[PATCH net-next 3/6] eth: mpnic: TCP segmentation offload

From: Daniel Zahka

Date: Fri Nov 06 2026 - 06:38:12 EST


Support segmentation of non-encapsulated tcp4/tcp6 packets. When doing
segmentation the device expects the l4 checksum to be seeded with 0
length.

IPv4 header and TCP checksums that compute to zero are sent as 0 rather
than 0xffff when the HW segments packets. IPv4 IDs are incrementing
starting from the value that is in the skb's IPv4 header.

Count gso super and wire packets and report via the netdev qstats API.

Signed-off-by: Daniel Zahka <daniel.zahka@xxxxxxxxx>
---
drivers/net/ethernet/meta/mpnic/mpnic_csr.h | 27 ++++++++
drivers/net/ethernet/meta/mpnic/mpnic_init.c | 11 ++++
drivers/net/ethernet/meta/mpnic/mpnic_netdev.c | 17 ++++--
drivers/net/ethernet/meta/mpnic/mpnic_netdev.h | 2 +
drivers/net/ethernet/meta/mpnic/mpnic_txrx.c | 85 ++++++++++++++++++++++----
drivers/net/ethernet/meta/mpnic/mpnic_txrx.h | 2 +
6 files changed, 129 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
index 1c86f114ab0c..672ce0a98c22 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
@@ -16,8 +16,21 @@
#define MPNIC_TWD_L2_HLEN DESC_GENMASK(5, 0)
#define MPNIC_TWD_L3_IHLEN DESC_GENMASK(23, 16)
#define MPNIC_TWD_CSUM_OFFSET DESC_GENMASK(27, 24)
+#define MPNIC_TWD_L4_HLEN DESC_GENMASK(31, 28)
+#define MPNIC_TWD_L4_TYPE DESC_GENMASK(33, 32)
+enum {
+ MPNIC_TWD_L4_TYPE_TCP = 1,
+};
+
+#define MPNIC_TWD_FLAG_REQ_LSO DESC_BIT(35)
#define MPNIC_TWD_FLAG_REQ_CSO DESC_BIT(36)
#define MPNIC_TWD_FLAG_REQ_COMPLETION DESC_BIT(37)
+#define MPNIC_TWD_L3_TYPE DESC_GENMASK(42, 40)
+enum {
+ MPNIC_TWD_L3_TYPE_IPV4 = 1,
+ MPNIC_TWD_L3_TYPE_IPV6 = 2,
+};
+
#define MPNIC_TWD_FLAG_DEST_MAC DESC_BIT(43)
#define MPNIC_TWD_TYPE DESC_GENMASK(47, 46)
enum {
@@ -26,6 +39,8 @@ enum {
MPNIC_TWD_TYPE_LAST_AL = 3,
};

+#define MPNIC_TWD_MSS DESC_GENMASK(61, 48)
+
#define MPNIC_TWD_ADDR DESC_GENMASK(45, 0)
#define MPNIC_TWD_LEN DESC_GENMASK(63, 48)

@@ -312,7 +327,19 @@ enum {
/* NIC_CORE_TOF */
#define MPNIC_TOF_TCAM_DEST_REMAP 0x7e3022 /* 0x1f8c088 */
#define MPNIC_TOF_MODE 0x7e302e /* 0x1f8c0b8 */
+#define MPNIC_TOF_MODE_IPV4_ID_MODE CSR_GENMASK(0, 0)
+enum {
+ MPNIC_IPV4_ID_MODE_FIXED = 0,
+ MPNIC_IPV4_ID_MODE_INCREMENT = 1,
+};
+
+#define MPNIC_TOF_MODE_IPV4_ZERO_CSUM CSR_BIT(1)
+#define MPNIC_TOF_MODE_TCP_ZERO_CSUM CSR_BIT(2)
#define MPNIC_TOF_MODE_L4_ZERO_CSUM CSR_BIT(4)
+#define MPNIC_TOF_TCP_FLAG_CLR 0x7e3030 /* 0x1f8c0c0 */
+#define MPNIC_TOF_TCP_FLAG_CLR_FIRST_SEGMENT CSR_GENMASK(8, 0)
+#define MPNIC_TOF_TCP_FLAG_CLR_MIDDLE_SEGMENT CSR_GENMASK(24, 16)
+#define MPNIC_TOF_TCP_FLAG_CLR_LAST_SEGMENT CSR_GENMASK(40, 32)

