Index: sys/arch/octeon/dev/if_cnmac.c =================================================================== RCS file: /mount/openbsd/cvs/src/sys/arch/octeon/dev/if_cnmac.c,v diff -u -p -u -p -r1.86 if_cnmac.c --- sys/arch/octeon/dev/if_cnmac.c 20 May 2024 23:13:33 -0000 1.86 +++ sys/arch/octeon/dev/if_cnmac.c 21 Mar 2025 12:17:46 -0000 @@ -55,6 +55,9 @@ #include #include #include +#include +#include +#include #if NBPFILTER > 0 #include @@ -306,7 +309,7 @@ cnmac_attach(struct device *parent, stru strncpy(ifp->if_xname, sc->sc_dev.dv_xname, sizeof(ifp->if_xname)); ifp->if_softc = sc; ifp->if_flags = IFF_BROADCAST | IFF_SIMPLEX | IFF_MULTICAST; - ifp->if_xflags = IFXF_MPSAFE; + ifp->if_xflags = IFXF_MPSAFE | IFXF_LRO; ifp->if_ioctl = cnmac_ioctl; ifp->if_qstart = cnmac_start; ifp->if_watchdog = cnmac_watchdog; @@ -314,7 +317,7 @@ cnmac_attach(struct device *parent, stru ifq_init_maxlen(&ifp->if_snd, max(GATHER_QUEUE_SIZE, IFQ_MAXLEN)); ifp->if_capabilities = IFCAP_VLAN_MTU | IFCAP_CSUM_TCPv4 | - IFCAP_CSUM_UDPv4 | IFCAP_CSUM_TCPv6 | IFCAP_CSUM_UDPv6; + IFCAP_CSUM_UDPv4 | IFCAP_CSUM_TCPv6 | IFCAP_CSUM_UDPv6 | IFCAP_LRO; cn30xxgmx_set_filter(sc->sc_gmx_port); @@ -1246,7 +1249,7 @@ cnmac_recv(struct cnmac_softc *sc, uint6 M_TCP_CSUM_IN_OK | M_UDP_CSUM_IN_OK; } - ml_enqueue(ml, m); + tcp_softlro_enqueue(ifp, ml, m); return nmbuf; Index: sys/dev/pci/if_bnxt.c =================================================================== RCS file: /mount/openbsd/cvs/src/sys/dev/pci/if_bnxt.c,v diff -u -p -u -p -r1.52 if_bnxt.c --- sys/dev/pci/if_bnxt.c 6 Oct 2024 23:43:18 -0000 1.52 +++ sys/dev/pci/if_bnxt.c 21 Mar 2025 12:17:46 -0000 @@ -646,6 +646,8 @@ bnxt_attach(struct device *parent, struc IFCAP_CSUM_UDPv4 | IFCAP_CSUM_TCPv4 | IFCAP_CSUM_UDPv6 | IFCAP_CSUM_TCPv6; ifp->if_capabilities |= IFCAP_TSOv4 | IFCAP_TSOv6; + ifp->if_xflags |= IFXF_LRO; + ifp->if_capabilities |= IFCAP_LRO; #if NVLAN > 0 ifp->if_capabilities |= IFCAP_VLAN_HWTAGGING; #endif @@ -2283,6 +2285,7 @@ bnxt_rx(struct bnxt_softc *sc, struct bn struct bnxt_cp_ring *cpr, struct mbuf_list *ml, int *slots, int *agslots, struct cmpl_base *cmpl) { + struct ifnet *ifp = &sc->sc_ac.ac_if; struct mbuf *m, *am; struct bnxt_slot *bs; struct rx_pkt_cmpl *rxlo = (struct rx_pkt_cmpl *)cmpl; @@ -2355,7 +2358,7 @@ bnxt_rx(struct bnxt_softc *sc, struct bn (*agslots)++; } - ml_enqueue(ml, m); + tcp_softlro_enqueue(ifp, ml, m); return (0); } Index: sys/dev/pci/if_em.c =================================================================== RCS file: /mount/openbsd/cvs/src/sys/dev/pci/if_em.c,v diff -u -p -u -p -r1.378 if_em.c --- sys/dev/pci/if_em.c 31 Aug 