From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- drivers/net/netkit.c | 1308 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1308 insertions(+) create mode 100644 drivers/net/netkit.c (limited to 'drivers/net/netkit.c') diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c new file mode 100644 index 000000000..a3931cd82 --- /dev/null +++ b/drivers/net/netkit.c @@ -0,0 +1,1308 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2023 Isovalent */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#define NETKIT_DRV_NAME "netkit" + +#define NETKIT_NUM_RX_QUEUES_MAX 1024 +#define NETKIT_NUM_TX_QUEUES_MAX 1 + +#define NETKIT_NUM_RX_QUEUES_REAL 1 +#define NETKIT_NUM_TX_QUEUES_REAL 1 + +struct netkit { + __cacheline_group_begin(netkit_fastpath); + struct net_device __rcu *peer; + struct bpf_mprog_entry __rcu *active; + enum netkit_action policy; + enum netkit_scrub scrub; + struct bpf_mprog_bundle bundle; + __cacheline_group_end(netkit_fastpath); + + __cacheline_group_begin(netkit_slowpath); + enum netkit_mode mode; + enum netkit_pairing pair; + bool primary; + u32 headroom; + __cacheline_group_end(netkit_slowpath); +}; + +struct netkit_link { + struct bpf_link link; + struct net_device *dev; +}; + +static struct rtnl_link_ops netkit_link_ops; + +static __always_inline int +netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, + enum netkit_action ret) +{ + const struct bpf_mprog_fp *fp; + const struct bpf_prog *prog; + + bpf_mprog_foreach_prog(entry, fp, prog) { + bpf_compute_data_pointers(skb); + ret = bpf_prog_run(prog, skb); + if (ret != NETKIT_NEXT) + break; + } + return ret; +} + +static void netkit_xnet(struct sk_buff *skb) +{ + skb->priority = 0; + skb->mark = 0; +} + +static void netkit_prep_forward(struct sk_buff *skb, + bool xnet, bool xnet_scrub) +{ + skb_scrub_packet(skb, false); + nf_skip_egress(skb, true); + skb_reset_mac_header(skb); + if (!xnet) + return; + skb_clear_tstamp(skb); + if (xnet_scrub) + netkit_xnet(skb); +} + +static struct netkit *netkit_priv(const struct net_device *dev) +{ + return netdev_priv(dev); +} + +static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; + struct netkit *nk = netkit_priv(dev); + enum netkit_action ret = READ_ONCE(nk->policy); + netdev_tx_t ret_dev = NET_XMIT_SUCCESS; + const struct bpf_mprog_entry *entry; + struct net_device *peer; + int len = skb->len; + + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (unlikely(!peer || !(peer->flags & IFF_UP) || + !pskb_may_pull(skb, ETH_HLEN) || + skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer)), + nk->scrub); + eth_skb_pkt_type(skb, peer); + skb->dev = peer; + entry = rcu_dereference(nk->active); + if (entry) + ret = netkit_run(entry, skb, ret); + switch (ret) { + case NETKIT_NEXT: + case NETKIT_PASS: + eth_skb_pull_mac(skb); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { + dev_sw_netstats_tx_add(dev, 1, len); + dev_sw_netstats_rx_add(peer, len); + } else { + goto drop_stats; + } + break; + case NETKIT_REDIRECT: + dev_sw_netstats_tx_add(dev, 1, len); + skb_do_redirect(skb); + break; + case NETKIT_DROP: + default: +drop: + kfree_skb(skb); +drop_stats: + dev_core_stats_tx_dropped_inc(dev); + ret_dev = NET_XMIT_DROP; + break; + } + rcu_read_unlock(); + bpf_net_ctx_clear(bpf_net_ctx); + return ret_dev; +} + +static int netkit_open(struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + if (nk->pair == NETKIT_DEVICE_SINGLE) { + netif_carrier_on(dev); + return 0; + } + if (!peer) + return -ENOTCONN; + if (peer->flags & IFF_UP) { + netif_carrier_on(dev); + netif_carrier_on(peer); + } + return 0; +} + +static int netkit_close(struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + netif_carrier_off(dev); + if (peer) + netif_carrier_off(peer); + return 0; +} + +static int netkit_get_iflink(const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer; + int iflink = 0; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (peer) + iflink = READ_ONCE(peer->ifindex); + rcu_read_unlock(); + return iflink; +} + +static int netkit_set_multicast(struct net_device *dev, + struct netdev_hw_addr_list *uc, + struct netdev_hw_addr_list *mc) +{ + /* Nothing to do, we receive whatever gets pushed to us! */ + return 0; +} + +static int netkit_set_macaddr(struct net_device *dev, void *sa) +{ + struct netkit *nk = netkit_priv(dev); + + if (nk->mode != NETKIT_L2) + return -EOPNOTSUPP; + + return eth_mac_addr(dev, sa); +} + +static void netkit_set_headroom(struct net_device *dev, int headroom) +{ + struct netkit *nk = netkit_priv(dev), *nk2; + struct net_device *peer; + + if (headroom < 0) + headroom = NET_SKB_PAD; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (!peer) { + nk->headroom = headroom; + dev->needed_headroom = headroom; + } else { + nk2 = netkit_priv(peer); + nk->headroom = headroom; + headroom = max(nk->headroom, nk2->headroom); + + peer->needed_headroom = headroom; + dev->needed_headroom = headroom; + } + rcu_read_unlock(); +} + +INDIRECT_CALLABLE_SCOPE struct net_device *netkit_peer_dev(struct net_device *dev) +{ + return rcu_dereference(netkit_priv(dev)->peer); +} + +static void netkit_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + dev_fetch_sw_netstats(stats, dev->tstats); + stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); +} + +static bool netkit_xsk_supported_at_phys(const struct net_device *dev) +{ + if (!dev->netdev_ops->ndo_bpf || + !dev->netdev_ops->ndo_xdp_xmit || + !dev->netdev_ops->ndo_xsk_wakeup) + return false; + return true; +} + +static int netkit_xsk(struct net_device *dev, struct netdev_bpf *xdp) +{ + struct netkit *nk = netkit_priv(dev); + struct netdev_bpf xdp_lower; + struct netdev_rx_queue *rxq; + struct net_device *phys; + bool create = false; + int ret = -EBUSY; + + switch (xdp->command) { + case XDP_SETUP_XSK_POOL: + if (nk->pair == NETKIT_DEVICE_PAIR) + return -EOPNOTSUPP; + if (xdp->xsk.queue_id >= dev->real_num_rx_queues) + return -EINVAL; + + rxq = __netif_get_rx_queue(dev, xdp->xsk.queue_id); + if (!rxq->lease) + return -EOPNOTSUPP; + + phys = rxq->lease->dev; + if (!netkit_xsk_supported_at_phys(phys)) + return -EOPNOTSUPP; + + create = xdp->xsk.pool; + memcpy(&xdp_lower, xdp, sizeof(xdp_lower)); + xdp_lower.xsk.queue_id = get_netdev_rx_queue_index(rxq->lease); + break; + case XDP_SETUP_PROG: + return -EOPNOTSUPP; + default: + return -EINVAL; + } + + netdev_lock(phys); + if (create && + (phys->xdp_features & NETDEV_XDP_ACT_XSK) != NETDEV_XDP_ACT_XSK) { + ret = -EOPNOTSUPP; + goto out; + } + if (!create || !dev_get_min_mp_channel_count(phys)) + ret = phys->netdev_ops->ndo_bpf(phys, &xdp_lower); +out: + netdev_unlock(phys); + return ret; +} + +static int netkit_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) +{ + struct netdev_rx_queue *rxq, *rxq_lease; + struct net_device *phys; + + if (queue_id >= dev->real_num_rx_queues) + return -EINVAL; + + rxq = __netif_get_rx_queue(dev, queue_id); + rxq_lease = READ_ONCE(rxq->lease); + if (unlikely(!rxq_lease)) + return -EOPNOTSUPP; + + /* netkit_xsk already validated full xsk support, hence it's + * fine to call into ndo_xsk_wakeup right away given this + * was a prerequisite to get here in the first place. The + * phys xsk support cannot change without tearing down the + * device (which clears the lease first). + */ + phys = rxq_lease->dev; + return phys->netdev_ops->ndo_xsk_wakeup(phys, + get_netdev_rx_queue_index(rxq_lease), flags); +} + +static int netkit_init(struct net_device *dev) +{ + netdev_lockdep_set_classes(dev); + return 0; +} + +static void netkit_uninit(struct net_device *dev); + +static const struct net_device_ops netkit_netdev_ops = { + .ndo_init = netkit_init, + .ndo_open = netkit_open, + .ndo_stop = netkit_close, + .ndo_start_xmit = netkit_xmit, + .ndo_set_rx_mode_async = netkit_set_multicast, + .