/* PEMO_WRAPPER */
#define MPNIC_OB_ATTR_RO CSR_BIT(1)
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_init.c b/drivers/net/ethernet/meta/mpnic/mpnic_init.c
index 71d13bec7ec4..b9a41656f8f7 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_init.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_init.c
@@ -8,6 +8,7 @@
#include <linux/iopoll.h>
#include <linux/log2.h>
#include <linux/sizes.h>
+#include <net/tcp.h>

#include "mpnic.h"
#include "mpnic_txrx.h"
@@ -299,7 +300,17 @@ static void mpnic_txglb_init(struct mpnic_dev *mpd)
*/
mpnic_wr64(mpd, MPNIC_TOF_TCAM_DEST_REMAP, 0);
mpnic_wr64(mpd, MPNIC_TOF_MODE,
+ FIELD_PREP(MPNIC_TOF_MODE_IPV4_ID_MODE,
+ MPNIC_IPV4_ID_MODE_INCREMENT) |
+ FIELD_PREP(MPNIC_TOF_MODE_IPV4_ZERO_CSUM, 1) |
+ FIELD_PREP(MPNIC_TOF_MODE_TCP_ZERO_CSUM, 1) |
FIELD_PREP(MPNIC_TOF_MODE_L4_ZERO_CSUM, 0));
+ mpnic_wr64(mpd, MPNIC_TOF_TCP_FLAG_CLR,
+ FIELD_PREP(MPNIC_TOF_TCP_FLAG_CLR_FIRST_SEGMENT,
+ TCPHDR_PSH | TCPHDR_FIN) |
+ FIELD_PREP(MPNIC_TOF_TCP_FLAG_CLR_MIDDLE_SEGMENT,
+ TCPHDR_PSH | TCPHDR_CWR | TCPHDR_FIN) |
+ FIELD_PREP(MPNIC_TOF_TCP_FLAG_CLR_LAST_SEGMENT, TCPHDR_CWR));

mpnic_wr64(mpd, MPNIC_TCM_MEM_INIT_REQ, MPNIC_MEM_INIT_TCM_VAL);
mpnic_wr64(mpd, MPNIC_TDE_MEM_INIT_REQ, MPNIC_MEM_INIT_TDE_VAL);
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
index 91b70fe8483c..3a4aa5be57a1 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
@@ -205,11 +205,11 @@ static void mpnic_get_queue_stats_tx(struct net_device *dev, int idx,
{
struct mpnic_net *mpn = netdev_priv(dev);
struct mpnic_ring *txr = mpn->tx[idx];
+ u64 csum_partial, hw_gso, hw_gso_wire;
struct mpnic_queue_stats *stats;
u64 bytes, packets, stop, wake;
struct mpnic_q_triad *qt;
unsigned int start;
- u64 csum_partial;

if (!txr)
return;
@@ -228,12 +228,16 @@ static void mpnic_get_queue_stats_tx(struct net_device *dev, int idx,
do {
start = u64_stats_fetch_begin(&stats->syncp);
csum_partial = u64_stats_read(&stats->twq.csum_partial);
+ hw_gso = u64_stats_read(&stats->twq.hw_gso);
+ hw_gso_wire = u64_stats_read(&stats->twq.hw_gso_wire);
stop = u64_stats_read(&stats->twq.stop);
} while (u64_stats_fetch_retry(&stats->syncp, start));

tx->bytes = bytes;
tx->packets = packets;
- tx->needs_csum = csum_partial;
+ tx->needs_csum = csum_partial + hw_gso_wire;
+ tx->hw_gso_packets = hw_gso;
+ tx->hw_gso_wire_packets = hw_gso_wire;
tx->stop = stop;
tx->wake = wake;
}
@@ -249,7 +253,9 @@ static void mpnic_get_base_stats(struct net_device *dev,

tx->bytes = base->tx.bytes;
tx->packets = base->tx.packets;
- tx->needs_csum = base->tx.csum_partial;
+ tx->needs_csum = base->tx.csum_partial + base->tx.hw_gso_wire;
+ tx->hw_gso_packets = base->tx.hw_gso;
+ tx->hw_gso_wire_packets = base->tx.hw_gso_wire;
tx->stop = base->tx.stop;
tx->wake = base->tx.wake;