2024 16:23:09 -0000 1.378 +++ sys/dev/pci/if_em.c 21 Mar 2025 12:17:46 -0000 @@ -2013,6 +2013,9 @@ em_setup_interface(struct em_softc *sc) ifp->if_capabilities |= IFCAP_TSOv4 | IFCAP_TSOv6; } + ifp->if_xflags |= IFXF_LRO; + ifp->if_capabilities |= IFCAP_LRO; + /* * Specify the media types supported by this adapter and register * callbacks to update media and link information @@ -3185,7 +3188,8 @@ em_rxeof(struct em_queue *que) m->m_flags |= M_VLANTAG; } #endif - ml_enqueue(&ml, m); + + tcp_softlro_enqueue(ifp, &ml, m); que->rx.fmp = NULL; que->rx.lmp = NULL; Index: sys/dev/pci/if_ixl.c =================================================================== RCS file: /mount/openbsd/cvs/src/sys/dev/pci/if_ixl.c,v diff -u -p -u -p -r1.102 if_ixl.c --- sys/dev/pci/if_ixl.c 30 Oct 2024 18:02:45 -0000 1.102 +++ sys/dev/pci/if_ixl.c 21 Mar 2025 12:17:46 -0000 @@ -883,6 +883,8 @@ struct ixl_rx_wb_desc_16 { #define IXL_RX_DESC_PTYPE_SHIFT 30 #define IXL_RX_DESC_PTYPE_MASK (0xffULL << IXL_RX_DESC_PTYPE_SHIFT) +#define IXL_RX_DESC_PTYPE_MAC_IPV4_TCP 26 +#define IXL_RX_DESC_PTYPE_MAC_IPV6_TCP 92 #define IXL_RX_DESC_PLEN_SHIFT 38 #define IXL_RX_DESC_PLEN_MASK (0x3fffULL << IXL_RX_DESC_PLEN_SHIFT) @@ -1976,6 +1978,9 @@ ixl_attach(struct device *parent, struct IFCAP_CSUM_TCPv6 | IFCAP_CSUM_UDPv6; ifp->if_capabilities |= IFCAP_TSOv4 | IFCAP_TSOv6; + ifp->if_xflags |= IFXF_LRO; + ifp->if_capabilities |= IFCAP_LRO; + ifmedia_init(&sc->sc_media, 0, ixl_media_change, ixl_media_status); ixl_media_add(sc, phy_types); @@ -3255,9 +3260,11 @@ ixl_rxeof(struct ixl_softc *sc, struct i struct ixl_rx_map *rxm; bus_dmamap_t map; unsigned int cons, prod; - struct mbuf_list ml = MBUF_LIST_INITIALIZER(); + struct mbuf_list mlt = MBUF_LIST_INITIALIZER(); + struct mbuf_list mlo = MBUF_LIST_INITIALIZER(); struct mbuf *m; uint64_t word; + unsigned int ptype; unsigned int len; unsigned int mask; int done = 0; @@ -3294,6 +3301,8 @@ ixl_rxeof(struct ixl_softc *sc, struct i m = rxm->rxm_m; rxm->rxm_m = NULL; + ptype = (word & IXL_RX_DESC_PTYPE_MASK) + >> IXL_RX_DESC_PTYPE_SHIFT; len = (word & IXL_RX_DESC_PLEN_MASK) >> IXL_RX_DESC_PLEN_SHIFT; m->m_len = len; m->m_pkthdr.len = 0; @@ -3324,7 +3333,12 @@ ixl_rxeof(struct ixl_softc *sc, struct i #endif ixl_rx_checksum(m, word); - ml_enqueue(&ml, m); + + if (ptype == IXL_RX_DESC_PTYPE_MAC_IPV4_TCP || + ptype == IXL_RX_DESC_PTYPE_MAC_IPV6_TCP) + tcp_softlro_enqueue(ifp, &mlt, m); + else + ml_enqueue(&mlo, m); } else { ifp->if_ierrors++; /* XXX */ m_freem(m); @@ -3342,7 +3356,7 @@ ixl_rxeof(struct ixl_softc *sc, struct i if (done) { rxr->rxr_cons = cons; - if (ifiq_input(ifiq, &ml)) + if (ifiq_input(ifiq, &mlt) || ifiq_input(ifiq, &mlo)) if_rxr_livelocked(&rxr->rxr_acct); ixl_rxfill(sc, rxr); } Index: sys/net/if.c =================================================================== RCS file: /mount/openbsd/cvs/src/sys/net/if.c,v diff -u -p -u -p -r1.729 if.c --- sys/net/if.c 19 Mar 2025 23:29:49 -0000 1.729 +++ sys/net/if.c 21 Mar 2025 12:17:46 -0000 @@ -3388,6 +3388,7 @@ ifsetlro(struct ifnet *ifp, int on) } else if (!on && ISSET(ifp->if_xflags, IFXF_LRO)) CLR(ifp->if_xflags, IFXF_LRO); + error = 0; out: splx(s); Index: sys/netinet/tcp_input.c =================================================================== RCS file: /mount/openbsd/cvs/src/sys/netinet/tcp_input.c,v diff -u -p -u -p -r1.434 tcp_input.c --- sys/netinet/tcp_input.c 10 Mar 2025 15:11:46 -0000 1.434 +++ sys/netinet/tcp_input.c 21 Mar 2025 12:17:46 -0000 @@ -84,6 +84,7 @@ #include #include +#include #include #include #include @@ -4229,4 +4230,233 @@ syn_cache_respond(struct syn_cache *sc, } in_pcbunref(inp); return (error); +} + +int +tcp_softlro(struct mbuf *mhead, struct mbuf *mtail) +{ + struct ether_extracted head; + struct ether_extracted tail; + struct mbuf *m; + unsigned int hdrlen; + + /* + * Check if head and tail are mergeable + */ + + ether_extract_headers(mhead, &head); + ether_extract_headers(mtail, &tail); + + /* Don't merge packets of different VLANs */ + if (head.evh && tail.evh) { + if (head.evh->evl_tag != tail.evh->evl_tag) + return 0; + } else if (head.evh || tail.evh) + return 0; + + /* Check IP header. */ + if (head.ip4 && tail.ip4) { + /* Don't merge packets with invalid header checksum. */ + if (!ISSET(mhead->m_pkthdr.csum_flags, M_IPV4_CSUM_IN_OK) || + !ISSET(mtail->m_pkthdr.csum_flags, M_IPV4_CSUM_IN_OK)) + return 0; + + /* Check IPv4 addresses. */ + if (head.ip4->ip_src.s_addr != tail.ip4->ip_src.s_addr || + head.ip4->ip_dst.s_addr != tail.ip4->ip_dst.s_addr) + return 0; + + /* Don't merge IPv4 fragments. */ + if (ISSET(head.ip4->ip_off, htons(IP_OFFMASK | IP_MF)) || + ISSET(tail.ip4->ip_off, htons(IP_OFFMASK | IP_MF))) + return 0; + + /* Check max. IPv4 length. */ + if (head.iplen + tail.iplen > IP_MAXPACKET) + return 0; + + /* Don't merge IPv4 packets with option headers. */ + if (head.iphlen != sizeof(struct ip) || + tail.iphlen != sizeof(struct ip)) + return 0; + + /* Don't non-TCP packets. */ + if (head.ip4->ip_p != IPPROTO_TCP || + tail.ip4->ip_p != IPPROTO_TCP) + return 0; + } else if (head.ip6 && tail.ip6) { + /* Check IPv6 addresses. */ + if (!IN6_ARE_ADDR_EQUAL(&head.ip6->ip6_src, &tail.ip6->ip6_src) || + !IN6_ARE_ADDR_EQUAL(&head.ip6->ip6_dst, &tail.ip6->ip6_dst)) + return 