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/net/wireguard/device.c | 478 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 478 insertions(+) create mode 100644 drivers/net/wireguard/device.c (limited to 'drivers/net/wireguard/device.c') diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c new file mode 100644 index 000000000..d58e9f818 --- /dev/null +++ b/drivers/net/wireguard/device.c @@ -0,0 +1,478 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld . All Rights Reserved. + */ + +#include "queueing.h" +#include "socket.h" +#include "timers.h" +#include "device.h" +#include "ratelimiter.h" +#include "peer.h" +#include "messages.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(device_list); + +static int wg_open(struct net_device *dev) +{ + struct in_device *dev_v4 = __in_dev_get_rtnl(dev); + struct inet6_dev *dev_v6 = __in6_dev_get(dev); + struct wg_device *wg = netdev_priv(dev); + struct wg_peer *peer; + int ret; + + if (dev_v4) { + /* At some point we might put this check near the ip_rt_send_ + * redirect call of ip_forward in net/ipv4/ip_forward.c, similar + * to the current secpath check. + */ + IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); + IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; + } + if (dev_v6) + dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; + + mutex_lock(&wg->device_update_lock); + ret = wg_socket_init(wg, wg->incoming_port); + if (ret < 0) + goto out; + list_for_each_entry(peer, &wg->peer_list, peer_list) { + wg_packet_send_staged_packets(peer); + if (peer->persistent_keepalive_interval) + wg_packet_send_keepalive(peer); + } +out: + mutex_unlock(&wg->device_update_lock); + return ret; +} + +static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data) +{ + struct wg_device *wg; + struct wg_peer *peer; + + /* If the machine is constantly suspending and resuming, as part of + * its normal operation rather than as a somewhat rare event, then we + * don't actually want to clear keys. + */ + if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || + IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)) + return 0; + + if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE) + return 0; + + rtnl_lock(); + list_for_each_entry(wg, &device_list, device_list) { + mutex_lock(&wg->device_update_lock); + list_for_each_entry(peer, &wg->peer_list, peer_list) { + del_timer(&peer->timer_zero_key_material); + wg_noise_handshake_clear(&peer->handshake); + wg_noise_keypairs_clear(&peer->keypairs); + } + mutex_unlock(&wg->device_update_lock); + } + rtnl_unlock(); + rcu_barrier(); + return 0; +} + +static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification }; + +static int wg_vm_notification(struct notifier_block *nb, unsigned long action, void *data) +{ + struct wg_device *wg; + struct wg_peer *peer; + + rtnl_lock(); + list_for_each_entry(wg, &device_list, device_list) { + mutex_lock(&wg->device_update_lock); + list_for_each_entry(peer, &wg->peer_list, peer_list) + wg_noise_expire_current_peer_keypairs(peer); + mutex_unlock(&wg->device_update_lock); + } + rtnl_unlock(); + return 0; +} + +static struct notifier_block vm_notifier = { .notifier_call = wg_vm_notification }; + +static int wg_stop(struct net_device *dev) +{ + struct wg_device *wg = netdev_priv(dev); + struct wg_peer *peer; + struct sk_buff *skb; + + mutex_lock(&wg->device_update_lock); + list_for_each_entry(peer, &wg->peer_list, peer_list) { + wg_packet_purge_staged_packets(peer); + wg_timers_stop(peer); + wg_noise_handshake_clear(&peer->handshake); + wg_noise_keypairs_clear(&peer->keypairs); + wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); + } + mutex_unlock(&wg->device_update_lock); + while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL) + kfree_skb(skb); + atomic_set(&wg->handshake_queue_len, 0); + wg_socket_reinit(wg, NULL, NULL); + return 0; +} + +static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct wg_device *wg = netdev_priv(dev); + struct sk_buff_head packets; + struct wg_peer *peer; + struct sk_buff *next; + sa_family_t family; + u32 mtu; + int ret; + + if (unlikely(!wg_check_packet_protocol(skb))) { + ret = -EPROTONOSUPPORT; + net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); + goto err; + } + + peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb); + if (unlikely(!peer)) { + ret = -ENOKEY; + if (skb->protocol == htons(ETH_P_IP)) + net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n", + dev->name, &ip_hdr(skb)->daddr); + else if (skb->protocol == htons(ETH_P_IPV6)) + net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", + dev->name, &ipv6_hdr(skb)->daddr); + goto err_icmp; + } + + family = READ_ONCE(peer->endpoint.addr.sa_family); + if (unlikely(family != AF_INET && family != AF_INET6)) { + ret = -EDESTADDRREQ; + net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n", + dev->name, peer->internal_id); + goto err_peer; + } + + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + + __skb_queue_head_init(&packets); + if (!skb_is_gso(skb)) { + skb_mark_not_on_list(skb); + } else { + struct sk_buff *segs = skb_gso_segment(skb, 0); + + if (IS_ERR(segs)) { + ret = PTR_ERR(segs); + goto err_peer; + } + dev_kfree_skb(skb); + skb = segs; + } + + skb_list_walk_safe(skb, skb, next) { + skb_mark_not_on_list(skb); + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + continue; + + /* We only need to keep the original dst around for icmp, + * so at this point we're in a position to drop it. + */ + skb_dst_drop(skb); + + PACKET_CB(skb)->mtu = mtu; + + __skb_queue_tail(&packets, skb); + } + + spin_lock_bh(&peer->staged_packet_queue.lock); + /* If the queue is getting too big, we start removing the oldest packets + * until it's small again. We do this before adding the new packet, so + * we don't remove GSO segments that are in excess. + */ + while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { + dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); + ++dev->stats.tx_dropped; + } + skb_queue_splice_tail(&packets, &peer->staged_packet_queue); + spin_unlock_bh(&peer->staged_packet_queue.lock); + + wg_packet_send_staged_packets(peer); + + wg_peer_put(peer); + return NETDEV_TX_OK; + +err_peer: + wg_peer_put(peer); +err_icmp: + if (skb->protocol == htons(ETH_P_IP)) + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + else if (skb->protocol == htons(ETH_P_IPV6)) + icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); +err: + ++dev->stats.tx_errors; + kfree_skb(skb); + return ret; +} + +static const struct net_device_ops netdev_ops = { + .ndo_open = wg_open, + .ndo_stop = wg_stop, + .ndo_start_xmit = wg_xmit, + .ndo_get_stats64 = dev_get_tstats64 +}; + +static void wg_destruct(struct net_device *dev) +{ + struct wg_device *wg = netdev_priv(dev); + + rtnl_lock(); + list_del(&wg->device_list); + rtnl_unlock(); + mutex_lock(&wg->device_update_lock); + rcu_assign_pointer(wg->creating_net, NULL); + wg->incoming_port = 0; + wg_socket_reinit(wg, NULL, NULL); + /* The final references are cleared in the below calls to destroy_workqueue. */ + wg_peer_remove_all(wg); + destroy_workqueue(wg->handshake_receive_wq); + destroy_workqueue(wg->handshake_send_wq); + destroy_workqueue(wg->packet_crypt_wq); + wg_packet_queue_free(&wg->handshake_queue, true); + wg_packet_queue_free(&wg->decrypt_queue, false); + wg_packet_queue_free(&wg->encrypt_queue, false); + rcu_barrier(); /* Wait for all the peers to be actually freed. */ + wg_ratelimiter_uninit(); + memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); + free_percpu(dev->tstats); + kvfree(wg->index_hashtable); + kvfree(wg->peer_hashtable); + mutex_unlock(&wg->device_update_lock); + + pr_debug("%s: Interface destroyed\n", dev->name); + free_netdev(dev); +} + +static const struct device_type device_type = { .name = KBUILD_MODNAME }; + +static void wg_setup(struct net_device *dev) +{ + struct wg_device *wg = netdev_priv(dev); + enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | + NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; + const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); + + dev->netdev_ops = &netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->needed_headroom = DATA_PACKET_HEAD_ROOM; + dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE); + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP; + dev->priv_flags |= IFF_NO_QUEUE; + dev->features |= NETIF_F_LLTX; + dev->features |= WG_NETDEV_FEATURES; + dev->hw_features |= WG_NETDEV_FEATURES; + dev->hw_enc_features |= WG_NETDEV_FEATURES; + dev->mtu = ETH_DATA_LEN - overhead; + dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; + + SET_NETDEV_DEVTYPE(dev, &device_type); + + /* We need to keep the dst around in case of icmp replies. */ + netif_keep_dst(dev); + + memset(wg, 0, sizeof(*wg)); + wg->dev = dev; +} + +static int wg_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct wg_device *wg = netdev_priv(dev); + int ret = -ENOMEM; + + rcu_assign_pointer(wg->creating_net, src_net); + init_rwsem(&wg->static_identity.lock); + mutex_init(&wg->socket_update_lock); + mutex_init(&wg->device_update_lock); + wg_allowedips_init(&wg->peer_allowedips); + wg_cookie_checker_init(&wg->cookie_checker, wg); + INIT_LIST_HEAD(&wg->peer_list); + wg->device_update_gen = 1; + + wg->peer_hashtable = wg_pubkey_hashtable_alloc(); + if (!wg->peer_hashtable) + return ret; + + wg->index_hashtable = wg_index_hashtable_alloc(); + if (!wg->index_hashtable) + goto err_free_peer_hashtable; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + goto err_free_index_hashtable; + + wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", + WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); + if (!wg->handshake_receive_wq) + goto err_free_tstats; + + wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", + WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); + if (!wg->handshake_send_wq) + goto err_destroy_handshake_receive; + + wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s", + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name); + if (!wg->packet_crypt_wq) + goto err_destroy_handshake_send; + + ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, + MAX_QUEUED_PACKETS); + if (ret < 0) + goto err_destroy_packet_crypt; + + ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, + MAX_QUEUED_PACKETS); + if (ret < 0) + goto err_free_encrypt_queue; + + ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker, + MAX_QUEUED_INCOMING_HANDSHAKES); + if (ret < 0) + goto err_free_decrypt_queue; + + ret = wg_ratelimiter_init(); + if (ret < 0) + goto err_free_handshake_queue; + + ret = register_netdevice(dev); + if (ret < 0) + goto err_uninit_ratelimiter; + + list_add(&wg->device_list, &device_list); + + /* We wait until the end to assign priv_destructor, so that + * register_netdevice doesn't call it for us if it fails. + */ + dev->priv_destructor = wg_destruct; + + pr_debug("%s: Interface created\n", dev->name); + return ret; + +err_uninit_ratelimiter: + wg_ratelimiter_uninit(); +err_free_handshake_queue: + wg_packet_queue_free(&wg->handshake_queue, false); +err_free_decrypt_queue: + wg_packet_queue_free(&wg->decrypt_queue, false); +err_free_encrypt_queue: + wg_packet_queue_free(&wg->encrypt_queue, false); +err_destroy_packet_crypt: + destroy_workqueue(wg->packet_crypt_wq); +err_destroy_handshake_send: + destroy_workqueue(wg->handshake_send_wq); +err_destroy_handshake_receive: + destroy_workqueue(wg->handshake_receive_wq); +err_free_tstats: + free_percpu(dev->tstats); +err_free_index_hashtable: + kvfree(wg->index_hashtable); +err_free_peer_hashtable: + kvfree(wg->peer_hashtable); + return ret; +} + +static struct rtnl_link_ops link_ops __read_mostly = { + .kind = KBUILD_MODNAME, + .priv_size = sizeof(struct wg_device), + .setup = wg_setup, + .newlink = wg_newlink, +}; + +static void wg_netns_pre_exit(struct net *net) +{ + struct wg_device *wg; + struct wg_peer *peer; + + rtnl_lock(); + list_for_each_entry(wg, &device_list, device_list) { + if (rcu_access_pointer(wg->creating_net) == net) { + pr_debug("%s: Creating namespace exiting\n", wg->dev->name); + netif_carrier_off(wg->dev); + mutex_lock(&wg->device_update_lock); + rcu_assign_pointer(wg->creating_net, NULL); + wg_socket_reinit(wg, NULL, NULL); + list_for_each_entry(peer, &wg->peer_list, peer_list) + wg_socket_clear_peer_endpoint_src(peer); + mutex_unlock(&wg->device_update_lock); + } + } + rtnl_unlock(); +} + +static struct pernet_operations pernet_ops = { + .pre_exit = wg_netns_pre_exit +}; + +int __init wg_device_init(void) +{ + int ret; + + ret = register_pm_notifier(&pm_notifier); + if (ret) + return ret; + + ret = register_random_vmfork_notifier(&vm_notifier); + if (ret) + goto error_pm; + + ret = register_pernet_device(&pernet_ops); + if (ret) + goto error_vm; + + ret = rtnl_link_register(&link_ops); + if (ret) + goto error_pernet; + + return 0; + +error_pernet: + unregister_pernet_device(&pernet_ops); +error_vm: + unregister_random_vmfork_notifier(&vm_notifier); +error_pm: + unregister_pm_notifier(&pm_notifier); + return ret; +} + +void wg_device_uninit(void) +{ + rtnl_link_unregister(&link_ops); + unregister_pernet_device(&pernet_ops); + unregister_random_vmfork_notifier(&vm_notifier); + unregister_pm_notifier(&pm_notifier); + rcu_barrier(); +} -- cgit v1.2.3