From: Daniel Zahka <daniel.zahka@gmail.com>
To: Alexander Duyck <alexanderduyck@fb.com>,
Jakub Kicinski <kuba@kernel.org>,
kernel-team@meta.com, Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@kernel.org>,
Paolo Abeni <pabeni@redhat.com>,
Dimitri Daskalakis <dimitri.daskalakis1@gmail.com>,
Mohsin Bashir <mohsin.bashr@gmail.com>
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH net-next 1/6] eth: mpnic: Tx checksum offload
Date: Fri, 06 Nov 2026 03:30:05 -0800 [thread overview]
Message-ID: <20261106-mpnic-lso-v1-1-e943ff1493e4@gmail.com> (raw)
In-Reply-To: <20261106-mpnic-lso-v1-0-e943ff1493e4@gmail.com>
Support generic Tx checksum offload per NETIF_F_HW_CSUM.
Add mpnic_features_check() to ensure that skb metadata can be mapped
into Tx descriptor fields. The headers and offsets used have units of
2B. The device also requires any headers modified to be in the first
256B of the packet.
Zero checksums are inverted by HW, matching the behavior of
skb_checksum_help().
Count CSO frames and report them via netdev qstats API.
Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
---
drivers/net/ethernet/meta/mpnic/mpnic_csr.h | 6 +++
drivers/net/ethernet/meta/mpnic/mpnic_init.c | 2 +
drivers/net/ethernet/meta/mpnic/mpnic_netdev.c | 10 ++++-
drivers/net/ethernet/meta/mpnic/mpnic_netdev.h | 1 +
drivers/net/ethernet/meta/mpnic/mpnic_txrx.c | 60 ++++++++++++++++++++++++++
drivers/net/ethernet/meta/mpnic/mpnic_txrx.h | 4 ++
6 files changed, 82 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
index d6ab9df58168..62304be203e6 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_csr.h
@@ -13,6 +13,10 @@
#define DESC_GENMASK(h, l) GENMASK_ULL(h, l)
/* Transmit Work Descriptor Format */
+#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_FLAG_REQ_CSO DESC_BIT(36)
#define MPNIC_TWD_FLAG_REQ_COMPLETION DESC_BIT(37)
#define MPNIC_TWD_FLAG_DEST_MAC DESC_BIT(43)
#define MPNIC_TWD_TYPE DESC_GENMASK(47, 46)
@@ -305,6 +309,8 @@ enum {
/* NIC_CORE_TOF */
#define MPNIC_TOF_TCAM_DEST_REMAP 0x7e3022 /* 0x1f8c088 */
+#define MPNIC_TOF_MODE 0x7e302e /* 0x1f8c0b8 */
+#define MPNIC_TOF_MODE_L4_ZERO_CSUM CSR_BIT(4)
/* 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 ace4124158fb..71d13bec7ec4 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_init.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_init.c
@@ -298,6 +298,8 @@ static void mpnic_txglb_init(struct mpnic_dev *mpd)
* programmed with its addresses.
*/
mpnic_wr64(mpd, MPNIC_TOF_TCAM_DEST_REMAP, 0);
+ mpnic_wr64(mpd, MPNIC_TOF_MODE,
+ FIELD_PREP(MPNIC_TOF_MODE_L4_ZERO_CSUM, 0));
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 7fdf57f70151..3de5abc20f9a 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.c
@@ -144,6 +144,7 @@ static const struct net_device_ops mpnic_netdev_ops = {
.ndo_stop = mpnic_stop,
.ndo_validate_addr = eth_validate_addr,
.ndo_start_xmit = mpnic_xmit_frame,
+ .ndo_features_check = mpnic_features_check,
.ndo_get_stats64 = mpnic_get_stats64,
};
@@ -200,6 +201,7 @@ static void mpnic_get_queue_stats_tx(struct net_device *dev, int idx,
u64 bytes, packets, stop, wake;
struct mpnic_q_triad *qt;
unsigned int start;
+ u64 csum_partial;
if (!txr)
return;
@@ -217,11 +219,13 @@ static void mpnic_get_queue_stats_tx(struct net_device *dev, int idx,
stats = &txr->stats;
do {
start = u64_stats_fetch_begin(&stats->syncp);
+ csum_partial = u64_stats_read(&stats->twq.csum_partial);
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->stop = stop;
tx->wake = wake;
}
@@ -237,6 +241,7 @@ 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->stop = base->tx.stop;
tx->wake = base->tx.wake;
@@ -303,7 +308,10 @@ struct net_device *mpnic_netdev_alloc(struct mpnic_dev *mpd)
mpn->num_rx_queues = queues;
mpn->num_napi = queues;
- netdev->features |= NETIF_F_SG;
+ netdev->features |=
+ NETIF_F_SG |
+ NETIF_F_HW_CSUM;
+
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 6711766ebc3c..94f7a3355c5c 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_netdev.h
@@ -16,6 +16,7 @@ struct mpnic_base_stats {
u64 packets;
u64 bytes;
u64 dropped;
+ u64 csum_partial;
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 93abdec44642..edb087b12a1e 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
@@ -8,6 +8,7 @@