@@ -322,7 +328,10 @@ struct net_device *mpnic_netdev_alloc(struct mpnic_dev *mpd)
netdev->features |=
NETIF_F_SG |
NETIF_F_HW_CSUM |
- NETIF_F_RXCSUM;
+ NETIF_F_RXCSUM |
+ NETIF_F_TSO |
+ NETIF_F_TSO_ECN |
+ NETIF_F_TSO6;

netdev->hw_features |= netdev->features;
netdev->vlan_features |= netdev->features;
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
index 76ec9811e79e..567a52d0b33d 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
@@ -17,6 +17,8 @@ struct mpnic_base_stats {
u64 bytes;
u64 dropped;
u64 csum_partial;
+ u64 hw_gso;
+ u64 hw_gso_wire;
u64 stop;
u64 wake;
} tx;
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
index 680625810ec0..e2e6ab6d3c59 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
@@ -16,11 +16,14 @@

struct mpnic_xmit_cb {
u32 bytecount;
+ u16 gso_segs;
u8 desc_count;
};

struct mpnic_tx_hdrs {
unsigned int i3len;
+ unsigned int l3_type;
+ unsigned int l4_type;
};

#define MPNIC_XMIT_CB(__skb) ((struct mpnic_xmit_cb *)((__skb)->cb))
@@ -215,30 +218,82 @@ mpnic_tx_map(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta)

static void mpnic_tx_fill_hdrs(struct sk_buff *skb, struct mpnic_tx_hdrs *hdrs)
{
- hdrs->i3len = skb_checksum_start(skb) - skb_network_header(skb);
+ if (!skb_is_gso(skb)) {
+ hdrs->i3len = skb_checksum_start(skb) - skb_network_header(skb);
+ return;
+ }
+
+ hdrs->l4_type = MPNIC_TWD_L4_TYPE_TCP;
+ hdrs->i3len = skb_transport_offset(skb) - skb_network_offset(skb);
+ hdrs->l3_type = ip_hdr(skb)->version == 4 ?
+ MPNIC_TWD_L3_TYPE_IPV4 : MPNIC_TWD_L3_TYPE_IPV6;
}

-static void
+static bool
+mpnic_tx_lso(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta)
+{
+ struct skb_shared_info *shinfo;
+ unsigned int l4len, hdrlen;
+ struct tcphdr *tcph;
+ __be16 payload_len;
+
+ if (skb_cow_head(skb, 0))
+ return true;
+
+ shinfo = skb_shinfo(skb);
+
+ tcph = (struct tcphdr *)skb_checksum_start(skb);
+ l4len = __tcp_hdrlen(tcph);
+ payload_len = cpu_to_be16(skb->len - skb_checksum_start_offset(skb));
+ csum_replace_by_diff(&tcph->check, (__force __wsum)payload_len);
+
+ *meta |= cpu_to_le64(FIELD_PREP(MPNIC_TWD_L4_HLEN, l4len / 4) |
+ FIELD_PREP(MPNIC_TWD_MSS, shinfo->gso_size) |
+ MPNIC_TWD_FLAG_REQ_LSO);
+
+ hdrlen = skb_checksum_start_offset(skb) + l4len;
+ MPNIC_XMIT_CB(skb)->bytecount += (shinfo->gso_segs - 1) * hdrlen;
+ MPNIC_XMIT_CB(skb)->gso_segs = shinfo->gso_segs;
+
+ u64_stats_update_begin(&ring->stats.syncp);
+ u64_stats_inc(&ring->stats.twq.hw_gso);
+ u64_stats_add(&ring->stats.twq.hw_gso_wire, shinfo->gso_segs);
+ u64_stats_update_end(&ring->stats.syncp);
+
+ return false;
+}
+
+static bool
mpnic_tx_offloads(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta)
{
struct mpnic_tx_hdrs hdrs = {};

if (skb->ip_summed != CHECKSUM_PARTIAL)
- return;
+ return false;

mpnic_tx_fill_hdrs(skb, &hdrs);

