[PATCH RFC net-next v2] net: airoha: Add TCP LRO support
Lorenzo Bianconi
lorenzo at kernel.org
Mon May 25 23:58:05 PDT 2026
Add hardware TCP Large Receive Offload (LRO) support to the airoha_eth
driver, leveraging the EN7581/AN7583 SoC's 8 dedicated LRO hardware queues
mapped to RX queues 24–31. LRO hw offloading does not support
Scatter-Gather (SG) so it is required to increase the page_pool allocation
order to 2 for RX queues 24–31 (LRO queues).
Performance comparison between GRO and hw LRO has been carried out using
a 10Gbps NIC:
GRO: ~2.7 Gbps
LRO: ~8.1 Gbps
Please note with respect to the previous implementation, page_pool
allocation order has been reduced from 5 to 2.
Tested-by: Madhur Agrawal <madhur.agrawal at airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo at kernel.org>
---
Changes in RFC v2:
- Improve performances fixing buf_size computation.
- Fix possible overflow in REG_CDM_LRO_LIMIT() register configuration.
- Require the device to be not running before configuring LRO.
- Fix configuration order in airoha_fe_lro_is_enabled().
- Check skb header length in airoha_qdma_lro_rx_process().
- Do not check net_device feature in airoha_qdma_rx_process() before
executing airoha_qdma_lro_rx_process() but rely on
airoha_qdma_lro_rx_process() logic.
- Fix possible double recycle in airoha_qdma_rx_process() for LRO
packets.
- Always use AIROHA_RXQ_LRO_MAX_AGG_COUNT macro for max LRO aggregated
fragments in airoha_fe_lro_init_rx_queue().
- Link to v1: https://lore.kernel.org/r/20260520-airoha-eth-lro-v1-1-129cc33766e9@kernel.org
---
drivers/net/ethernet/airoha/airoha_eth.c | 217 +++++++++++++++++++++++++++---
drivers/net/ethernet/airoha/airoha_eth.h | 24 ++++
drivers/net/ethernet/airoha/airoha_regs.h | 22 ++-
3 files changed, 247 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 6418fe0c9f80..c8e5abe8942a 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -12,6 +12,7 @@
#include <net/dst_metadata.h>
#include <net/page_pool/helpers.h>
#include <net/pkt_cls.h>
+#include <net/tcp.h>
#include <uapi/linux/ppp_defs.h>
#include "airoha_regs.h"
@@ -431,6 +432,48 @@ static void airoha_fe_crsn_qsel_init(struct airoha_eth *eth)
CDM_CRSN_QSEL_Q1));
}
+static void airoha_fe_lro_init_rx_queue(struct airoha_eth *eth, int qdma_id,
+ int lro_queue_index, int qid,
+ int buf_size)
+{
+ int id = qdma_id + 1;
+
+ airoha_fe_rmw(eth, REG_CDM_LRO_LIMIT(id),
+ CDM_LRO_AGG_NUM_MASK | CDM_LRO_AGG_SIZE_MASK,
+ FIELD_PREP(CDM_LRO_AGG_SIZE_MASK, buf_size) |
+ FIELD_PREP(CDM_LRO_AGG_NUM_MASK,
+ AIROHA_RXQ_LRO_MAX_AGG_COUNT));
+ airoha_fe_rmw(eth, REG_CDM_LRO_AGE_TIME(id),
+ CDM_LRO_AGE_TIME_MASK | CDM_LRO_AGG_TIME_MASK,
