[PATCH v4 net-next 0/5] Add more feautues for ENETC v4 - round 1

[PATCH v4 net-next 0/5] Add more feautues for ENETC v4 - round 1

[Wei Fang]

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/imx/20241107033817.1654163-1-wei.fang@nxp.com/
v2 Link: https://lore.kernel.org/imx/20241111015216.1804534-1-wei.fang@nxp.com/
v3 Link: https://lore.kernel.org/imx/20241112091447.1850899-1-wei.fang@nxp.com/
---

Wei Fang (5):
  net: enetc: add Rx checksum offload for i.MX95 ENETC
  net: enetc: add Tx checksum offload for i.MX95 ENETC
  net: enetc: update max chained Tx BD number for i.MX95 ENETC
  net: enetc: add LSO support for i.MX95 ENETC PF
  net: enetc: add UDP segmentation offload support

 drivers/net/ethernet/freescale/enetc/enetc.c  | 344 ++++++++++++++++--
 drivers/net/ethernet/freescale/enetc/enetc.h  |  32 +-
 .../net/ethernet/freescale/enetc/enetc4_hw.h  |  22 ++
 .../net/ethernet/freescale/enetc/enetc_hw.h   |  31 +-
 .../freescale/enetc/enetc_pf_common.c         |  16 +-
 .../net/ethernet/freescale/enetc/enetc_vf.c   |   7 +-
 6 files changed, 418 insertions(+), 34 deletions(-)

-- 
2.34.1

[PATCH v4 net-next 1/5] net: enetc: add Rx checksum offload for i.MX95 ENETC

[Wei Fang]

ENETC rev 4.1 supports TCP and UDP checksum offload for receive, the bit
108 of the Rx BD will be set if the TCP/UDP checksum is correct. Since
this capability is not defined in register, the rx_csum bit is added to
struct enetc_drvdata to indicate whether the device supports Rx checksum
offload.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
---
v2: no changes
v3: no changes
v4: no changes
---
 drivers/net/ethernet/freescale/enetc/enetc.c       | 14 ++++++++++----
 drivers/net/ethernet/freescale/enetc/enetc.h       |  2 ++
 drivers/net/ethernet/freescale/enetc/enetc_hw.h    |  2 ++
 .../net/ethernet/freescale/enetc/enetc_pf_common.c |  3 +++
 4 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 35634c516e26..3137b6ee62d3 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1011,10 +1011,15 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 
 	/* TODO: hashing */
 	if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
-		u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
-
-		skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
-		skb->ip_summed = CHECKSUM_COMPLETE;
+		if (priv->active_offloads & ENETC_F_RXCSUM &&
+		    le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_L4_CSUM_OK) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		} else {
+			u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
+
+			skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
+			skb->ip_summed = CHECKSUM_COMPLETE;
+		}
 	}
 
 	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) {
@@ -3281,6 +3286,7 @@ static const struct enetc_drvdata enetc_pf_data = {
 static const struct enetc_drvdata enetc4_pf_data = {
 	.sysclk_freq = ENETC_CLK_333M,
 	.pmac_offset = ENETC4_PMAC_OFFSET,
+	.rx_csum = 1,
 	.eth_ops = &enetc4_pf_ethtool_ops,
 };
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 72fa03dbc2dd..5b65f79e05be 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -234,6 +234,7 @@ enum enetc_errata {
 
 struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
+	u8 rx_csum:1;
 	u64 sysclk_freq;
 	const struct ethtool_ops *eth_ops;
 };
@@ -341,6 +342,7 @@ enum enetc_active_offloads {
 	ENETC_F_QBV			= BIT(9),
 	ENETC_F_QCI			= BIT(10),
 	ENETC_F_QBU			= BIT(11),
+	ENETC_F_RXCSUM			= BIT(12),
 };
 
 enum enetc_flags_bit {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 7c3285584f8a..4b8fd1879005 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -645,6 +645,8 @@ union enetc_rx_bd {
 #define ENETC_RXBD_LSTATUS(flags)	((flags) << 16)
 #define ENETC_RXBD_FLAG_VLAN	BIT(9)
 #define ENETC_RXBD_FLAG_TSTMP	BIT(10)
+/* UDP and TCP checksum offload, for ENETC 4.1 and later */
+#define ENETC_RXBD_FLAG_L4_CSUM_OK	BIT(12)
 #define ENETC_RXBD_FLAG_TPID	GENMASK(1, 0)
 