*meta |= cpu_to_le64(FIELD_PREP(MPNIC_TWD_CSUM_OFFSET,
- skb->csum_offset / 2) |
- MPNIC_TWD_FLAG_REQ_CSO);
+ skb->csum_offset / 2));

- u64_stats_update_begin(&ring->stats.syncp);
- u64_stats_inc(&ring->stats.twq.csum_partial);
- u64_stats_update_end(&ring->stats.syncp);
+ if (skb_is_gso(skb)) {
+ if (mpnic_tx_lso(ring, skb, meta))
+ return true;
+ } else {
+ *meta |= cpu_to_le64(MPNIC_TWD_FLAG_REQ_CSO);
+
+ u64_stats_update_begin(&ring->stats.syncp);
+ u64_stats_inc(&ring->stats.twq.csum_partial);
+ u64_stats_update_end(&ring->stats.syncp);
+ }

*meta |= cpu_to_le64(FIELD_PREP(MPNIC_TWD_L2_HLEN,
skb_mac_header_len(skb) / 2) |
- FIELD_PREP(MPNIC_TWD_L3_IHLEN, hdrs.i3len / 2));
+ FIELD_PREP(MPNIC_TWD_L3_IHLEN, hdrs.i3len / 2) |
+ FIELD_PREP(MPNIC_TWD_L3_TYPE, hdrs.l3_type) |
+ FIELD_PREP(MPNIC_TWD_L4_TYPE, hdrs.l4_type));
+
+ return false;
}

#define MPNIC_MIN_FRAME_LEN 60
@@ -261,9 +316,11 @@ static netdev_tx_t mpnic_xmit_frame_ring(struct sk_buff *skb,
*meta = cpu_to_le64(MPNIC_TWD_FLAG_DEST_MAC);

MPNIC_XMIT_CB(skb)->bytecount = skb->len;
+ MPNIC_XMIT_CB(skb)->gso_segs = 1;
MPNIC_XMIT_CB(skb)->desc_count = 0;

- mpnic_tx_offloads(ring, skb, meta);
+ if (mpnic_tx_offloads(ring, skb, meta))
+ goto err_free;

if (mpnic_tx_map(ring, skb, meta))
goto err_free;
@@ -312,6 +369,10 @@ netdev_features_t mpnic_features_check(struct sk_buff *skb,
l2len + i3len + sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE > 256)
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);

+ if (skb_is_gso(skb) &&
+ !FIELD_FIT(MPNIC_TWD_MSS, skb_shinfo(skb)->gso_size))
+ return features & ~NETIF_F_GSO_MASK;
+
return features;
}

@@ -357,7 +418,7 @@ static void mpnic_clean_twq0(struct mpnic_napi_vector *nv, int napi_budget,
}

total_bytes += MPNIC_XMIT_CB(skb)->bytecount;
- total_packets++;
+ total_packets += MPNIC_XMIT_CB(skb)->gso_segs;

napi_consume_skb(skb, napi_budget);
}
@@ -811,6 +872,8 @@ static void mpnic_aggregate_ring_twq_counters(struct mpnic_base_stats *base,
{
base->tx.dropped += u64_stats_read(&twq->stats.twq.dropped);
base->tx.csum_partial += u64_stats_read(&twq->stats.twq.csum_partial);
+ base->tx.hw_gso += u64_stats_read(&twq->stats.twq.hw_gso);
+ base->tx.hw_gso_wire += u64_stats_read(&twq->stats.twq.hw_gso_wire);
base->tx.stop += u64_stats_read(&twq->stats.twq.stop);
}

diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
index 714f09f4160e..70f321ac4368 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
@@ -90,6 +90,8 @@ struct mpnic_queue_stats {
struct {
u64_stats_t dropped;
u64_stats_t csum_partial;
+ u64_stats_t hw_gso;
+ u64_stats_t hw_gso_wire;
u64_stats_t stop;
} twq;
struct {

--
2.52.0