+ FIELD_PREP(CDM_LRO_AGE_TIME_MASK,
+ AIROHA_RXQ_LRO_MAX_AGE_TIME) |
+ FIELD_PREP(CDM_LRO_AGG_TIME_MASK,
+ AIROHA_RXQ_LRO_MAX_AGG_TIME));
+ airoha_fe_rmw(eth, REG_CDM_LRO_RXQ(id, lro_queue_index),
+ LRO_RXQ_MASK(lro_queue_index),
+ __field_prep(LRO_RXQ_MASK(lro_queue_index), qid));
+ airoha_fe_set(eth, REG_CDM_LRO_EN(id), BIT(lro_queue_index));
+}
+
+static void airoha_fe_lro_disable(struct airoha_eth *eth, int qdma_id)
+{
+ int i, id = qdma_id + 1;
+
+ airoha_fe_clear(eth, REG_CDM_LRO_EN(id), LRO_RXQ_EN_MASK);
+ airoha_fe_clear(eth, REG_CDM_LRO_LIMIT(id),
+ CDM_LRO_AGG_NUM_MASK | CDM_LRO_AGG_SIZE_MASK);
+ airoha_fe_clear(eth, REG_CDM_LRO_AGE_TIME(id),
+ CDM_LRO_AGE_TIME_MASK | CDM_LRO_AGG_TIME_MASK);
+ for (i = 0; i < AIROHA_MAX_NUM_LRO_QUEUES; i++)
+ airoha_fe_clear(eth, REG_CDM_LRO_RXQ(id, i), LRO_RXQ_MASK(i));
+}
+
+static bool airoha_fe_lro_is_enabled(struct airoha_eth *eth, int qdma_id)
+{
+ return airoha_fe_get(eth, REG_CDM_LRO_EN(qdma_id + 1),
+ LRO_RXQ_EN_MASK);
+}
+
static int airoha_fe_init(struct airoha_eth *eth)
{
airoha_fe_maccr_init(eth);
@@ -587,6 +630,85 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
return port >= ARRAY_SIZE(eth->ports) ? -EINVAL : port;
}
+static int airoha_qdma_lro_rx_process(struct airoha_queue *q,
+ struct airoha_qdma_desc *desc)
+{
+ u32 desc_ctrl = le32_to_cpu(READ_ONCE(desc->ctrl));
+ u32 msg1 = le32_to_cpu(READ_ONCE(desc->msg1));
+ u32 msg2 = le32_to_cpu(READ_ONCE(desc->msg2));
+ u32 msg3 = le32_to_cpu(READ_ONCE(desc->msg3));
+ struct sk_buff *skb = q->skb;
+ u32 len, th_off, tcp_ack_seq;
+ u16 tcp_win, l2_len;
+ struct tcphdr *th;
+ bool ipv4, ipv6;
+
+ if (FIELD_GET(QDMA_ETH_RXMSG_AGG_COUNT_MASK, msg2) <= 1)
+ return 0;
+
+ ipv4 = FIELD_GET(QDMA_ETH_RXMSG_IP4_MASK, msg1);
+ ipv6 = FIELD_GET(QDMA_ETH_RXMSG_IP6_MASK, msg1);
+ if (!ipv4 && !ipv6)
+ return -EOPNOTSUPP;
+
+ l2_len = FIELD_GET(QDMA_ETH_RXMSG_L2_LEN_MASK, msg2);
+ len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl);
+ if (ipv4) {
+ struct iphdr *iph;
+
+ if (!pskb_may_pull(skb, l2_len + sizeof(*iph)))
+ return -EINVAL;
+
+ iph = (struct iphdr *)(skb->data + l2_len);
+ if (iph->protocol != IPPROTO_TCP)
+ return -EOPNOTSUPP;
+
+ iph->tot_len = cpu_to_be16(len - l2_len);
+ iph->check = 0;
+ iph->check = ip_fast_csum((void *)iph, iph->ihl);
+ th_off = l2_len + (iph->ihl << 2);
+ } else {
+ struct ipv6hdr *ip6h;
+
+ if (!pskb_may_pull(skb, l2_len + sizeof(*ip6h)))
+ return -EINVAL;
+
+ ip6h = (struct ipv6hdr *)(skb->data + l2_len);
+ if (ip6h->nexthdr != NEXTHDR_TCP)
+ return -EOPNOTSUPP;
+
+ ip6h->payload_len = cpu_to_be16(len - l2_len - sizeof(*ip6h));
+ th_off = l2_len + sizeof(*ip6h);
+ }
+