#include <linux/slab.h>
#include <net/netdev_lock.h>
#include <net/page_pool/helpers.h>
+#include <net/tcp.h>
#include "mpnic.h"
#include "mpnic_netdev.h"
@@ -18,6 +19,10 @@ struct mpnic_xmit_cb {
u8 desc_count;
};
+struct mpnic_tx_hdrs {
+ unsigned int i3len;
+};
+
#define MPNIC_XMIT_CB(__skb) ((struct mpnic_xmit_cb *)((__skb)->cb))
#define MPNIC_TWD_TYPE_MASK(_type) \
cpu_to_le64(FIELD_PREP(MPNIC_TWD_TYPE, MPNIC_TWD_TYPE_##_type))
@@ -208,6 +213,34 @@ mpnic_tx_map(struct mpnic_ring *ring, struct sk_buff *skb, __le64 *meta)
return true;
}
+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);
+}
+
+static void
+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;
+
+ 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);
+
+ 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));
+}
+
#define MPNIC_MIN_FRAME_LEN 60
static netdev_tx_t mpnic_xmit_frame_ring(struct sk_buff *skb,
@@ -230,6 +263,8 @@ static netdev_tx_t mpnic_xmit_frame_ring(struct sk_buff *skb,
MPNIC_XMIT_CB(skb)->bytecount = skb->len;
MPNIC_XMIT_CB(skb)->desc_count = 0;
+ mpnic_tx_offloads(ring, skb, meta);
+
if (mpnic_tx_map(ring, skb, meta))
goto err_free;
@@ -256,6 +291,30 @@ netdev_tx_t mpnic_xmit_frame(struct sk_buff *skb, struct net_device *dev)
return mpnic_xmit_frame_ring(skb, mpn->tx[skb_get_queue_mapping(skb)]);
}
+netdev_features_t mpnic_features_check(struct sk_buff *skb,
+ struct net_device *dev,
+ netdev_features_t features)
+{
+ unsigned int l2len, i3len;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return features;
+
+ l2len = skb_mac_header_len(skb);
+ if (skb_vlan_tag_present(skb))
+ l2len += VLAN_HLEN;
+ i3len = skb_checksum_start(skb) - skb_network_header(skb);
+
+ if ((l2len | i3len | skb->csum_offset) % 2 ||
+ !FIELD_FIT(MPNIC_TWD_L2_HLEN, l2len / 2) ||
+ !FIELD_FIT(MPNIC_TWD_L3_IHLEN, i3len / 2) ||
+ !FIELD_FIT(MPNIC_TWD_CSUM_OFFSET, skb->csum_offset / 2) ||
+ l2len + i3len + sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE > 256)
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+
+ return features;
+}
+
static void mpnic_clean_twq0(struct mpnic_napi_vector *nv, int napi_budget,
struct mpnic_q_triad *qt, bool discard,
unsigned int hw_head)
@@ -721,6 +780,7 @@ static void mpnic_aggregate_ring_twq_counters(struct mpnic_base_stats *base,
struct mpnic_ring *twq)
{
base->tx.dropped += u64_stats_read(&twq->stats.twq.dropped);
+ base->tx.csum_partial += u64_stats_read(&twq->stats.twq.csum_partial);
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 52492e3f484f..a6dff9dc32d6 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
@@ -89,6 +89,7 @@ struct mpnic_queue_stats {
union {
struct {
u64_stats_t dropped;
+ u64_stats_t csum_partial;
u64_stats_t stop;
} twq;
struct {
@@ -168,6 +169,9 @@ struct mpnic_napi_vector {
};
netdev_tx_t mpnic_xmit_frame(struct sk_buff *skb, struct net_device *dev);
+netdev_features_t mpnic_features_check(struct sk_buff *skb,
+ struct net_device *dev,
+ netdev_features_t features);
int mpnic_alloc_napi_vectors(struct mpnic_net *mpn);
void mpnic_free_napi_vectors(struct mpnic_net *mpn);
void mpnic_stats_attach_rings(struct mpnic_net *mpn);
--
2.52.0
next prev parent reply other threads:[~2026-11-06 11:30 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-06 11:30 [PATCH net-next 0/6] eth: mpnic: checksum and segmentation offloads Daniel Zahka
2026-11-06 11:30 ` Daniel Zahka [this message]
2026-11-06 11:30 ` [PATCH net-next 2/6] eth: mpnic: Rx checksum offload Daniel Zahka
2026-11-06 11:30 ` [PATCH net-next 3/6] eth: mpnic: TCP segmentation offload Daniel Zahka
2026-11-06 11:30 ` [PATCH net-next 4/6] eth: mpnic: UDP " Daniel Zahka
2026-11-06 11:30 ` [PATCH net-next 5/6] eth: mpnic: IPv4 and IPv6 in IPv6 tunnel segmentation Daniel Zahka
2026-11-06 11:30 ` [PATCH net-next 6/6] eth: mpnic: add GSO_PARTIAL for other tunnels Daniel Zahka
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261106-mpnic-lso-v1-1-e943ff1493e4@gmail.com \
--to=daniel.zahka@gmail.com \
--cc=alexanderduyck@fb.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=dimitri.daskalakis1@gmail.com \
--cc=edumazet@kernel.org \
--cc=kernel-team@meta.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mohsin.bashr@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®