 #define ENETC_MAC_ADDR_FILT_CNT	8 /* # of supported entries per port */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 0eecfc833164..91e79582a541 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -119,6 +119,9 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 
 	ndev->priv_flags |= IFF_UNICAST_FLT;
 
+	if (si->drvdata->rx_csum)
+		priv->active_offloads |= ENETC_F_RXCSUM;
+
 	/* 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);
-- 
2.34.1

[PATCH v4 net-next 2/5] net: enetc: add Tx checksum offload for i.MX95 ENETC

[Wei Fang]

In addition to supporting Rx checksum offload, i.MX95 ENETC also supports
Tx checksum offload. The transmit checksum offload is implemented through
the Tx BD. To support Tx checksum offload, software needs to fill some
auxiliary information in Tx BD, such as IP version, IP header offset and
size, whether L4 is UDP or TCP, etc.

Same as Rx checksum offload, Tx checksum offload capability isn't defined
in register, so tx_csum bit is added to struct enetc_drvdata to indicate
whether the device supports Tx checksum offload.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
---
v2: refine enetc_tx_csum_offload_check().
v3:
1. refine enetc_tx_csum_offload_check() and enetc_skb_is_tcp() through
skb->csum_offset instead of touching skb->data.
2. add enetc_skb_is_ipv6() helper function
v4: no changes
---
 drivers/net/ethernet/freescale/enetc/enetc.c  | 51 ++++++++++++++++---
 drivers/net/ethernet/freescale/enetc/enetc.h  |  2 +
 .../net/ethernet/freescale/enetc/enetc_hw.h   | 14 +++--
 .../freescale/enetc/enetc_pf_common.c         |  3 ++
 4 files changed, 60 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 3137b6ee62d3..eeefd536d051 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -143,6 +143,27 @@ 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 inline bool enetc_skb_is_ipv6(struct sk_buff *skb)
+{
+	return vlan_get_protocol(skb) == htons(ETH_P_IPV6);
+}
+
+static inline 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;
@@ -160,6 +181,27 @@ 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_start = skb_network_offset(skb);
+			temp_bd.ipcs = enetc_skb_is_ipv6(skb) ? 0 : 1;
+			temp_bd.l3_hdr_size = skb_network_header_len(skb) / 4;
+			temp_bd.l3t = enetc_skb_is_ipv6(skb) ? 1 : 0;
+			temp_bd.l4t = enetc_skb_is_tcp(skb) ? ENETC_TXBD_L4T_TCP :
+							      ENETC_TXBD_L4T_UDP;
+			flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS;
+		} else {
+			if (skb_checksum_help(skb)) {
+				dev_err(tx_ring->dev, "skb_checksum_help() error\n");
+
+				return 0;
+			}
+		}
+	}
+
 	i = tx_ring->next_to_use;
 	txbd = ENETC_TXBD(*tx_ring, i);
 	prefetchw(txbd);
@@ -170,7 +212,6 @@ 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;
@@ -591,7 +632,7 @@ 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) {
@@ -624,11 +665,6 @@ 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();
@@ -3287,6 +3323,7 @@ static const struct enetc_drvdata enetc4_pf_data = {
 	.sysclk_freq = ENETC_CLK_333M,
 	.pmac_offset = ENETC4_PMAC_OFFSET,
 	.rx_csum = 1,
+	.tx_csum = 1,
 	.eth_ops = &enetc4_pf_ethtool_ops,
 };
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 5b65f79e05be..ee11ff97e9ed 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -235,6 +235,7 @@ enum enetc_errata {
 struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
 	u8 rx_csum:1;
+	u8 tx_csum:1;
 	u64 sysclk_freq;
 	const struct ethtool_ops *eth_ops;
 };
@@ -343,6 +344,7 @@ enum enetc_active_offloads {
 	ENETC_F_QCI			= BIT(10),
 	ENETC_F_QBU			= BIT(11),
 	ENETC_F_RXCSUM			= BIT(12),
+	ENETC_F_TXCSUM			= BIT(13),
 };
 