+ tcp_win = FIELD_GET(QDMA_ETH_RXMSG_TCP_WIN_MASK, msg3);
+ tcp_ack_seq = le32_to_cpu(READ_ONCE(desc->data));
+
+ if (!pskb_may_pull(skb, th_off + sizeof(*th)))
+ return -EINVAL;
+
+ th = (struct tcphdr *)(skb->data + th_off);
+ th->ack_seq = cpu_to_be32(tcp_ack_seq);
+ th->window = cpu_to_be16(tcp_win);
+
+ /* Check tcp timestamp option */
+ if (th->doff == (sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4) {
+ __be32 *topt = (__be32 *)(th + 1);
+
+ if (*topt == cpu_to_be32((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP)) {
+ __le32 tcp_ts_reply = READ_ONCE(desc->tcp_ts_reply);
+
+ put_unaligned_be32(le32_to_cpu(tcp_ts_reply),
+ topt + 2);
+ }
+ }
+
+ return 0;
+}
+
static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
{
enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
@@ -634,11 +756,15 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
skb_reserve(q->skb, AIROHA_RX_HEADROOM);
__skb_put(q->skb, len);
- skb_mark_for_recycle(q->skb);
q->skb->dev = port->dev;
- q->skb->protocol = eth_type_trans(q->skb, port->dev);
q->skb->ip_summed = CHECKSUM_UNNECESSARY;
skb_record_rx_queue(q->skb, qid);
+
+ if (airoha_qdma_lro_rx_process(q, desc) < 0)
+ goto free_frag;
+
+ q->skb->protocol = eth_type_trans(q->skb, port->dev);
+ skb_mark_for_recycle(q->skb);
} else { /* scattered frame */
struct skb_shared_info *shinfo = skb_shinfo(q->skb);
int nr_frags = shinfo->nr_frags;
@@ -727,23 +853,18 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
struct airoha_qdma *qdma, int ndesc)
{
- const struct page_pool_params pp_params = {
- .order = 0,
- .pool_size = 256,
+ struct page_pool_params pp_params = {
.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
.dma_dir = DMA_FROM_DEVICE,
- .max_len = PAGE_SIZE,
.nid = NUMA_NO_NODE,
.dev = qdma->eth->dev,
.napi = &q->napi,
};
+ int pp_order, qid = q - &qdma->q_rx[0], thr;
struct airoha_eth *eth = qdma->eth;
- int qid = q - &qdma->q_rx[0], thr;
dma_addr_t dma_addr;
- q->buf_size = PAGE_SIZE / 2;
q->qdma = qdma;
-
q->entry = devm_kzalloc(eth->dev, ndesc * sizeof(*q->entry),
GFP_KERNEL);
if (!q->entry)
@@ -754,6 +875,11 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
if (!q->desc)
return -ENOMEM;
+ pp_order = airoha_qdma_is_lro_queue(q) ? AIROHA_LRO_PAGE_ORDER : 0;
+ pp_params.order = pp_order;
+ pp_params.pool_size = 256;
+ pp_params.max_len = PAGE_SIZE << pp_order;
+
q->page_pool = page_pool_create(&pp_params);
if (IS_ERR(q->page_pool)) {
int err = PTR_ERR(q->page_pool);
@@ -762,6 +888,8 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
return err;
}
+ q->buf_size = airoha_qdma_is_lro_queue(q) ? pp_params.max_len
+ : pp_params.max_len / 2;
q->ndesc = ndesc;
