diff options
-rw-r--r-- | drivers/net/netkit.c | 22 | ||||
-rw-r--r-- | drivers/net/veth.c | 44 | ||||
-rw-r--r-- | drivers/net/vrf.c | 38 | ||||
-rw-r--r-- | include/linux/bpf_verifier.h | 16 | ||||
-rw-r--r-- | include/linux/netdevice.h | 30 | ||||
-rw-r--r-- | include/net/netkit.h | 6 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 402 | ||||
-rw-r--r-- | net/core/dev.c | 57 | ||||
-rw-r--r-- | net/core/filter.c | 19 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/tc_redirect.c | 317 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/verifier.c | 2 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/bpf_loop_bench.c | 13 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/cb_refs.c | 1 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/exceptions_fail.c | 2 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/strobemeta.h | 78 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c | 242 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/verifier_subprog_precision.c | 86 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c | 84 |
18 files changed, 1043 insertions, 416 deletions
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 5a0f86f38f09..97bd6705c241 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -7,6 +7,7 @@ #include <linux/filter.h> #include <linux/netfilter_netdev.h> #include <linux/bpf_mprog.h> +#include <linux/indirect_call_wrapper.h> #include <net/netkit.h> #include <net/dst.h> @@ -68,6 +69,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_t ret_dev = NET_XMIT_SUCCESS; const struct bpf_mprog_entry *entry; struct net_device *peer; + int len = skb->len; rcu_read_lock(); peer = rcu_dereference(nk->peer); @@ -85,15 +87,22 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) case NETKIT_PASS: skb->protocol = eth_type_trans(skb, skb->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - __netif_rx(skb); + 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; @@ -169,11 +178,18 @@ out: rcu_read_unlock(); } -static struct net_device *netkit_peer_dev(struct net_device *dev) +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 void netkit_uninit(struct net_device *dev); static const struct net_device_ops netkit_netdev_ops = { @@ -184,6 +200,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_set_rx_headroom = netkit_set_headroom, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, + .ndo_get_stats64 = netkit_get_stats, .ndo_uninit = netkit_uninit, .ndo_features_check = passthru_features_check, }; @@ -218,6 +235,7 @@ static void netkit_setup(struct net_device *dev) 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; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 9980517ed8b0..6cc352296c67 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -373,7 +373,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) { if (!use_napi) - dev_lstats_add(dev, length); + dev_sw_netstats_tx_add(dev, 1, length); else __veth_xdp_flush(rq); } else { @@ -387,14 +387,6 @@ drop: return ret; } -static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes) -{ - struct veth_priv *priv = netdev_priv(dev); - - dev_lstats_read(dev, packets, bytes); - return atomic64_read(&priv->dropped); -} - static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); @@ -432,24 +424,24 @@ static void veth_get_stats64(struct net_device *dev, struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; struct veth_stats rx; - u64 packets, bytes; - tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes); - tot->tx_bytes = bytes; - tot->tx_packets = packets; + tot->tx_dropped = atomic64_read(&priv->dropped); + dev_fetch_sw_netstats(tot, dev->tstats); veth_stats_rx(&rx, dev); tot->tx_dropped += rx.xdp_tx_err; tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err; - tot->rx_bytes = rx.xdp_bytes; - tot->rx_packets = rx.xdp_packets; + tot->rx_bytes += rx.xdp_bytes; + tot->rx_packets += rx.xdp_packets; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { - veth_stats_tx(peer, &packets, &bytes); - tot->rx_bytes += bytes; - tot->rx_packets += packets; + struct rtnl_link_stats64 tot_peer = {}; + + dev_fetch_sw_netstats(&tot_peer, peer->tstats); + tot->rx_bytes += tot_peer.tx_bytes; + tot->rx_packets += tot_peer.tx_packets; veth_stats_rx(&rx, peer); tot->tx_dropped += rx.peer_tq_xdp_xmit_err; @@ -1506,25 +1498,12 @@ static void veth_free_queues(struct net_device *dev) static int veth_dev_init(struct net_device *dev) { - int err; - - dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); - if (!dev->lstats) - return -ENOMEM; - - err = veth_alloc_queues(dev); - if (err) { - free_percpu(dev->lstats); - return err; - } - - return 0; + return veth_alloc_queues(dev); } static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); - free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -1796,6 +1775,7 @@ static void veth_setup(struct net_device *dev) NETIF_F_HW_VLAN_STAG_RX); dev->needs_free_netdev = true; dev->priv_destructor = veth_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->max_mtu = ETH_MAX_MTU; dev->hw_features = VETH_FEATURES; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index db766941b78f..bb95ce43cd97 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -121,22 +121,12 @@ struct net_vrf { int ifindex; }; -struct pcpu_dstats { - u64 tx_pkts; - u64 tx_bytes; - u64 tx_drps; - u64 rx_pkts; - u64 rx_bytes; - u64 rx_drps; - struct u64_stats_sync syncp; -}; - static void vrf_rx_stats(struct net_device *dev, int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->rx_pkts++; + dstats->rx_packets++; dstats->rx_bytes += len; u64_stats_update_end(&dstats->syncp); } @@ -161,10 +151,10 @@ static void vrf_get_stats64(struct net_device *dev, do { start = u64_stats_fetch_begin(&dstats->syncp); tbytes = dstats->tx_bytes; - tpkts = dstats->tx_pkts; - tdrops = dstats->tx_drps; + tpkts = dstats->tx_packets; + tdrops = dstats->tx_drops; rbytes = dstats->rx_bytes; - rpkts = dstats->rx_pkts; + rpkts = dstats->rx_packets; } while (u64_stats_fetch_retry(&dstats->syncp, start)); stats->tx_bytes += tbytes; stats->tx_packets += tpkts; @@ -421,7 +411,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) vrf_rx_stats(dev, len); else - this_cpu_inc(dev->dstats->rx_drps); + this_cpu_inc(dev->dstats->rx_drops); return NETDEV_TX_OK; } @@ -616,11 +606,11 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->tx_pkts++; + dstats->tx_packets++; dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { - this_cpu_inc(dev->dstats->tx_drps); + this_cpu_inc(dev->dstats->tx_drops); } return ret; @@ -1174,22 +1164,15 @@ static void vrf_dev_uninit(struct net_device *dev) vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); - - free_percpu(dev->dstats); - dev->dstats = NULL; } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); - dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); - if (!dev->dstats) - goto out_nomem; - /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) - goto out_stats; + goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; @@ -1203,9 +1186,6 @@ static int vrf_dev_init(struct net_device *dev) out_rth: vrf_rtable_release(dev, vrf); -out_stats: - free_percpu(dev->dstats); - dev->dstats = NULL; out_nomem: return -ENOMEM; } @@ -1704,6 +1684,8 @@ static void vrf_setup(struct net_device *dev) dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; + + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 24213a99cc79..aa4d19d0bc94 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -301,6 +301,17 @@ struct bpf_func_state { struct tnum callback_ret_range; bool in_async_callback_fn; bool in_exception_callback_fn; + /* For callback calling functions that limit number of possible + * callback executions (e.g. bpf_loop) keeps track of current + * simulated iteration number. + * Value in frame N refers to number of times callback with frame + * N+1 was simulated, e.g. for the following call: + * + * bpf_loop(..., fn, ...); | suppose current frame is N + * | fn would be simulated in frame N+1 + * | number of simulations is tracked in frame N + */ + u32 callback_depth; /* The following fields should be last. See copy_func_state() */ int acquired_refs; @@ -400,6 +411,7 @@ struct bpf_verifier_state { struct bpf_idx_pair *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; + u32 callback_unroll_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ @@ -511,6 +523,10 @@ struct bpf_insn_aux_data { * this instruction, regardless of any heuristics */ bool force_checkpoint; + /* true if instruction is a call to a helper function that + * accepts callback function as a parameter. + */ + bool calls_callback; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a16c9cc063fe..2564e209465e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1797,6 +1797,13 @@ enum netdev_ml_priv_type { ML_PRIV_CAN, }; +enum netdev_stat_type { + NETDEV_PCPU_STAT_NONE, + NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ + NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ + NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ +}; + /** * struct net_device - The DEVICE structure. * @@ -1991,10 +1998,14 @@ enum netdev_ml_priv_type { * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type - * @lstats: Loopback statistics - * @tstats: Tunnel statistics - * @dstats: Dummy statistics - * @vstats: Virtual ethernet statistics + * + * @pcpu_stat_type: Type of device statistics which the core should + * allocate/free: none, lstats, tstats, dstats. none + * means the driver is handling statistics allocation/ + * freeing internally. + * @lstats: Loopback statistics: packets, bytes + * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes + * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP @@ -2354,6 +2365,7 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; + enum netdev_stat_type