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_set_mac_address = netkit_set_macaddr, + .ndo_get_iflink = netkit_get_iflink, + .ndo_get_peer_dev = netkit_peer_dev, + .ndo_get_stats64 = netkit_get_stats, + .ndo_uninit = netkit_uninit, + .ndo_bpf = netkit_xsk, + .ndo_xsk_wakeup = netkit_xsk_wakeup, + .ndo_features_check = passthru_features_check, +}; + +static void netkit_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strscpy(info->driver, NETKIT_DRV_NAME, sizeof(info->driver)); +} + +static const struct ethtool_ops netkit_ethtool_ops = { + .get_drvinfo = netkit_get_drvinfo, +}; + +static int netkit_queue_create(struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct netkit *nk = netkit_priv(dev); + u32 rxq_count_old, rxq_count_new; + int err; + + rxq_count_old = dev->real_num_rx_queues; + rxq_count_new = rxq_count_old + 1; + + /* In paired mode, only the non-primary (peer) device can + * create leased queues since the primary is the management + * side. In single device mode, leasing is always allowed. + */ + if (nk->pair == NETKIT_DEVICE_PAIR && nk->primary) { + NL_SET_ERR_MSG(extack, + "netkit can only lease against the peer device"); + return -EOPNOTSUPP; + } + + err = netif_set_real_num_rx_queues(dev, rxq_count_new); + if (err) { + if (rxq_count_new > dev->num_rx_queues) + NL_SET_ERR_MSG(extack, + "netkit maximum queue limit reached"); + else + NL_SET_ERR_MSG_FMT(extack, + "netkit cannot create more queues err=%d", err); + return err; + } + + return rxq_count_old; +} + +static const struct netdev_queue_mgmt_ops netkit_queue_mgmt_ops = { + .ndo_queue_create = netkit_queue_create, +}; + +static struct net_device *netkit_alloc(struct nlattr *tb[], + const char *ifname, + unsigned char name_assign_type, + unsigned int num_tx_queues, + unsigned int num_rx_queues) +{ + const struct rtnl_link_ops *ops = &netkit_link_ops; + struct net_device *dev; + + if (num_tx_queues > NETKIT_NUM_TX_QUEUES_MAX || + num_rx_queues > NETKIT_NUM_RX_QUEUES_MAX) + return ERR_PTR(-EOPNOTSUPP); + + dev = alloc_netdev_mqs(ops->priv_size, ifname, + name_assign_type, ops->setup, + num_tx_queues, num_rx_queues); + if (dev) { + dev->real_num_tx_queues = NETKIT_NUM_TX_QUEUES_REAL; + dev->real_num_rx_queues = NETKIT_NUM_RX_QUEUES_REAL; + } + return dev; +} + +static void netkit_queue_unlease(struct net_device *dev) +{ + struct netdev_rx_queue *rxq, *rxq_lease; + struct net_device *dev_lease; + int i; + + if (dev->real_num_rx_queues == 1) + return; + + netdev_lock(dev); + for (i = 1; i < dev->real_num_rx_queues; i++) { + rxq = __netif_get_rx_queue(dev, i); + rxq_lease = rxq->lease; + dev_lease = rxq_lease->dev; + + netdev_lock(dev_lease); + netdev_rx_queue_unlease(rxq, rxq_lease); + netdev_unlock(dev_lease); + } + netdev_unlock(dev); +} + +static void netkit_setup(struct net_device *dev) +{ + static const netdev_features_t netkit_features_hw_vlan = + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_TX | + NETIF_F_HW_VLAN_STAG_RX; + static const netdev_features_t netkit_features = + netkit_features_hw_vlan | + NETIF_F_SG | + NETIF_F_FRAGLIST | + NETIF_F_HW_CSUM | + NETIF_F_RXCSUM | + NETIF_F_SCTP_CRC | + NETIF_F_HIGHDMA | + NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL; + + ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + + dev->flags |= IFF_NOARP; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->priv_flags |= IFF_PHONY_HEADROOM; + dev->priv_flags |= IFF_NO_QUEUE; + dev->priv_flags |= IFF_DISABLE_NETPOLL; + dev->lltx = true; + dev->netmem_tx = NETMEM_TX_NO_DMA; + + dev->netdev_ops = &netkit_netdev_ops; + dev->ethtool_ops = &netkit_ethtool_ops; + dev->queue_mgmt_ops = &netkit_queue_mgmt_ops; + + dev->features |= netkit_features; + dev->hw_features = netkit_features; + dev->hw_enc_features = netkit_features; + dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; + dev->vlan_features = dev->features & ~netkit_features_hw_vlan; + + dev->needs_free_netdev = true; + + netif_set_tso_max_size(dev, GSO_MAX_SIZE); +} + +static struct net *netkit_get_link_net(const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + return peer ? dev_net(peer) : dev_net(dev); +} + +static int netkit_check_policy(int policy, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + switch (policy) { + case NETKIT_PASS: + case NETKIT_DROP: + return 0; + default: + NL_SET_ERR_MSG_ATTR(extack, tb, + "Provided default xmit policy not supported"); + return -EINVAL; + } +} + +static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct nlattr *attr = tb[IFLA_ADDRESS]; + + if (!attr) + return 0; + if (nla_len(attr) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(attr))) + return -EADDRNOTAVAIL; + return 0; +} + +static int netkit_new_link(struct net_device *dev, + struct rtnl_newlink_params *params, + struct netlink_ext_ack *extack) +{ + struct net *peer_net = rtnl_newlink_peer_net(params); + enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT; + enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT; + struct nlattr *peer_tb[IFLA_MAX + 1], **tbp, *attr; + enum netkit_pairing pair = NETKIT_DEVICE_PAIR; + enum netkit_action policy_prim = NETKIT_PASS; + enum netkit_action policy_peer = NETKIT_PASS; + bool seen_peer = false, seen_scrub = false; + struct nlattr **data = params->data; + enum netkit_mode mode = NETKIT_L3; + unsigned char ifname_assign_type; + struct nlattr **tb = params->tb; + u16 headroom = 0, tailroom = 0; + struct ifinfomsg *ifmp = NULL; + struct net_device *peer = NULL; + char ifname[IFNAMSIZ]; + struct netkit *nk; + int err; + + tbp = tb; + if (data) { + if (data[IFLA_NETKIT_MODE]) + mode = nla_get_u32(data[IFLA_NETKIT_MODE]); + if (data[IFLA_NETKIT_PEER_INFO]) { + attr = data[IFLA_NETKIT_PEER_INFO]; + ifmp = nla_data(attr); + rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack); + tbp = peer_tb; + } + if (data[IFLA_NETKIT_SCRUB]) + scrub_prim = nla_get_u32(data[IFLA_NETKIT_SCRUB]); + if (data[IFLA_NETKIT_PEER_SCRUB]) + scrub_peer = nla_get_u32(data[IFLA_NETKIT_PEER_SCRUB]); + if (data[IFLA_NETKIT_POLICY]) { + attr = data[IFLA_NETKIT_POLICY]; + policy_prim = nla_get_u32(attr); + err = netkit_check_policy(policy_prim, attr, extack); + if (err < 0) + return err; + } + if (data[IFLA_NETKIT_PEER_POLICY]) { + attr = data[IFLA_NETKIT_PEER_POLICY]; + policy_peer = nla_get_u32(attr); + err = netkit_check_policy(policy_peer, attr, extack); + if (err < 0) + return err; + } + if (data[IFLA_NETKIT_HEADROOM]) + headroom = nla_get_u16(data[IFLA_NETKIT_HEADROOM]); + if (data[IFLA_NETKIT_TAILROOM]) + tailroom = nla_get_u16(data[IFLA_NETKIT_TAILROOM]); + if (data[IFLA_NETKIT_PAIRING]) + pair = nla_get_u32(data[IFLA_NETKIT_PAIRING]); + + seen_scrub = data[IFLA_NETKIT_SCRUB]; + seen_peer = data[IFLA_NETKIT_PEER_INFO] || + data[IFLA_NETKIT_PEER_SCRUB] || + data[IFLA_NETKIT_PEER_POLICY]; + } + + if (ifmp && tbp[IFLA_IFNAME]) { + nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); + ifname_assign_type = NET_NAME_USER; + } else { + strscpy(ifname, "nk%d", IFNAMSIZ); + ifname_assign_type = NET_NAME_ENUM; + } + if (mode != NETKIT_L2 && + (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) + return -EOPNOTSUPP; + if (pair == NETKIT_DEVICE_SINGLE && + (tb != tbp || seen_peer || seen_scrub || + policy_prim != NETKIT_PASS)) + return -EOPNOTSUPP; + + if (pair == NETKIT_DEVICE_PAIR) { + peer = rtnl_create_link(peer_net, ifname, ifname_assign_type, + &netkit_link_ops, tbp, extack); + if (IS_ERR(peer)) + return PTR_ERR(peer); + + netif_inherit_tso_max(peer, dev); + if (headroom) + peer->needed_headroom = headroom; + if (tailroom) + peer->needed_tailroom = tailroom; + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) + eth_hw_addr_random(peer); + if (ifmp && dev->ifindex) + peer->ifindex = ifmp->ifi_index; + + nk = netkit_priv(peer); + nk->primary = false; + nk->policy = policy_peer; + nk->scrub = scrub_peer; + nk->mode = mode; + nk->pair = pair; + nk->headroom = headroom; + bpf_mprog_bundle_init(&nk->bundle); + + err = register_netdevice(peer); + if (err < 0) + goto err_register_peer; + netif_carrier_off(peer); + if (mode == NETKIT_L2) + dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL); + + err = rtnl_configure_link(peer, NULL, 0, NULL); + if (err < 0) + goto err_configure_peer; + } + + if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) + eth_hw_addr_random(dev); + if (tb[IFLA_IFNAME]) + nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); + else + strscpy(dev->name, "nk%d", IFNAMSIZ); + if (headroom) + dev->needed_headroom = headroom; + if (tailroom) + dev->needed_tailroom = tailroom; + + nk = netkit_priv(dev); + nk->primary = true; + nk->policy = policy_prim; + nk->scrub = scrub_prim; + nk->mode = mode; + nk->pair = pair; + nk->headroom = headroom; + bpf_mprog_bundle_init(&nk->bundle); + + if (pair == NETKIT_DEVICE_SINGLE) + xdp_set_features_flag(dev, NETDEV_XDP_ACT_XSK); + + err = register_netdevice(dev); + if (err < 0) + goto err_configure_peer; + netif_carrier_off(dev); + if (mode == NETKIT_L2) + dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL); + + rcu_assign_pointer(netkit_priv(dev)->peer, peer); + if (peer) + rcu_assign_pointer(netkit_priv(peer)->peer, dev); + return 0; +err_configure_peer: + if (peer) + unregister_netdevice(peer); + return err; +err_register_peer: + free_netdev(peer); + return err; +} + +static struct bpf_mprog_entry *netkit_entry_fetch(struct net_device *dev, + bool bundle_fallback) +{ + struct netkit *nk = netkit_priv(dev); + struct bpf_mprog_entry *entry; + + ASSERT_RTNL(); + entry = rcu_dereference_rtnl(nk->active); + if (entry) + return entry; + if (bundle_fallback) + return &nk->bundle.a; + return NULL; +} + +static void netkit_entry_update(struct net_device *dev, + struct bpf_mprog_entry *entry) +{ + struct netkit *nk = netkit_priv(dev); + + ASSERT_RTNL(); + rcu_assign_pointer(nk->active, entry); +} + +static void netkit_entry_sync(void) +{ + synchronize_rcu(); +} + +static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 which) +{ + struct net_device *dev; + struct netkit *nk; + + ASSERT_RTNL(); + + switch (which) { + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + break; + default: + return ERR_PTR(-EINVAL); + } + + dev = __dev_get_by_index(net, ifindex); + if (!dev) + return ERR_PTR(-ENODEV); + if (dev->netdev_ops != &netkit_netdev_ops) + return ERR_PTR(-ENXIO); + + nk = netkit_priv(dev); + if (!nk->primary) + return ERR_PTR(-EACCES); + if (nk->pair == NETKIT_DEVICE_SINGLE) + return ERR_PTR(-EOPNOTSUPP); + if (which == BPF_NETKIT_PEER) { + dev = rcu_dereference_rtnl(nk->peer); + if (!dev) + return ERR_PTR(-ENODEV); + } + return dev; +} + +int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_mprog_entry *entry, *entry_new; + struct bpf_prog *replace_prog = NULL; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex, + attr->attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + entry = netkit_entry_fetch(dev, true); + if (attr->attach_flags & BPF_F_REPLACE) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, + prog->type); + if (IS_ERR(replace_prog)) { + ret = PTR_ERR(replace_prog); + replace_prog = NULL; + goto out; + } + } + ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog, + attr->attach_flags, attr->relative_fd, + attr->expected_revision); + if (!ret) { + if (entry != entry_new) { + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + } + bpf_mprog_commit(entry); + } +out: + if (replace_prog) + bpf_prog_put(replace_prog); + rtnl_unlock(); + return ret; +} + +int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex, + attr->attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags, + attr->relative_fd, attr->expected_revision); + if (!ret) { + if (!bpf_mprog_total(entry_new)) + entry_new = NULL; + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) +{ + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, + attr->query.target_ifindex, + attr->query.attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + ret = bpf_mprog_query(attr, uattr, netkit_entry_fetch(dev, false)); +out: + rtnl_unlock(); + return ret; +} + +static struct netkit_link *netkit_link(const struct bpf_link *link) +{ + return container_of(link, struct netkit_link, link); +} + +static int netkit_link_prog_attach(struct bpf_link *link, u32 flags, + u32 id_or_fd, u64 revision) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev = nkl->dev; + int ret; + + ASSERT_RTNL(); + entry = netkit_entry_fetch(dev, true); + ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags, + id_or_fd, revision); + if (!ret) { + if (entry != entry_new) { + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + } + bpf_mprog_commit(entry); + } + return ret; +} + +static void netkit_link_release(struct bpf_link *link) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = nkl->dev; + if (!dev) + goto out; + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0); + if (!ret) { + if (!bpf_mprog_total(entry_new)) + entry_new = NULL; + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + bpf_mprog_commit(entry); + nkl->dev = NULL; + } +out: + WARN_ON_ONCE(ret); + rtnl_unlock(); +} + +static int netkit_link_update(struct bpf_link *link, struct bpf_prog *nprog, + struct bpf_prog *oprog) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = nkl->dev; + if (!dev) { + ret = -ENOLINK; + goto out; + } + if (oprog && link->prog != oprog) { + ret = -EPERM; + goto out; + } + oprog = link->prog; + if (oprog == nprog) { + bpf_prog_put(nprog); + goto out; + } + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog, + BPF_F_REPLACE | BPF_F_ID, + link->prog->aux->id, 0); + if (!ret) { + WARN_ON_ONCE(entry != entry_new); + oprog = xchg(&link->prog, nprog); + bpf_prog_put(oprog); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +static void netkit_link_dealloc(struct bpf_link *link) +{ + kfree(netkit_link(link)); +} + +static void netkit_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) +{ + const struct netkit_link *nkl = netkit_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (nkl->dev) + ifindex = nkl->dev->ifindex; + rtnl_unlock(); + + seq_printf(seq, "ifindex:\t%u\n", ifindex); + seq_printf(seq, "attach_type:\t%u (%s)\n", + link->attach_type, + link->attach_type == BPF_NETKIT_PRIMARY ? "primary" : "peer"); +} + +static int netkit_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct netkit_link *nkl = netkit_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (nkl->dev) + ifindex = nkl->dev->ifindex; + rtnl_unlock(); + + info->netkit.ifindex = ifindex; + info->netkit.attach_type = link->attach_type; + return 0; +} + +static int netkit_link_detach(struct bpf_link *link) +{ + netkit_link_release(link); + return 0; +} + +static const struct bpf_link_ops netkit_link_lops = { + .release = netkit_link_release, + .detach = netkit_link_detach, + .dealloc = netkit_link_dealloc, + .update_prog = netkit_link_update, + .show_fdinfo = netkit_link_fdinfo, + .fill_link_info = netkit_link_fill_info, +}; + +static int netkit_link_init(struct netkit_link *nkl, + struct bpf_link_primer *link_primer, + const union bpf_attr *attr, + struct net_device *dev, + struct bpf_prog *prog) +{ + bpf_link_init(&nkl->link, BPF_LINK_TYPE_NETKIT, + &netkit_link_lops, prog, attr->link_create.attach_type); + nkl->dev = dev; + return bpf_link_prime(&nkl->link, link_primer); +} + +int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct netkit_link *nkl; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, + attr->link_create.target_ifindex, + attr->link_create.attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + nkl = kzalloc_obj(*nkl, GFP_KERNEL_ACCOUNT); + if (!nkl) { + ret = -ENOMEM; + goto out; + } + ret = netkit_link_init(nkl, &link_primer, attr, dev, prog); + if (ret) { + kfree(nkl); + goto