netif_napi_add(eth->napi_dev, &q->napi, airoha_qdma_rx_napi_poll);
@@ -1993,6 +2121,67 @@ int airoha_get_fe_port(struct airoha_gdm_port *port)
}
}
+static int airoha_dev_set_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ netdev_features_t diff = dev->features ^ features;
+ struct airoha_gdm_port *port = netdev_priv(dev);
+ struct airoha_qdma *qdma = port->qdma;
+ struct airoha_eth *eth = qdma->eth;
+ int qdma_id = qdma - ð->qdma[0];
+ int i;
+
+ if (!(diff & NETIF_F_LRO))
+ return 0;
+
+ if (netif_running(dev))
+ return -EBUSY;
+
+ /* reset LRO configuration */
+ if (features & NETIF_F_LRO) {
+ int lro_queue_index = 0;
+
+ if (airoha_fe_lro_is_enabled(eth, qdma_id))
+ return 0;
+
+ for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+ struct airoha_queue *q = &qdma->q_rx[i];
+ u32 size;
+
+ if (!q->ndesc)
+ continue;
+
+ if (!airoha_qdma_is_lro_queue(q))
+ continue;
+
+ size = SKB_WITH_OVERHEAD(AIROHA_RX_LEN(q->buf_size));
+ size = min_t(u32, size, CDM_LRO_AGG_SIZE_MASK);
+ airoha_fe_lro_init_rx_queue(eth, qdma_id,
+ lro_queue_index, i, size);
+ lro_queue_index++;
+ }
+ } else {
+ for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
+ struct airoha_gdm_port *p = eth->ports[i];
+
+ if (!p)
+ continue;
+
+ if (p->qdma != qdma)
+ continue;
+
+ if (p->dev == dev)
+ continue;
+
+ if (p->dev->features & NETIF_F_LRO)
+ return 0;
+ }
+ airoha_fe_lro_disable(eth, qdma_id);
+ }
+
+ return 0;
+}
+
static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
struct net_device *dev)
{
@@ -2892,6 +3081,7 @@ static const struct net_device_ops airoha_netdev_ops = {
.ndo_stop = airoha_dev_stop,
.ndo_change_mtu = airoha_dev_change_mtu,
.ndo_select_queue = airoha_dev_select_queue,
+ .ndo_set_features = airoha_dev_set_features,
.ndo_start_xmit = airoha_dev_xmit,
.ndo_get_stats64 = airoha_dev_get_stats64,
.ndo_set_mac_address = airoha_dev_set_macaddr,
@@ -2989,12 +3179,9 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth,
dev->ethtool_ops = &airoha_ethtool_ops;
dev->max_mtu = AIROHA_MAX_MTU;
dev->watchdog_timeo = 5 * HZ;
- dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
- NETIF_F_TSO6 | NETIF_F_IPV6_CSUM |
- NETIF_F_SG | NETIF_F_TSO |
- NETIF_F_HW_TC;
- dev->features |= dev->hw_features;
- dev->vlan_features = dev->hw_features;
+ dev->hw_features = AIROHA_HW_FEATURES | NETIF_F_LRO;
+ dev->features |= AIROHA_HW_FEATURES;
+ dev->vlan_features = AIROHA_HW_FEATURES;
dev->dev.of_node = np;
SET_NETDEV_DEV(dev, eth->dev);
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index d3781103abb5..aed5077d3db5 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -43,6 +43,18 @@
(_n) == 15 ? 128 : \
(_n) == 0 ? 1024 : 16)
+#define AIROHA_LRO_PAGE_ORDER 2