pcpu_stat_type:8; union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; @@ -2755,6 +2767,16 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); +struct pcpu_dstats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_drops; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; + struct u64_stats_sync syncp; +} __aligned(8 * sizeof(u64)); + struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; diff --git a/include/net/netkit.h b/include/net/netkit.h index 0ba2e6b847ca..9ec0163739f4 100644 --- a/include/net/netkit.h +++ b/include/net/netkit.h @@ -10,6 +10,7 @@ int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev)); #else static inline int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -34,5 +35,10 @@ static inline int netkit_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline struct net_device *netkit_peer_dev(struct net_device *dev) +{ + return NULL; +} #endif /* CONFIG_NETKIT */ #endif /* __NET_NETKIT_H */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6da370a047fe..af2819d5c8ee 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -547,13 +547,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_dynptr_data; } -static bool is_callback_calling_kfunc(u32 btf_id); +static bool is_sync_callback_calling_kfunc(u32 btf_id); static bool is_bpf_throw_kfunc(struct bpf_insn *insn); -static bool is_callback_calling_function(enum bpf_func_id func_id) +static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || - func_id == BPF_FUNC_timer_set_callback || func_id == BPF_FUNC_find_vma || func_id == BPF_FUNC_loop || func_id == BPF_FUNC_user_ringbuf_drain; @@ -564,6 +563,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_timer_set_callback; } +static bool is_callback_calling_function(enum bpf_func_id func_id) +{ + return is_sync_callback_calling_function(func_id) || + is_async_callback_calling_function(func_id); +} + +static bool is_sync_callback_calling_insn(struct bpf_insn *insn) +{ + return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) || + (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -1808,6 +1819,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; dst_state->dfs_depth = src->dfs_depth; + dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; @@ -3439,13 +3451,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env, reg->subreg_def = DEF_NOT_SUBREG; } -static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, - enum reg_arg_type t) +static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, + enum reg_arg_type t) { - struct bpf_verifier_state *vstate = env->cur_state; - struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; - struct bpf_reg_state *reg, *regs = state->regs; + struct bpf_reg_state *reg; bool rw64; if (regno >= MAX_BPF_REG) { @@ -3486,6 +3496,15 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, + enum reg_arg_type t) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + + return __check_reg_arg(env, state->regs, regno, t); +} + static void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; @@ -3724,6 +3743,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) } } +static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); + /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. @@ -3899,16 +3920,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, return -EFAULT; return 0; } - } else if ((bpf_helper_call(insn) && - is_callback_calling_function(insn->imm) && - !is_async_callback_calling_function(insn->imm)) || - (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) { - /* callback-calling helper or kfunc call, which means - * we are exiting from subprog, but unlike the subprog - * call handling above, we shouldn't propagate - * precision of r1-r5 (if any requested), as they are - * not actually arguments passed directly to callback - * subprogs + } else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) { + /* exit from callback subprog to callback-calling helper or + * kfunc call. Use idx/subseq_idx check to discern it from + * straight line code backtracking. + * Unlike the subprog call handling above, we shouldn't + * propagate precision of r1-r5 (if any requested), as they are + * not actually arguments passed directly to callback subprogs */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); @@ -3943,10 +3961,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, } else if (opcode == BPF_EXIT) { bool r0_precise; + /* Backtracking to a nested function call, 'idx' is a part of + * the inner frame 'subseq_idx' is a part of the outer frame. + * In case of a regular function call, instructions giving + * precision to registers R1-R5 should have been found already. + * In case of a callback, it is ok to have R1-R5 marked for + * backtracking, as these registers are set by the function + * invoking callback. + */ + if (subseq_idx >= 0 && calls_callback(env, subseq_idx)) + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + bt_clear_reg(bt, i); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { - /* if backtracing was looking for registers R1-R5 - * they should have been found already. - */ verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; @@ -9350,7 +9376,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env, /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); - check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK); } } @@ -9363,11 +9389,10 @@ static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); -static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx, int subprog, - set_callee_state_fn set_callee_state_cb) +static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite, + set_callee_state_fn set_callee_state_cb, + struct bpf_verifier_state *state) { - struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; int err; @@ -9377,54 +9402,72 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -E2BIG; } - caller = state->frame[state->curframe]; if (state->frame[state->curframe + 1]) { verbose(env, "verifier bug. Frame %d already allocated\n", state->curframe + 1); return -EFAULT; } + caller = state->frame[state->curframe]; + callee = kzalloc(sizeof(*callee), GFP_KERNEL); + if (!callee) + return -ENOMEM; + state->frame[state->curframe + 1] = callee; + + /* callee cannot access r0, r6 - r9 for reading and has to write + * into its own stack before reading from it. + * callee can read/write into caller's stack + */ + init_func_state(env, callee, + /* remember the callsite, it will be used by bpf_exit */ + callsite, + state->curframe + 1 /* frameno within this callchain */, + subprog /* subprog number within this prog */); + /* Transfer references to the callee */ + err = copy_reference_state(callee, caller); + err = err ?: set_callee_state_cb(env, caller, callee, callsite); + if (err) + goto err_out; + + /* only increment it after check_reg_arg() finished */ + state->curframe++; + + return 0; + +err_out: + free_func_state(callee); + state->frame[state->curframe + 1] = NULL; + return err; +} + +static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int insn_idx, int subprog, + set_callee_state_fn set_callee_state_cb) +{ + struct bpf_verifier_state *state = env->cur_state, *callback_state; + struct bpf_func_state *caller, *callee; + int err; + + caller = state->frame[state->curframe]; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; - if (subprog_is_global(env, subprog)) { - if (err) { - verbose(env, "Caller passes invalid args into func#%d\n", - subprog); - return err; - } else { - if (env->log.level & BPF_LOG_LEVEL) - verbose(env, - "Func#%d is global and valid. Skipping.\n", - subprog); - clear_caller_saved_regs(env, caller->regs); - - /* All global functions return a 64-bit SCALAR_VALUE */ - mark_reg_unknown(env, caller->regs, BPF_REG_0); - caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; - - /* continue with next insn after call */ - return 0; - } - } /* set_callee_state is used for direct subprog calls, but we are * interested in validating only BPF helpers that can call subprogs as * callbacks */ - if (set_callee_state_cb != set_callee_state) { - env->subprog_info[subprog].is_cb = true; - if (bpf_pseudo_kfunc_call(insn) && - !is_callback_calling_kfunc(insn->imm)) { - verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", - func_id_name(insn->imm), insn->imm); - return -EFAULT; - } else if (!bpf_pseudo_kfunc_call(insn) && - !is_callback_calling_function(insn->imm)) { /* helper */ - verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", - func_id_name(insn->imm), insn->imm); - return -EFAULT; - } + env->subprog_info[subprog].is_cb = true; + if (bpf_pseudo_kfunc_call(insn) && + !is_sync_callback_calling_kfunc(insn->imm)) { + verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } else if (!bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_function(insn->imm)) { /* helper */ + verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; } if (insn->code == (BPF_JMP | BPF_CALL) && @@ -9435,53 +9478,83 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn /* there is no real recursion here. timer callbacks are async */ env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, - *insn_idx, subprog); + insn_idx, subprog); if (!async_cb) return -EFAULT; callee = async_cb->frame[0]; callee->async_entry_cnt = caller->async_entry_cnt + 1; /* Convert bpf_timer_set_callback() args into timer callback args */ - err = set_callee_state_cb(env, caller, callee, *insn_idx); + err = set_callee_state_cb(env, caller, callee, insn_idx); if (err) return err; + return 0; + } + + /* for callback functions enqueue entry to callback and + * proceed with next instruction within current frame. + */ + callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false); + if (!callback_state) + return -ENOMEM; + + err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb, + callback_state); + if (err) + return err; + + callback_state->callback_unroll_depth++; + callback_state->frame[callback_state->curframe - 1]->callback_depth++; + caller->callback_depth = 0; + return 0; +} + +static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *caller; + int err, subprog, target_insn; + + target_insn = *insn_idx + insn->imm + 1; + subprog = find_subprog(env, target_insn); + if (subprog < 0) { + verbose(env, "verifier bug. No program starts at insn %d\n", target_insn); + return -EFAULT; + } + + caller = state->frame[state->curframe]; + err = btf_check_subprog_call(env, subprog, caller->regs); + if (err == -EFAULT) + return err; + if (subprog_is_global(env, subprog)) { + if (err) { + verbose(env, "Caller passes invalid args into func#%d\n", subprog); + return err; + } + + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, "Func#%d is global and valid. Skipping.\n", subprog); clear_caller_saved_regs(env, caller->regs); + + /* All global functions return a 64-bit SCALAR_VALUE */ mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* continue with next insn after call */ return 0; } - callee = kzalloc(sizeof(*callee), GFP_KERNEL); - if (!callee) - return -ENOMEM; - state->frame[state->curframe + 1] = callee; - - /* callee cannot access r0, r6 - r9 for reading and has to write - * into its own stack before reading from it. - * callee can read/write into caller's stack + /* for regular function entry setup new frame and continue + * from that frame. */ - init_func_state(env, callee, - /* remember the callsite, it will be used by bpf_exit */ - *insn_idx /* callsite */, - state->curframe + 1 /* frameno within this callchain */, - subprog /* subprog number within this prog */); - - /* Transfer references to the callee */ - err = copy_reference_state(callee, caller); + err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state); if (err) - goto err_out; - - err = set_callee_state_cb(env, caller, callee, *insn_idx); - if (err) - goto err_out; + return err; clear_caller_saved_regs(env, caller->regs); - /* only increment it after check_reg_arg() finished */ - state->curframe++; - /* and go analyze first insn of the callee */ *insn_idx = env->subprog_info[subprog].start - 1; @@ -9489,14 +9562,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn verbose(env, "caller:\n"); print_verifier_state(env, caller, true); verbose(env, "callee:\n"); - print_verifier_state(env, callee, true); + print_verifier_state(env, state->frame[state->curframe], true); } - return 0; -err_out: - free_func_state(callee); - state->frame[state->curframe + 1] = NULL; - return err; + return 0; } int map_set_for_each_callback_args(struct bpf_verifier_env *env, @@ -9540,22 +9609,6 @@ static int set_callee_state(struct bpf_verifier_env *env, return 0; } -static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx) -{ - int subprog, target_insn; - - target_insn = *insn_idx + insn->imm + 1; - subprog = find_subprog(env, target_insn); - if (subprog < 0) { - verbose(env, "verifier bug. No program starts at insn %d\n", - target_insn); - return -EFAULT; - } - - return __check_func_call(env, insn, insn_idx, subprog, set_callee_state); -} - static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -9748,9 +9801,10 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { - struct bpf_verifier_state *state = env->cur_state; + struct bpf_verifier_state *state = env->cur_state, *prev_st; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + bool in_callback_fn; int err; callee = state->frame[state->curframe]; @@ -9779,6 +9833,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); return -EINVAL; } + if (!calls_callback(env, callee->callsite)) { + verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n", + *insn_idx, callee->callsite); + return -EFAULT; + } } else { /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; @@ -9796,7 +9855,16 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return err; } - *insn_idx = callee->callsite + 1; + /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite, + * there function call logic would reschedule callback visit. If iteration + * converges is_state_visited() would prune that visit eventually. + */ + in_callback_fn = callee->in_callback_fn; + if (in_callback_fn) + *insn_idx = callee->callsite; + else + *insn_idx = callee->callsite + 1; + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee, true); @@ -9807,6 +9875,24 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); state->frame[state->curframe--] = NULL; + + /* for callbacks widen imprecise scalars to make programs like below verify: + * + * struct ctx { int i; } + * void cb(int idx, struct ctx *ctx) { ctx->i++; ... } + * ... + * struct ctx = { .i = 0; } + * bpf_loop(100, cb, &ctx, 0); + * + * This is similar to what is done in process_iter_next_call() for open + * coded iterators. + */ + prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL; + if (prev_st) { + err = widen_imprecise_scalars(env, prev_st, state); + if (err) + return err; + } return 0; } @@ -10209,24 +10295,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } break; case BPF_FUNC_for_each_map_elem: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_map_elem_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_map_elem_callback_state); break; case BPF_FUNC_timer_set_callback: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_timer_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_timer_callback_state); break; case BPF_FUNC_find_vma: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_find_vma_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_find_vma_callback_state); break; case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: update_loop_inline_state(env, meta.subprogno); - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_loop_callback_state); + /* Verifier relies on R1 value to determine if bpf_loop() iteration + * is finished, thus mark it precise. + */ + err = mark_chain_precision(env, BPF_REG_1); + if (err) + return err; + if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_loop_callback_state); + } else { + cur_func(env)->callback_depth = 0; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame%d bpf_loop iteration limit reached\n", + env->cur_state->curframe); + } break; case BPF_FUNC_dynptr_from_mem: if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { @@ -10322,8 +10421,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn break; } case BPF_FUNC_user_ringbuf_drain: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_user_ringbuf_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_user_ringbuf_callback_state); break; } @@ -11211,7 +11310,7 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id) btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]; } -static bool is_callback_calling_kfunc(u32 btf_id) +static bool is_sync_callback_calling_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; } @@ -11963,6 +12062,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EACCES; } + /* Check the arguments */ + err = check_kfunc_args(env, &meta, insn_idx); + if (err < 0) + return err; + + if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_rbtree_add_callback_state); + if (err) { + verbose(env, "kfunc %s#%d failed callback verification\n", + func_name, meta.func_id); + return err; + } + } + rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); @@ -11998,10 +12112,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } - /* Check the arguments */ - err = check_kfunc_args(env, &meta, insn_idx); - if (err < 0) - return err; /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ @@ -12035,16 +12145,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } - if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_rbtree_add_callback_state); - if (err) { - verbose(env, "kfunc %s#%d failed callback verification\n", - func_name, meta.func_id); - return err; - } - } - if (meta.func_id == special_kfunc_list[KF_bpf_throw]) { if (!bpf_jit_supports_exceptions()) { verbose(env, "JIT does not support calling kfunc %s#%d\n", @@ -15408,6 +15508,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx) return env->insn_aux_data[insn_idx].force_checkpoint; } +static void mark_calls_callback(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].calls_callback = true; +} + +static bool calls_callback(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].calls_callback; +} enum { DONE_EXPLORING = 0, @@ -15521,6 +15630,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env) * async state will be pushed for further exploration. */ mark_prune_point(env, t); + /* For functions that invoke callbacks it is not known how many times + * callback would be called. Verifier models callback calling functions + * by repeatedly visiting callback bodies and returning to origin call + * instruction. + * In order to stop such iteration verifier needs to identify when a + * state identical some state from a previous iteration is reached. + * Check below forces creation of checkpoint before callback calling + * instruction to allow search for such identical states. + */ + if (is_sync_callback_calling_insn(insn)) { + mark_calls_callback(env, t); + mark_force_checkpoint(env, t); + mark_prune_point(env, t); + mark_jmp_point(env, t); + } if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { struct bpf_kfunc_call_arg_meta meta; @@ -16990,10 +17114,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } goto skip_inf_loop_check; } + if (calls_callback(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, true)) + goto hit; + goto skip_inf_loop_check; + } /* attempt to detect infinite loop to avoid unnecessary doomed work */ if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur, false) && - !iter_active_depths_differ(&sl->state, cur)) { + !iter_active_depths_differ(&sl->state, cur) && + sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); verbose(env, "cur state:"); diff --git a/net/core/dev.c b/net/core/dev.c index af53f6d838ce..c879246be48d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10051,6 +10051,54 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static int netdev_do_alloc_pcpu_stats(struct net_device *dev) +{ + void __percpu *v; + + /* Drivers implementing ndo_get_peer_dev must support tstat + * accounting, so that skb_do_redirect() can bump the dev's + * RX stats upon network namespace switch. + */ + if (dev->netdev_ops->ndo_get_peer_dev && + dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) + return -EOPNOTSUPP; + + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return 0; + case NETDEV_PCPU_STAT_LSTATS: + v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); + break; + default: + return -EINVAL; + } + + return v ? 0 : -ENOMEM; +} + +static void netdev_do_free_pcpu_stats(struct net_device *dev) +{ + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return; + case NETDEV_PCPU_STAT_LSTATS: + free_percpu(dev->lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + free_percpu(dev->tstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + free_percpu(dev->dstats); + break; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -10111,9 +10159,13 @@ int register_netdevice(struct net_device *dev) goto err_uninit; } + ret = netdev_do_alloc_pcpu_stats(dev); + if (ret) + goto err_uninit; + ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) - goto err_uninit; + goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable @@ -10219,6 +10271,8 @@ err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); +err_free_pcpu: + netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10471,6 +10525,7 @@ void netdev_run_todo(void) WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); + netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) diff --git a/net/core/filter.c b/net/core/filter.c index 383f96b0a1c7..7e4d7c3bcc84 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -81,6 +81,7 @@ #include <net/xdp.h> #include <net/mptcp.h> #include <net/netfilter/nf_conntrack_bpf.h> +#include <net/netkit.h> #include <linux/un.h> #include "dev.h" @@ -2468,6 +2469,16 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); +static struct net_device *skb_get_peer_dev(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (likely(ops->ndo_get_peer_dev)) + return INDIRECT_CALL_1(ops->ndo_get_peer_dev, + netkit_peer_dev, dev); + return NULL; +} + int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); @@ -2481,17 +2492,15 @@ int skb_do_redirect(struct sk_buff *skb) if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { - const struct net_device_ops *ops = dev->netdev_ops; - - if (unlikely(!ops->ndo_get_peer_dev || - !skb_at_tc_ingress(skb))) + if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; - dev = ops->ndo_get_peer_dev(dev); + dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; + dev_sw_netstats_rx_add(dev, skb->len); return -EAGAIN; } return flags & BPF_F_NEIGH ? diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 6ee22c3b251a..518f143c5b0f 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -24,6 +24,7 @@ #include "test_progs.h" #include "network_helpers.h" +#include "netlink_helpers.h" #include "test_tc_neigh_fib.skel.h" #include "test_tc_neigh.skel.h" #include "test_tc_peer.skel.h" @@ -110,11 +111,17 @@ static void netns_setup_namespaces_nofail(const char *verb) } } +enum dev_mode { + MODE_VETH, + MODE_NETKIT, +}; + struct netns_setup_result { - int ifindex_veth_src; - int ifindex_veth_src_fwd; - int ifindex_veth_dst; - int ifindex_veth_dst_fwd; + enum dev_mode dev_mode; + int ifindex_src; + int ifindex_src_fwd; + int ifindex_dst; + int ifindex_dst_fwd; }; static int get_ifaddr(const char *name, char *ifaddr) @@ -137,58 +144,110 @@ static int get_ifaddr(const char *name, char *ifaddr) return 0; } +static int create_netkit(int mode, char *prim, char *peer) +{ + struct rtattr *linkinfo, *data, *peer_info; + struct rtnl_handle rth = { .fd = -1 }; + const char *type = "netkit"; + struct { + struct nlmsghdr n; + struct ifinfomsg i; + char buf[1024]; + } req = {}; + int err; + + err = rtnl_open(&rth, 0); + if (!ASSERT_OK(err, "open_rtnetlink")) + return err; + + memset(&req, 0, sizeof(req)); + req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL; + req.n.nlmsg_type = RTM_NEWLINK; + req.i.ifi_family = AF_UNSPEC; + + addattr_l(&req.n, sizeof(req), IFLA_IFNAME, prim, strlen(prim)); + linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO); + addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type)); + data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); + peer_info = addattr_nest(&req.n, sizeof(req), IFLA_NETKIT_PEER_INFO); + req.n.nlmsg_len += sizeof(struct