 enum enetc_flags_bit {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 4b8fd1879005..590b1412fadf 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -558,7 +558,12 @@ union enetc_tx_bd {
 		__le16 frm_len;
 		union {
 			struct {
-				u8 reserved[3];
+				u8 l3_start:7;
+				u8 ipcs:1;
+				u8 l3_hdr_size:7;
+				u8 l3t:1;
+				u8 resv:5;
+				u8 l4t:3;
 				u8 flags;
 			}; /* default layout */
 			__le32 txstart;
@@ -582,10 +587,10 @@ union enetc_tx_bd {
 };
 
 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_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)
@@ -594,6 +599,9 @@ enum enetc_txbd_flags {
 #define ENETC_TXBD_TXSTART_MASK GENMASK(24, 0)
 #define ENETC_TXBD_FLAGS_OFFSET 24
 
+#define ENETC_TXBD_L4T_UDP	BIT(0)
+#define ENETC_TXBD_L4T_TCP	BIT(1)
+
 static inline __le32 enetc_txbd_set_tx_start(u64 tx_start, u8 flags)
 {
 	u32 temp;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 91e79582a541..3a8a5b6d8c26 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -122,6 +122,9 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	if (si->drvdata->rx_csum)
 		priv->active_offloads |= ENETC_F_RXCSUM;
 
+	if (si->drvdata->tx_csum)
+		priv->active_offloads |= ENETC_F_TXCSUM;
+
 	/* 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);
-- 
2.34.1

[PATCH v4 net-next 3/5] net: enetc: update max chained Tx BD number for i.MX95 ENETC

[Wei Fang]

The max chained Tx BDs of latest ENETC (i.MX95 ENETC, rev 4.1) has been
increased to 63, but since the range of MAX_SKB_FRAGS is 17~45, so for
i.MX95 ENETC and later revision, it is better to set ENETC4_MAX_SKB_FRAGS
to MAX_SKB_FRAGS.

In addition, add max_frags in struct enetc_drvdata to indicate the max
chained BDs supported by device. Because the max number of chained BDs
supported by LS1028A and i.MX95 ENETC is different.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
---
v2:
1. Refine the commit message
2. Add Reviewed-by tag
v3: no changes
v4: no changes
---
 drivers/net/ethernet/freescale/enetc/enetc.c        | 13 +++++++++----
 drivers/net/ethernet/freescale/enetc/enetc.h        | 13 +++++++++++--
 .../net/ethernet/freescale/enetc/enetc_pf_common.c  |  1 +
 drivers/net/ethernet/freescale/enetc/enetc_vf.c     |  1 +
 4 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index eeefd536d051..7c6b844c2e96 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -529,6 +529,7 @@ static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso
 
 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;
@@ -594,7 +595,7 @@ 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;
 		}
 
@@ -655,7 +656,7 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb,
 		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;
 
@@ -673,7 +674,7 @@ 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;
@@ -941,7 +942,8 @@ 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);
 	}
 
@@ -3316,6 +3318,7 @@ 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,
 };
 