+#define AIROHA_MAX_NUM_LRO_QUEUES 8
+#define AIROHA_RXQ_LRO_EN_MASK 0xff000000
+#define AIROHA_RXQ_LRO_MAX_AGG_COUNT 64
+#define AIROHA_RXQ_LRO_MAX_AGG_TIME 100
+#define AIROHA_RXQ_LRO_MAX_AGE_TIME 2000 /* 1ms */
+
+#define AIROHA_HW_FEATURES \
+ (NETIF_F_IP_CSUM | NETIF_F_RXCSUM | \
+ NETIF_F_TSO6 | NETIF_F_IPV6_CSUM | \
+ NETIF_F_SG | NETIF_F_TSO | NETIF_F_HW_TC)
+
#define PSE_RSV_PAGES 128
#define PSE_QUEUE_RSV_PAGES 64
@@ -661,6 +673,18 @@ static inline bool airoha_is_7583(struct airoha_eth *eth)
return eth->soc->version == 0x7583;
}
+static inline bool airoha_qdma_is_lro_queue(struct airoha_queue *q)
+{
+ struct airoha_qdma *qdma = q->qdma;
+ int qid = q - &qdma->q_rx[0];
+
+ /* EN7581 SoC supports at most 8 LRO rx queues */
+ BUILD_BUG_ON(hweight32(AIROHA_RXQ_LRO_EN_MASK) >
+ AIROHA_MAX_NUM_LRO_QUEUES);
+
+ return !!(AIROHA_RXQ_LRO_EN_MASK & BIT(qid));
+}
+
int airoha_get_fe_port(struct airoha_gdm_port *port);
bool airoha_is_valid_gdm_port(struct airoha_eth *eth,
struct airoha_gdm_port *port);
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 436f3c8779c1..dfc786583774 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -122,6 +122,20 @@
#define CDM_CRSN_QSEL_REASON_MASK(_n) \
GENMASK(4 + (((_n) % 4) << 3), (((_n) % 4) << 3))
+#define REG_CDM_LRO_RXQ(_n, _m) (CDM_BASE(_n) + 0x78 + ((_m) & 0x4))
+#define LRO_RXQ_MASK(_n) GENMASK(4 + (((_n) & 0x3) << 3), ((_n) & 0x3) << 3)
+
+#define REG_CDM_LRO_EN(_n) (CDM_BASE(_n) + 0x80)
+#define LRO_RXQ_EN_MASK GENMASK(7, 0)
+
+#define REG_CDM_LRO_LIMIT(_n) (CDM_BASE(_n) + 0x84)
+#define CDM_LRO_AGG_NUM_MASK GENMASK(23, 16)
+#define CDM_LRO_AGG_SIZE_MASK GENMASK(15, 0)
+
+#define REG_CDM_LRO_AGE_TIME(_n) (CDM_BASE(_n) + 0x88)
+#define CDM_LRO_AGE_TIME_MASK GENMASK(31, 16)
+#define CDM_LRO_AGG_TIME_MASK GENMASK(15, 0)
+
#define REG_GDM_FWD_CFG(_n) GDM_BASE(_n)
#define GDM_PAD_EN_MASK BIT(28)
#define GDM_DROP_CRC_ERR_MASK BIT(23)
@@ -883,9 +897,15 @@
#define QDMA_ETH_RXMSG_SPORT_MASK GENMASK(25, 21)
#define QDMA_ETH_RXMSG_CRSN_MASK GENMASK(20, 16)
#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK GENMASK(15, 0)
+/* RX MSG2 */
+#define QDMA_ETH_RXMSG_AGG_COUNT_MASK GENMASK(31, 24)
+#define QDMA_ETH_RXMSG_L2_LEN_MASK GENMASK(6, 0)
+/* RX MSG3 */
+#define QDMA_ETH_RXMSG_AGG_LEN_MASK GENMASK(31, 16)
+#define QDMA_ETH_RXMSG_TCP_WIN_MASK GENMASK(15, 0)
struct airoha_qdma_desc {
- __le32 rsv;
+ __le32 tcp_ts_reply;
__le32 ctrl;
__le32 addr;
__le32 data;
---
base-commit: 3baa7ba4ab98af452925926ffc2ee58c683e3f28
change-id: 20260520-airoha-eth-lro-a5d1c3631811
Best regards,
--
Lorenzo Bianconi <lorenzo at kernel.org>
More information about the linux-arm-kernel
mailing list