out; + } + ret = netkit_link_prog_attach(&nkl->link, + attr->link_create.flags, + attr->link_create.netkit.relative_fd, + attr->link_create.netkit.expected_revision); + if (ret) { + nkl->dev = NULL; + bpf_link_cleanup(&link_primer); + goto out; + } + ret = bpf_link_settle(&link_primer); +out: + rtnl_unlock(); + return ret; +} + +static void netkit_release_all(struct net_device *dev) +{ + struct bpf_mprog_entry *entry; + struct bpf_tuple tuple = {}; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + + entry = netkit_entry_fetch(dev, false); + if (!entry) + return; + netkit_entry_update(dev, NULL); + netkit_entry_sync(); + bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { + if (tuple.link) + netkit_link(tuple.link)->dev = NULL; + else + bpf_prog_put(tuple.prog); + } +} + +static void netkit_uninit(struct net_device *dev) +{ + netkit_release_all(dev); + netkit_queue_unlease(dev); +} + +static void netkit_del_link(struct net_device *dev, struct list_head *head) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + RCU_INIT_POINTER(nk->peer, NULL); + unregister_netdevice_queue(dev, head); + if (peer) { + nk = netkit_priv(peer); + RCU_INIT_POINTER(nk->peer, NULL); + /* Guard against the peer already being in an unregister + * list (e.g. same-namespace teardown where the peer is + * in the caller's dev_kill_list). list_move_tail() on an + * already-queued device would otherwise corrupt that + * list's iteration. This situation can occur via netkit + * notifier, hence guard against this scenario. + */ + if (!unregister_netdevice_queued(peer)) + unregister_netdevice_queue(peer, head); + } +} + +static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + enum netkit_action policy; + struct nlattr *attr; + int err, i; + static const struct { + u32 attr; + char *name; + } fixed_params[] = { + { IFLA_NETKIT_MODE, "operating mode" }, + { IFLA_NETKIT_SCRUB, "scrubbing" }, + { IFLA_NETKIT_PEER_SCRUB, "peer scrubbing" }, + { IFLA_NETKIT_PEER_INFO, "peer info" }, + { IFLA_NETKIT_HEADROOM, "headroom" }, + { IFLA_NETKIT_TAILROOM, "tailroom" }, + { IFLA_NETKIT_PAIRING, "pairing" }, + }; + + if (!nk->primary) { + NL_SET_ERR_MSG(extack, + "netkit link settings can be changed only through the primary device"); + return -EACCES; + } + + for (i = 0; i < ARRAY_SIZE(fixed_params); i++) { + attr = data[fixed_params[i].attr]; + if (attr) { + NL_SET_ERR_MSG_ATTR_FMT(extack, attr, + "netkit link %s cannot be changed after device creation", + fixed_params[i].name); + return -EACCES; + } + } + + if (data[IFLA_NETKIT_POLICY]) { + err = -EOPNOTSUPP; + attr = data[IFLA_NETKIT_POLICY]; + policy = nla_get_u32(attr); + if (nk->pair == NETKIT_DEVICE_PAIR) + err = netkit_check_policy(policy, attr, extack); + if (err) + return err; + WRITE_ONCE(nk->policy, policy); + } + + if (data[IFLA_NETKIT_PEER_POLICY]) { + err = -EOPNOTSUPP; + attr = data[IFLA_NETKIT_PEER_POLICY]; + policy = nla_get_u32(attr); + if (peer) + err = netkit_check_policy(policy, attr, extack); + if (err) + return err; + nk = netkit_priv(peer); + WRITE_ONCE(nk->policy, policy); + } + + return 0; +} + +static void netkit_check_lease_unregister(struct net_device *dev) +{ + LIST_HEAD(list_kill); + u32 q_idx; + + if (READ_ONCE(dev->reg_state) != NETREG_UNREGISTERING || + !dev->dev.parent) + return; + + netdev_lock_ops(dev); + for (q_idx = 0; q_idx < dev->real_num_rx_queues; q_idx++) { + struct net_device *tmp = dev; + struct netdev_rx_queue *rxq; + u32 tmp_q_idx = q_idx; + + rxq = __netif_get_rx_queue_lease(&tmp, &tmp_q_idx, + NETIF_PHYS_TO_VIRT); + if (rxq && tmp != dev && + tmp->netdev_ops == &netkit_netdev_ops) { + /* A single phys device can have multiple queues leased + * to one netkit device. We can only queue that netkit + * device once to the list_kill. Queues of that phys + * device can be leased with different individual netkit + * devices, hence we batch via list_kill. + */ + if (unregister_netdevice_queued(tmp)) + continue; + netkit_del_link(tmp, &list_kill); + } + } + netdev_unlock_ops(dev); + unregister_netdevice_many(&list_kill); +} + +static int netkit_notifier(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (event == NETDEV_UNREGISTER) + netkit_check_lease_unregister(dev); + return NOTIFY_DONE; +} + +static size_t netkit_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_POLICY */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_SCRUB */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_SCRUB */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */ + nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */ + nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_HEADROOM */ + nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_TAILROOM */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PAIRING */ + 0; +} + +static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + if (nla_put_u8(skb, IFLA_NETKIT_PRIMARY, nk->primary)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_POLICY, nk->policy)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_MODE, nk->mode)) + return -EMSGSIZE; + if (nk->pair == NETKIT_DEVICE_PAIR && + nla_put_u32(skb, IFLA_NETKIT_SCRUB, nk->scrub)) + return -EMSGSIZE; + if (nla_put_u16(skb, IFLA_NETKIT_HEADROOM, dev->needed_headroom)) + return -EMSGSIZE; + if (nla_put_u16(skb, IFLA_NETKIT_TAILROOM, dev->needed_tailroom)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_PAIRING, nk->pair)) + return -EMSGSIZE; + + if (peer) { + nk = netkit_priv(peer); + if (nla_put_u32(skb, IFLA_NETKIT_PEER_POLICY, nk->policy)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_PEER_SCRUB, nk->scrub)) + return -EMSGSIZE; + } + + return 0; +} + +static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = { + [IFLA_NETKIT_PEER_INFO] = { .len = sizeof(struct ifinfomsg) }, + [IFLA_NETKIT_MODE] = NLA_POLICY_MAX(NLA_U32, NETKIT_L3), + [IFLA_NETKIT_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_PEER_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_HEADROOM] = { .type = NLA_U16 }, + [IFLA_NETKIT_TAILROOM] = { .type = NLA_U16 }, + [IFLA_NETKIT_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT), + [IFLA_NETKIT_PEER_SCRUB] = NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT), + [IFLA_NETKIT_PAIRING] = NLA_POLICY_MAX(NLA_U32, NETKIT_DEVICE_SINGLE), + [IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT, + .reject_message = "Primary attribute is read-only" }, +}; + +static struct rtnl_link_ops netkit_link_ops = { + .kind = NETKIT_DRV_NAME, + .priv_size = sizeof(struct netkit), + .alloc = netkit_alloc, + .setup = netkit_setup, + .newlink = netkit_new_link, + .dellink = netkit_del_link, + .changelink = netkit_change_link, + .get_link_net = netkit_get_link_net, + .get_size = netkit_get_size, + .fill_info = netkit_fill_info, + .policy = netkit_policy, + .validate = netkit_validate, + .peer_type = IFLA_NETKIT_PEER_INFO, + .maxtype = IFLA_NETKIT_MAX, +}; + +static struct notifier_block netkit_netdev_notifier = { + .notifier_call = netkit_notifier, +}; + +static __init int netkit_mod_init(void) +{ + int ret; + + BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT || + (int)NETKIT_PASS != (int)TCX_PASS || + (int)NETKIT_DROP != (int)TCX_DROP || + (int)NETKIT_REDIRECT != (int)TCX_REDIRECT); + + ret = rtnl_link_register(&netkit_link_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&netkit_netdev_notifier); + if (ret) + rtnl_link_unregister(&netkit_link_ops); + return ret; +} + +static __exit void netkit_mod_exit(void) +{ + unregister_netdevice_notifier(&netkit_netdev_notifier); + rtnl_link_unregister(&netkit_link_ops); +} + +module_init(netkit_mod_init); +module_exit(netkit_mod_exit); + +MODULE_DESCRIPTION("BPF-programmable network device"); +MODULE_AUTHOR("Daniel Borkmann "); +MODULE_AUTHOR("Nikolay Aleksandrov "); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK(NETKIT_DRV_NAME); -- cgit v1.3.1