@@ -3324,11 +3327,13 @@ static const struct enetc_drvdata enetc4_pf_data = {
 	.pmac_offset = ENETC4_PMAC_OFFSET,
 	.rx_csum = 1,
 	.tx_csum = 1,
+	.max_frags = ENETC4_MAX_SKB_FRAGS,
 	.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 ee11ff97e9ed..a78af4f624e0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -59,9 +59,16 @@ 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;
@@ -236,6 +243,7 @@ struct enetc_drvdata {
 	u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */
 	u8 rx_csum:1;
 	u8 tx_csum:1;
+	u8 max_frags;
 	u64 sysclk_freq;
 	const struct ethtool_ops *eth_ops;
 };
@@ -379,6 +387,7 @@ 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/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 3a8a5b6d8c26..2c4c6af672e7 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;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 31e630638090..052833acd220 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -129,6 +129,7 @@ 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;
-- 
2.34.1

[PATCH v4 net-next 4/5] net: enetc: add LSO support for i.MX95 ENETC PF

[Wei Fang]

ENETC rev 4.1 supports large send offload (LSO), segmenting large TCP
and UDP transmit units into multiple Ethernet frames. To support LSO,
software needs to fill some auxiliary information in Tx BD, such as LSO
header length, frame length, LSO maximum segment size, etc.

At 1Gbps link rate, TCP segmentation was tested using iperf3, and the
CPU performance before and after applying the patch was compared through
the top command. It can be seen that LSO saves a significant amount of
CPU cycles compared to software TSO.

Before applying the patch:
%Cpu(s):  0.1 us,  4.1 sy,  0.0 ni, 85.7 id,  0.0 wa,  0.5 hi,  9.7 si

After applying the patch:
%Cpu(s):  0.1 us,  2.3 sy,  0.0 ni, 94.5 id,  0.0 wa,  0.4 hi,  2.6 si

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
---
v2: no changes
v3: use enetc_skb_is_ipv6() helper fucntion which is added in patch 2
v4: fix a typo
---
 drivers/net/ethernet/freescale/enetc/enetc.c  | 266 +++++++++++++++++-
 drivers/net/ethernet/freescale/enetc/enetc.h  |  15 +
 .../net/ethernet/freescale/enetc/enetc4_hw.h  |  22 ++
 .../net/ethernet/freescale/enetc/enetc_hw.h   |  15 +-
 .../freescale/enetc/enetc_pf_common.c         |   3 +
 5 files changed, 311 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 7c6b844c2e96..d05eaaf8a812 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -527,6 +527,233 @@ static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso
 	}
 }
 
+static inline 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. 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 = 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;
+
+	if (lso->tcp)
+		txbd_tmp.l4t = ENETC_TXBD_L4T_TCP;
+	else
+		txbd_tmp.l4t = ENETC_TXBD_L4T_UDP;
+
+	if (lso->ipv6)
+		txbd_tmp.l3t = 1;
+	else
+		txbd_tmp.ipcs = 1;
+
+	/* l3_hdr_size in 32-bits (4 bytes) */
+	txbd_tmp.l3_hdr_size = lso->l3_hdr_len / 4;
+	txbd_tmp.l3_start = lso->l3_start;
+
+	/* 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 = 0; /* < C-TAG */
+		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 (unlikely(dma_mapping_error(tx_ring->dev, dma))) {
+			netdev_err(tx_ring->ndev, "DMA map error\n");
+			goto dma_err;
+		}
+
+		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, 0, len,
+				       DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(tx_ring->dev, dma))) {
+			netdev_err(tx_ring->ndev, "DMA map error\n");
+			goto dma_err;
+		}
+
+		/* 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;
+
+dma_err:
+	return -ENOMEM;
+}
+
+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);
@@ -647,14 +874,26 @@ 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 > priv->max_frags))
 			if (unlikely(skb_linearize(skb)))
@@ -1800,6 +2039,9 @@ void enetc_get_si_caps(struct enetc_si *si)
 		si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(rss);
 	}
 
+	if (val & ENETC_SIPCAPR0_LSO)
+		si->hw_features |= ENETC_SI_F_LSO;
+
 	if (val & ENETC_SIPCAPR0_QBV)
 		si->hw_features |= ENETC_SI_F_QBV;
 
