_TSO6;
 
 	ndev->priv_flags |= IFF_UNICAST_FLT;
 
+	if (si->drvdata->tx_csum)
+		priv->active_offloads |= ENETC_F_TXCSUM;
+
+	if (si->hw_features & ENETC_SI_F_LSO)
+		priv->active_offloads |= ENETC_F_LSO;
+
 	/* TODO: currently, i.MX95 ENETC driver does not support advanced features */
 	if (!is_enetc_rev1(si)) {
 		ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index a5f8ce576b6e..3768752b6008 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -136,6 +136,7 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	priv->msg_enable = (NETIF_MSG_IFUP << 1) - 1;
 	priv->sysclk_freq = si->drvdata->sysclk_freq;
+	priv->max_frags = si->drvdata->max_frags;
 	ndev->netdev_ops = ndev_ops;
 	enetc_set_ethtool_ops(ndev);
 	ndev->watchdog_timeo = 5 * HZ;
@@ -144,11 +145,13 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
 			    NETIF_F_HW_VLAN_CTAG_TX |
 			    NETIF_F_HW_VLAN_CTAG_RX |
-			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			    NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			    NETIF_F_GSO_UDP_L4;
 	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM |
 			 NETIF_F_HW_VLAN_CTAG_TX |
 			 NETIF_F_HW_VLAN_CTAG_RX |
-			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			 NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			 NETIF_F_GSO_UDP_L4;
 	ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM |
 			      NETIF_F_TSO | NETIF_F_TSO6;