0; + + /* Check max. IPv6 length. */ + if ((head.iplen - head.iphlen) + + (tail.iplen - tail.iphlen) > IPV6_MAXPACKET) + return 0; + + /* Don't merge IPv6 packets with option headers nor non-TCP. */ + if (head.ip6->ip6_nxt != IPPROTO_TCP || + tail.ip6->ip6_nxt != IPPROTO_TCP) + return 0; + } else { + return 0; + } + + /* Check TCP header. */ + if (!head.tcp || !tail.tcp) + return 0; + + /* Check TCP ports. */ + if (head.tcp->th_sport != tail.tcp->th_sport || + head.tcp->th_dport != tail.tcp->th_dport) + return 0; + + /* Don't merge empty segments. */ + if (head.paylen == 0 || tail.paylen == 0) + return 0; + + /* Check for continues segments. */ + if (ntohl(head.tcp->th_seq) + head.paylen != ntohl(tail.tcp->th_seq)) + return 0; + + /* Just ACK and PUSH TCP flags are allowed. */ + if (ISSET(head.tcp->th_flags, ~(TH_ACK|TH_PUSH)) || + ISSET(tail.tcp->th_flags, ~(TH_ACK|TH_PUSH))) + return 0; + + /* TCP ACK flag has to be set. */ + if (!ISSET(head.tcp->th_flags, TH_ACK) || + !ISSET(tail.tcp->th_flags, TH_ACK)) + return 0; + + /* Ignore segments with different TCP options. */ + if (head.tcphlen - sizeof(struct tcphdr) != + tail.tcphlen - sizeof(struct tcphdr)) + return 0; + + /* Check for TCP options */ + if (head.tcphlen > sizeof(struct tcphdr)) { + char *hopt = (char *)(head.tcp) + sizeof(struct tcphdr); + char *topt = (char *)(tail.tcp) + sizeof(struct tcphdr); + int optsize = head.tcphlen - sizeof(struct tcphdr); + int optlen; + + for (; optsize > 0; optsize -= optlen) { + /* Ignore segments with different TCP options. */ + if (hopt[0] != topt[0] || hopt[1] != topt[1]) + return 0; + + /* Get option length */ + optlen = hopt[1]; + if (hopt[0] == TCPOPT_NOP) + optlen = 1; + else if (optlen < 2 || optlen > optsize) + return 0; /* Illegal length */ + + if (hopt[0] != TCPOPT_NOP && + hopt[0] != TCPOPT_TIMESTAMP) + return 0; /* Unsupported TCP option */ + + hopt += optlen; + topt += optlen; + } + } + + /* + * Prepare concatenation of head and tail. + */ + + /* Adjust IP header. */ + if (head.ip4) { + head.ip4->ip_len = htons(head.iplen + tail.paylen); + } else if (head.ip6) { + head.ip6->ip6_plen = + htons(head.iplen - head.iphlen + tail.paylen); + } + + /* Combine TCP flags from head and tail. */ + if (ISSET(tail.tcp->th_flags, TH_PUSH)) + SET(head.tcp->th_flags, TH_PUSH); + + /* Adjust TCP header. */ + head.tcp->th_win = tail.tcp->th_win; + head.tcp->th_ack = tail.tcp->th_ack; + + /* Calculate header length of tail packet. */ + hdrlen = sizeof(*tail.eh); + if (tail.evh) + hdrlen = sizeof(*tail.evh); + hdrlen += tail.iphlen; + hdrlen += tail.tcphlen; + + /* Skip