From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- drivers/infiniband/sw/rxe/rxe_net.c | 686 ++++++++++++++++++++++++++++++++++++ 1 file changed, 686 insertions(+) create mode 100644 drivers/infiniband/sw/rxe/rxe_net.c (limited to 'drivers/infiniband/sw/rxe/rxe_net.c') diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c new file mode 100644 index 000000000..e02e1624b --- /dev/null +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -0,0 +1,686 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* + * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. + * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rxe.h" +#include "rxe_net.h" +#include "rxe_loc.h" + +static struct rxe_recv_sockets recv_sockets; + +static struct dst_entry *rxe_find_route4(struct rxe_qp *qp, + struct net_device *ndev, + struct in_addr *saddr, + struct in_addr *daddr) +{ + struct rtable *rt; + struct flowi4 fl = { { 0 } }; + + memset(&fl, 0, sizeof(fl)); + fl.flowi4_oif = ndev->ifindex; + memcpy(&fl.saddr, saddr, sizeof(*saddr)); + memcpy(&fl.daddr, daddr, sizeof(*daddr)); + fl.flowi4_proto = IPPROTO_UDP; + + rt = ip_route_output_key(&init_net, &fl); + if (IS_ERR(rt)) { + rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr); + return NULL; + } + + return &rt->dst; +} + +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, + struct net_device *ndev, + struct in6_addr *saddr, + struct in6_addr *daddr) +{ + struct dst_entry *ndst; + struct flowi6 fl6 = { { 0 } }; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = ndev->ifindex; + memcpy(&fl6.saddr, saddr, sizeof(*saddr)); + memcpy(&fl6.daddr, daddr, sizeof(*daddr)); + fl6.flowi6_proto = IPPROTO_UDP; + + ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), + recv_sockets.sk6->sk, &fl6, + NULL); + if (IS_ERR(ndst)) { + rxe_dbg_qp(qp, "no route to %pI6\n", daddr); + return NULL; + } + + if (unlikely(ndst->error)) { + rxe_dbg_qp(qp, "no route to %pI6\n", daddr); + goto put; + } + + return ndst; +put: + dst_release(ndst); + return NULL; +} + +#else + +static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, + struct net_device *ndev, + struct in6_addr *saddr, + struct in6_addr *daddr) +{ + return NULL; +} + +#endif + +static struct dst_entry *rxe_find_route(struct net_device *ndev, + struct rxe_qp *qp, + struct rxe_av *av) +{ + struct dst_entry *dst = NULL; + + if (qp_type(qp) == IB_QPT_RC) + dst = sk_dst_get(qp->sk->sk); + + if (!dst || !dst_check(dst, qp->dst_cookie)) { + if (dst) + dst_release(dst); + + if (av->network_type == RXE_NETWORK_TYPE_IPV4) { + struct in_addr *saddr; + struct in_addr *daddr; + + saddr = &av->sgid_addr._sockaddr_in.sin_addr; + daddr = &av->dgid_addr._sockaddr_in.sin_addr; + dst = rxe_find_route4(qp, ndev, saddr, daddr); + } else if (av->network_type == RXE_NETWORK_TYPE_IPV6) { + struct in6_addr *saddr6; + struct in6_addr *daddr6; + + saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr; + daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr; + dst = rxe_find_route6(qp, ndev, saddr6, daddr6); +#if IS_ENABLED(CONFIG_IPV6) + if (dst) + qp->dst_cookie = + rt6_get_cookie((struct rt6_info *)dst); +#endif + } + + if (dst && (qp_type(qp) == IB_QPT_RC)) { + dst_hold(dst); + sk_dst_set(qp->sk->sk, dst); + } + } + return dst; +} + +static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) +{ + struct udphdr *udph; + struct rxe_dev *rxe; + struct net_device *ndev = skb->dev; + struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); + + /* takes a reference on rxe->ib_dev + * drop when skb is freed + */ + rxe = rxe_get_dev_from_net(ndev); + if (!rxe && is_vlan_dev(ndev)) + rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); + if (!rxe) + goto drop; + + if (skb_linearize(skb)) { + ib_device_put(&rxe->ib_dev); + goto drop; + } + + udph = udp_hdr(skb); + pkt->rxe = rxe; + pkt->port_num = 1; + pkt->hdr = (u8 *)(udph + 1); + pkt->mask = RXE_GRH_MASK; + pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph); + + rxe_rcv(skb); + + return 0; +drop: + kfree_skb(skb); + + return 0; +} + +static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, + bool ipv6) +{ + int err; + struct socket *sock; + struct udp_port_cfg udp_cfg = { }; + struct udp_tunnel_sock_cfg tnl_cfg = { }; + + if (ipv6) { + udp_cfg.family = AF_INET6; + udp_cfg.ipv6_v6only = 1; + } else { + udp_cfg.family = AF_INET; + } + + udp_cfg.local_udp_port = port; + + /* Create UDP socket */ + err = udp_sock_create(net, &udp_cfg, &sock); + if (err < 0) + return ERR_PTR(err); + + tnl_cfg.encap_type = 1; + tnl_cfg.encap_rcv = rxe_udp_encap_recv; + + /* Setup UDP tunnel */ + setup_udp_tunnel_sock(net, sock, &tnl_cfg); + + return sock; +} + +static void rxe_release_udp_tunnel(struct socket *sk) +{ + if (sk) + udp_tunnel_sock_release(sk); +} + +static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port, + __be16 dst_port) +{ + struct udphdr *udph; + + __skb_push(skb, sizeof(*udph)); + skb_reset_transport_header(skb); + udph = udp_hdr(skb); + + udph->dest = dst_port; + udph->source = src_port; + udph->len = htons(skb->len); + udph->check = 0; +} + +static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb, + __be32 saddr, __be32 daddr, __u8 proto, + __u8 tos, __u8 ttl, __be16 df, bool xnet) +{ + struct iphdr *iph; + + skb_scrub_packet(skb, xnet); + + skb_clear_hash(skb); + skb_dst_set(skb, dst_clone(dst)); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + + skb_push(skb, sizeof(struct iphdr)); + skb_reset_network_header(skb); + + iph = ip_hdr(skb); + + iph->version = IPVERSION; + iph->ihl = sizeof(struct iphdr) >> 2; + iph->tot_len = htons(skb->len); + iph->frag_off = df; + iph->protocol = proto; + iph->tos = tos; + iph->daddr = daddr; + iph->saddr = saddr; + iph->ttl = ttl; + __ip_select_ident(dev_net(dst->dev), iph, + skb_shinfo(skb)->gso_segs ?: 1); +} + +static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, + struct in6_addr *saddr, struct in6_addr *daddr, + __u8 proto, __u8 prio, __u8 ttl) +{ + struct ipv6hdr *ip6h; + + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED + | IPSKB_REROUTED); + skb_dst_set(skb, dst_clone(dst)); + + __skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + ip6_flow_hdr(ip6h, prio, htonl(0)); + ip6h->payload_len = htons(skb->len); + ip6h->nexthdr = proto; + ip6h->hop_limit = ttl; + ip6h->daddr = *daddr; + ip6h->saddr = *saddr; + ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); +} + +static int prepare4(struct rxe_av *av, struct rxe_pkt_info *pkt, + struct sk_buff *skb) +{ + struct rxe_qp *qp = pkt->qp; + struct dst_entry *dst; + bool xnet = false; + __be16 df = htons(IP_DF); + struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr; + struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr; + + dst = rxe_find_route(skb->dev, qp, av); + if (!dst) { + rxe_dbg_qp(qp, "Host not reachable\n"); + return -EHOSTUNREACH; + } + + prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), + cpu_to_be16(ROCE_V2_UDP_DPORT)); + + prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP, + av->grh.traffic_class, av->grh.hop_limit, df, xnet); + + dst_release(dst); + return 0; +} + +static int prepare6(struct rxe_av *av, struct rxe_pkt_info *pkt, + struct sk_buff *skb) +{ + struct rxe_qp *qp = pkt->qp; + struct dst_entry *dst; + struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr; + struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr; + + dst = rxe_find_route(skb->dev, qp, av); + if (!dst) { + rxe_dbg_qp(qp, "Host not reachable\n"); + return -EHOSTUNREACH; + } + + prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), + cpu_to_be16(ROCE_V2_UDP_DPORT)); + + prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP, + av->grh.traffic_class, + av->grh.hop_limit); + + dst_release(dst); + return 0; +} + +int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt, + struct sk_buff *skb) +{ + int err = 0; + + if (skb->protocol == htons(ETH_P_IP)) + err = prepare4(av, pkt, skb); + else if (skb->protocol == htons(ETH_P_IPV6)) + err = prepare6(av, pkt, skb); + + if (ether_addr_equal(skb->dev->dev_addr, av->dmac)) + pkt->mask |= RXE_LOOPBACK_MASK; + + return err; +} + +static void rxe_skb_tx_dtor(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct rxe_qp *qp = sk->sk_user_data; + int skb_out = atomic_dec_return(&qp->skb_out); + + if (unlikely(qp->need_req_skb && + skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)) + rxe_sched_task(&qp->req.task); + + rxe_put(qp); +} + +static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) +{ + int err; + + skb->destructor = rxe_skb_tx_dtor; + skb->sk = pkt->qp->sk->sk; + + rxe_get(pkt->qp); + atomic_inc(&pkt->qp->skb_out); + + if (skb->protocol == htons(ETH_P_IP)) { + err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); + } else if (skb->protocol == htons(ETH_P_IPV6)) { + err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); + } else { + rxe_dbg_qp(pkt->qp, "Unknown layer 3 protocol: %d\n", + skb->protocol); + atomic_dec(&pkt->qp->skb_out); + rxe_put(pkt->qp); + kfree_skb(skb); + return -EINVAL; + } + + if (unlikely(net_xmit_eval(err))) { + rxe_dbg_qp(pkt->qp, "error sending packet: %d\n", err); + return -EAGAIN; + } + + return 0; +} + +/* fix up a send packet to match the packets + * received from UDP before looping them back + */ +static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) +{ + memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); + + if (skb->protocol == htons(ETH_P_IP)) + skb_pull(skb, sizeof(struct iphdr)); + else + skb_pull(skb, sizeof(struct ipv6hdr)); + + if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) { + kfree_skb(skb); + return -EIO; + } + + rxe_rcv(skb); + + return 0; +} + +int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, + struct sk_buff *skb) +{ + int err; + int is_request = pkt->mask & RXE_REQ_MASK; + struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + + if ((is_request && (qp->req.state != QP_STATE_READY)) || + (!is_request && (qp->resp.state != QP_STATE_READY))) { + rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); + goto drop; + } + + rxe_icrc_generate(skb, pkt); + + if (pkt->mask & RXE_LOOPBACK_MASK) + err = rxe_loopback(skb, pkt); + else + err = rxe_send(skb, pkt); + if (err) { + rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); + return err; + } + + if ((qp_type(qp) != IB_QPT_RC) && + (pkt->mask & RXE_END_MASK)) { + pkt->wqe->state = wqe_state_done; + rxe_sched_task(&qp->comp.task); + } + + rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); + goto done; + +drop: + kfree_skb(skb); + err = 0; +done: + return err; +} + +struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, + int paylen, struct rxe_pkt_info *pkt) +{ + unsigned int hdr_len; + struct sk_buff *skb = NULL; + struct net_device *ndev; + const struct ib_gid_attr *attr; + const int port_num = 1; + + attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index); + if (IS_ERR(attr)) + return NULL; + + if (av->network_type == RXE_NETWORK_TYPE_IPV4) + hdr_len = ETH_HLEN + sizeof(struct udphdr) + + sizeof(struct iphdr); + else + hdr_len = ETH_HLEN + sizeof(struct udphdr) + + sizeof(struct ipv6hdr); + + rcu_read_lock(); + ndev = rdma_read_gid_attr_ndev_rcu(attr); + if (IS_ERR(ndev)) { + rcu_read_unlock(); + goto out; + } + skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev), + GFP_ATOMIC); + + if (unlikely(!skb)) { + rcu_read_unlock(); + goto out; + } + + skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev)); + + /* FIXME: hold reference to this netdev until life of this skb. */ + skb->dev = ndev; + rcu_read_unlock(); + + if (av->network_type == RXE_NETWORK_TYPE_IPV4) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); + + pkt->rxe = rxe; + pkt->port_num = port_num; + pkt->hdr = skb_put(skb, paylen); + pkt->mask |= RXE_GRH_MASK; + +out: + rdma_put_gid_attr(attr); + return skb; +} + +/* + * this is required by rxe_cfg to match rxe devices in + * /sys/class/infiniband up with their underlying ethernet devices + */ +const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) +{ + return rxe->ndev->name; +} + +int rxe_net_add(const char *ibdev_name, struct net_device *ndev) +{ + int err; + struct rxe_dev *rxe = NULL; + + rxe = ib_alloc_device(rxe_dev, ib_dev); + if (!rxe) + return -ENOMEM; + + rxe->ndev = ndev; + + err = rxe_add(rxe, ndev->mtu, ibdev_name); + if (err) { + ib_dealloc_device(&rxe->ib_dev); + return err; + } + + return 0; +} + +static void rxe_port_event(struct rxe_dev *rxe, + enum ib_event_type event) +{ + struct ib_event ev; + + ev.device = &rxe->ib_dev; + ev.element.port_num = 1; + ev.event = event; + + ib_dispatch_event(&ev); +} + +/* Caller must hold net_info_lock */ +void rxe_port_up(struct rxe_dev *rxe) +{ + struct rxe_port *port; + + port = &rxe->port; + port->attr.state = IB_PORT_ACTIVE; + + rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE); + dev_info(&rxe->ib_dev.dev, "set active\n"); +} + +/* Caller must hold net_info_lock */ +void rxe_port_down(struct rxe_dev *rxe) +{ + struct rxe_port *port; + + port = &rxe->port; + port->attr.state = IB_PORT_DOWN; + + rxe_port_event(rxe, IB_EVENT_PORT_ERR); + rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); + dev_info(&rxe->ib_dev.dev, "set down\n"); +} + +void rxe_set_port_state(struct rxe_dev *rxe) +{ + if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev)) + rxe_port_up(rxe); + else + rxe_port_down(rxe); +} + +static int rxe_notify(struct notifier_block *not_blk, + unsigned long event, + void *arg) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(arg); + struct rxe_dev *rxe = rxe_get_dev_from_net(ndev); + + if (!rxe) + return NOTIFY_OK; + + switch (event) { + case NETDEV_UNREGISTER: + ib_unregister_device_queued(&rxe->ib_dev); + break; + case NETDEV_UP: + rxe_port_up(rxe); + break; + case NETDEV_DOWN: + rxe_port_down(rxe); + break; + case NETDEV_CHANGEMTU: + rxe_dbg(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); + rxe_set_mtu(rxe, ndev->mtu); + break; + case NETDEV_CHANGE: + rxe_set_port_state(rxe); + break; + case NETDEV_REBOOT: + case NETDEV_GOING_DOWN: + case NETDEV_CHANGEADDR: + case NETDEV_CHANGENAME: + case NETDEV_FEAT_CHANGE: + default: + rxe_dbg(rxe, "ignoring netdev event = %ld for %s\n", + event, ndev->name); + break; + } + + ib_device_put(&rxe->ib_dev); + return NOTIFY_OK; +} + +static struct notifier_block rxe_net_notifier = { + .notifier_call = rxe_notify, +}; + +static int rxe_net_ipv4_init(void) +{ + recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net, + htons(ROCE_V2_UDP_DPORT), false); + if (IS_ERR(recv_sockets.sk4)) { + recv_sockets.sk4 = NULL; + pr_err("Failed to create IPv4 UDP tunnel\n"); + return -1; + } + + return 0; +} + +static int rxe_net_ipv6_init(void) +{ +#if IS_ENABLED(CONFIG_IPV6) + + recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, + htons(ROCE_V2_UDP_DPORT), true); + if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) { + recv_sockets.sk6 = NULL; + pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n"); + return 0; + } + + if (IS_ERR(recv_sockets.sk6)) { + recv_sockets.sk6 = NULL; + pr_err("Failed to create IPv6 UDP tunnel\n"); + return -1; + } +#endif + return 0; +} + +void rxe_net_exit(void) +{ + rxe_release_udp_tunnel(recv_sockets.sk6); + rxe_release_udp_tunnel(recv_sockets.sk4); + unregister_netdevice_notifier(&rxe_net_notifier); +} + +int rxe_net_init(void) +{ + int err; + + recv_sockets.sk6 = NULL; + + err = rxe_net_ipv4_init(); + if (err) + return err; + err = rxe_net_ipv6_init(); + if (err) + goto err_out; + err = register_netdevice_notifier(&rxe_net_notifier); + if (err) { + pr_err("Failed to register netdev notifier\n"); + goto err_out; + } + return 0; +err_out: + rxe_net_exit(); + return err; +} -- cgit v1.2.3