@@ -2104,6 +2346,13 @@ 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(TCP_NL_SEG_FLAGS_DMASK, 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;
@@ -2117,6 +2366,9 @@ 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
 	 */
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index a78af4f624e0..0a69f72fe8ec 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -41,6 +41,19 @@ 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_1KB_SIZE			1024
+#define ENETC_LSO_MAX_DATA_LEN		(256 * ENETC_1KB_SIZE)
+
 #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 */
@@ -238,6 +251,7 @@ 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 */
@@ -353,6 +367,7 @@ enum enetc_active_offloads {
 	ENETC_F_QBU			= BIT(11),
 	ENETC_F_RXCSUM			= BIT(12),
 	ENETC_F_TXCSUM			= BIT(13),
+	ENETC_F_LSO			= BIT(14),
 };
 
 enum enetc_flags_bit {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 26b220677448..cdde8e93a73c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -12,6 +12,28 @@
 #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)	((((mid) << 16) & SILSOSFMR0_TCP_MID_SEG) | \
+					 ((first) & SILSOSFMR0_TCP_1ST_SEG))
+
+#define ENETC4_SILSOSFMR1		0x1304
+#define  SILSOSFMR1_TCP_LAST_SEG	GENMASK(11, 0)
+#define   TCP_FLAGS_FIN			BIT(0)
+#define   TCP_FLAGS_SYN			BIT(1)
+#define   TCP_FLAGS_RST			BIT(2)
+#define   TCP_FLAGS_PSH			BIT(3)
+#define   TCP_FLAGS_ACK			BIT(4)
+#define   TCP_FLAGS_URG			BIT(5)
+#define   TCP_FLAGS_ECE			BIT(6)
+#define   TCP_FLAGS_CWR			BIT(7)
+#define   TCP_FLAGS_NS			BIT(8)
+/* According to tso_build_hdr(), clear all special flags for not last packet. */
+#define TCP_NL_SEG_FLAGS_DMASK		(TCP_FLAGS_FIN | TCP_FLAGS_RST | 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 590b1412fadf..34a3e8f1496e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -28,6 +28,8 @@
 #define ENETC_SIPCAPR0_QBV	BIT(4)
 #define ENETC_SIPCAPR0_QBU	BIT(3)
 #define ENETC_SIPCAPR0_RFS	BIT(2)
+#define ENETC_SIPCAPR0_LSO	BIT(1)
+#define ENETC_SIPCAPR0_RSC	BIT(0)
 #define ENETC_SIPCAPR1	0x24
 #define ENETC_SITGTGR	0x30
 #define ENETC_SIRBGCR	0x38
@@ -554,7 +556,10 @@ 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 {
@@ -574,13 +579,16 @@ 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 */
@@ -589,6 +597,7 @@ union enetc_tx_bd {
 enum enetc_txbd_flags {
 	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_CSUM_LSO = BIT(3), /* For ENETC 4.1 and later */
 	ENETC_TXBD_FLAGS_TXSTART = BIT(4),
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 2c4c6af672e7..82a67356abe4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -126,6 +126,9 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
 	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);
-- 
2.34.1

[PATCH v4 net-next 5/5] net: enetc: add UDP segmentation offload support

[Wei Fang]

Set NETIF_F_GSO_UDP_L4 bit of hw_features and features because i.MX95
enetc and LS1028A driver implements UDP segmentation.

- i.MX95 ENETC supports UDP segmentation via LSO.
- LS1028A ENETC supports UDP segmentation since the commit 3d5b459ba0e3
("net: tso: add UDP segmentation support").