protocol headers in tail. */ + m_adj(mtail, hdrlen); + CLR(mtail->m_flags, M_PKTHDR); + + /* Concatenate */ + for (m = mhead; m->m_next;) + m = m->m_next; + m->m_next = mtail; + mhead->m_pkthdr.len += tail.paylen; + + /* Flag mbuf as TSO packet with MSS. */ + if (!ISSET(mhead->m_pkthdr.csum_flags, M_TCP_TSO)) { + /* Set CSUM_OUT flags in case of forwarding. */ + SET(mhead->m_pkthdr.csum_flags, M_TCP_CSUM_OUT); + head.tcp->th_sum = 0; + if (head.ip4) { + SET(mhead->m_pkthdr.csum_flags, M_IPV4_CSUM_OUT); + head.ip4->ip_sum = 0; + } + + SET(mhead->m_pkthdr.csum_flags, M_TCP_TSO); + mhead->m_pkthdr.ph_mss = head.paylen; + tcpstat_inc(tcps_inhwlro); + tcpstat_inc(tcps_inpktlro); /* count head */ + } + mhead->m_pkthdr.ph_mss = MAX(mhead->m_pkthdr.ph_mss, tail.paylen); + tcpstat_inc(tcps_inpktlro); /* count tail */ + + return 1; +} + +void +tcp_softlro_enqueue(struct ifnet *ifp, struct mbuf_list *ml, struct mbuf *mtail) +{ + struct mbuf *mhead; + + if (!ISSET(ifp->if_xflags, IFXF_LRO)) + goto out; + + /* Don't merge packets with invalid header checksum. */ + if (!ISSET(mtail->m_pkthdr.csum_flags, M_TCP_CSUM_IN_OK)) + goto out; + + for (mhead = ml->ml_head; mhead != NULL; mhead = mhead->m_nextpkt) { + /* Don't merge packets with invalid header checksum. */ + if (!ISSET(mhead->m_pkthdr.csum_flags, M_TCP_CSUM_IN_OK)) + continue; + + /* Use RSS hash to skip packets of different connections. */ + if (ISSET(mhead->m_pkthdr.csum_flags, M_FLOWID) && + ISSET(mtail->m_pkthdr.csum_flags, M_FLOWID) && + mhead->m_pkthdr.ph_flowid != mtail->m_pkthdr.ph_flowid) + continue; + + /* Don't merge packets of different VLANs */ + if (ISSET(mhead->m_flags, M_VLANTAG) != + ISSET(mtail->m_flags, M_VLANTAG)) + continue; + + if (ISSET(mhead->m_flags, M_VLANTAG) && + EVL_VLANOFTAG(mhead->m_pkthdr.ether_vtag) != + EVL_VLANOFTAG(mtail->m_pkthdr.ether_vtag)) + continue; + + if (tcp_softlro(mhead, mtail)) + return; + } + out: + ml_enqueue(ml, mtail); } Index: sys/netinet/tcp_var.h =================================================================== RCS file: /mount/openbsd/cvs/src/sys/netinet/tcp_var.h,v diff -u -p -u -p -r1.186 tcp_var.h --- sys/netinet/tcp_var.h 2 Mar 2025 21:28:32 -0000 1.186 +++ sys/netinet/tcp_var.h 21 Mar 2025 12:17:46 -0000 @@ -720,6 +720,7 @@ void tcp_init(void); int tcp_input(struct mbuf **, int *, int, int, struct netstack *); int tcp_mss(struct tcpcb *, int); void tcp_mss_update(struct tcpcb *); +void tcp_softlro_enqueue(struct ifnet *, struct mbuf_list *, struct mbuf *); u_int tcp_hdrsz(struct tcpcb *); void tcp_mtudisc(struct inpcb *, int); void tcp_mtudisc_increase(struct inpcb *, int);