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
---
v2: rephrase the commit message
v3: no changes
v4: fix typo in commit message
---
 drivers/net/ethernet/freescale/enetc/enetc_pf_common.c | 6 ++++--
 drivers/net/ethernet/freescale/enetc/enetc_vf.c        | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 82a67356abe4..76fc3c6fdec1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -110,11 +110,13 @@ 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;
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
index 052833acd220..ba71c04994c4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -138,11 +138,13 @@ 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;
 
-- 
2.34.1

Re: [PATCH v4 net-next 2/5] net: enetc: add Tx checksum offload for i.MX95 ENETC

[Jakub Kicinski]

On Fri, 15 Nov 2024 10:47:41 +0800 Wei Fang wrote:
> +static inline bool enetc_skb_is_ipv6(struct sk_buff *skb)
> +{
> +	return vlan_get_protocol(skb) == htons(ETH_P_IPV6);
> +}
> +
> +static inline bool enetc_skb_is_tcp(struct sk_buff *skb)
> +{
> +	return skb->csum_offset == offsetof(struct tcphdr, check);
> +}

Please don't use "inline" for trivial functions, compiler will inline
them anyway, and it hides unused code. In addition to being pointless.

>  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;
> @@ -160,6 +181,27 @@ 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_start = skb_network_offset(skb);
> +			temp_bd.ipcs = enetc_skb_is_ipv6(skb) ? 0 : 1;

Linux calculates the IPv4 csum, always, no need.

> +			temp_bd.l3_hdr_size = skb_network_header_len(skb) / 4;
> +			temp_bd.l3t = enetc_skb_is_ipv6(skb) ? 1 : 0;

no need for ternary op, simply :

		temp_bd.l3t = enetc_skb_is_ipv6(skb);

> +			temp_bd.l4t = enetc_skb_is_tcp(skb) ? ENETC_TXBD_L4T_TCP :
> +							      ENETC_TXBD_L4T_UDP;
> +			flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS;
> +		} else {
> +			if (skb_checksum_help(skb)) {
> +				dev_err(tx_ring->dev, "skb_checksum_help() error\n");
> +
> +				return 0;

don't print errors on the datapath, it may flood the logs
-- 
pw-bot: cr

RE: [PATCH v4 net-next 2/5] net: enetc: add Tx checksum offload for i.MX95 ENETC

[Wei Fang]

> On Fri, 15 Nov 2024 10:47:41 +0800 Wei Fang wrote:
> > +static inline bool enetc_skb_is_ipv6(struct sk_buff *skb) {
> > +	return vlan_get_protocol(skb) == htons(ETH_P_IPV6); }
> > +
> > +static inline bool enetc_skb_is_tcp(struct sk_buff *skb) {
> > +	return skb->csum_offset == offsetof(struct tcphdr, check); }
> 
> Please don't use "inline" for trivial functions, compiler will inline them anyway,
> and it hides unused code. In addition to being pointless.
> 
> >  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;
> > @@ -160,6 +181,27 @@ 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_start = skb_network_offset(skb);
> > +			temp_bd.ipcs = enetc_skb_is_ipv6(skb) ? 0 : 1;
> 
> Linux calculates the IPv4 csum, always, no need.
> 
> > +			temp_bd.l3_hdr_size = skb_network_header_len(skb) / 4;
> > +			temp_bd.l3t = enetc_skb_is_ipv6(skb) ? 1 : 0;
> 
> no need for ternary op, simply :
> 
> 		temp_bd.l3t = enetc_skb_is_ipv6(skb);
> 
> > +			temp_bd.l4t = enetc_skb_is_tcp(skb) ? ENETC_TXBD_L4T_TCP :
> > +							      ENETC_TXBD_L4T_UDP;
> > +			flags |= ENETC_TXBD_FLAGS_CSUM_LSO |
> ENETC_TXBD_FLAGS_L4CS;
> > +		} else {
> > +			if (skb_checksum_help(skb)) {
> > +				dev_err(tx_ring->dev, "skb_checksum_help() error\n");
> > +
> > +				return 0;
> 
> don't print errors on the datapath, it may flood the logs

Thanks for the comments, I will improve this patch.

> --
> pw-bot: cr