ifinfomsg); + addattr_l(&req.n, sizeof(req), IFLA_IFNAME, peer, strlen(peer)); + addattr_nest_end(&req.n, peer_info); + addattr_nest_end(&req.n, data); + addattr_nest_end(&req.n, linkinfo); + + err = rtnl_talk(&rth, &req.n, NULL); + ASSERT_OK(err, "talk_rtnetlink"); + rtnl_close(&rth); + return err; +} + static int netns_setup_links_and_routes(struct netns_setup_result *result) { struct nstoken *nstoken = NULL; - char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {}; - - SYS(fail, "ip link add veth_src type veth peer name veth_src_fwd"); - SYS(fail, "ip link add veth_dst type veth peer name veth_dst_fwd"); + char src_fwd_addr[IFADDR_STR_LEN+1] = {}; + int err; - SYS(fail, "ip link set veth_dst_fwd address " MAC_DST_FWD); - SYS(fail, "ip link set veth_dst address " MAC_DST); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip link add src type veth peer name src_fwd"); + SYS(fail, "ip link add dst type veth peer name dst_fwd"); + + SYS(fail, "ip link set dst_fwd address " MAC_DST_FWD); + SYS(fail, "ip link set dst address " MAC_DST); + } else if (result->dev_mode == MODE_NETKIT) { + err = create_netkit(NETKIT_L3, "src", "src_fwd"); + if (!ASSERT_OK(err, "create_ifindex_src")) + goto fail; + err = create_netkit(NETKIT_L3, "dst", "dst_fwd"); + if (!ASSERT_OK(err, "create_ifindex_dst")) + goto fail; + } - if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr)) + if (get_ifaddr("src_fwd", src_fwd_addr)) goto fail; - result->ifindex_veth_src = if_nametoindex("veth_src"); - if (!ASSERT_GT(result->ifindex_veth_src, 0, "ifindex_veth_src")) + result->ifindex_src = if_nametoindex("src"); + if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src")) goto fail; - result->ifindex_veth_src_fwd = if_nametoindex("veth_src_fwd"); - if (!ASSERT_GT(result->ifindex_veth_src_fwd, 0, "ifindex_veth_src_fwd")) + result->ifindex_src_fwd = if_nametoindex("src_fwd"); + if (!ASSERT_GT(result->ifindex_src_fwd, 0, "ifindex_src_fwd")) goto fail; - result->ifindex_veth_dst = if_nametoindex("veth_dst"); - if (!ASSERT_GT(result->ifindex_veth_dst, 0, "ifindex_veth_dst")) + result->ifindex_dst = if_nametoindex("dst"); + if (!ASSERT_GT(result->ifindex_dst, 0, "ifindex_dst")) goto fail; - result->ifindex_veth_dst_fwd = if_nametoindex("veth_dst_fwd"); - if (!ASSERT_GT(result->ifindex_veth_dst_fwd, 0, "ifindex_veth_dst_fwd")) + result->ifindex_dst_fwd = if_nametoindex("dst_fwd"); + if (!ASSERT_GT(result->ifindex_dst_fwd, 0, "ifindex_dst_fwd")) goto fail; - SYS(fail, "ip link set veth_src netns " NS_SRC); - SYS(fail, "ip link set veth_src_fwd netns " NS_FWD); - SYS(fail, "ip link set veth_dst_fwd netns " NS_FWD); - SYS(fail, "ip link set veth_dst netns " NS_DST); + SYS(fail, "ip link set src netns " NS_SRC); + SYS(fail, "ip link set src_fwd netns " NS_FWD); + SYS(fail, "ip link set dst_fwd netns " NS_FWD); + SYS(fail, "ip link set dst netns " NS_DST); /** setup in 'src' namespace */ nstoken = open_netns(NS_SRC); if (!ASSERT_OK_PTR(nstoken, "setns src")) goto fail; - SYS(fail, "ip addr add " IP4_SRC "/32 dev veth_src"); - SYS(fail, "ip addr add " IP6_SRC "/128 dev veth_src nodad"); - SYS(fail, "ip link set dev veth_src up"); + SYS(fail, "ip addr add " IP4_SRC "/32 dev src"); + SYS(fail, "ip addr add " IP6_SRC "/128 dev src nodad"); + SYS(fail, "ip link set dev src up"); - SYS(fail, "ip route add " IP4_DST "/32 dev veth_src scope global"); - SYS(fail, "ip route add " IP4_NET "/16 dev veth_src scope global"); - SYS(fail, "ip route add " IP6_DST "/128 dev veth_src scope global"); + SYS(fail, "ip route add " IP4_DST "/32 dev src scope global"); + SYS(fail, "ip route add " IP4_NET "/16 dev src scope global"); + SYS(fail, "ip route add " IP6_DST "/128 dev src scope global"); - SYS(fail, "ip neigh add " IP4_DST " dev veth_src lladdr %s", - veth_src_fwd_addr); - SYS(fail, "ip neigh add " IP6_DST " dev veth_src lladdr %s", - veth_src_fwd_addr); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip neigh add " IP4_DST " dev src lladdr %s", + src_fwd_addr); + SYS(fail, "ip neigh add " IP6_DST " dev src lladdr %s", + src_fwd_addr); + } close_netns(nstoken); @@ -201,15 +260,15 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) * needs v4 one in order to start ARP probing. IP4_NET route is added * to the endpoints so that the ARP processing will reply. */ - SYS(fail, "ip addr add " IP4_SLL "/32 dev veth_src_fwd"); - SYS(fail, "ip addr add " IP4_DLL "/32 dev veth_dst_fwd"); - SYS(fail, "ip link set dev veth_src_fwd up"); - SYS(fail, "ip link set dev veth_dst_fwd up"); + SYS(fail, "ip addr add " IP4_SLL "/32 dev src_fwd"); + SYS(fail, "ip addr add " IP4_DLL "/32 dev dst_fwd"); + SYS(fail, "ip link set dev src_fwd up"); + SYS(fail, "ip link set dev dst_fwd up"); - SYS(fail, "ip route add " IP4_SRC "/32 dev veth_src_fwd scope global"); - SYS(fail, "ip route add " IP6_SRC "/128 dev veth_src_fwd scope global"); - SYS(fail, "ip route add " IP4_DST "/32 dev veth_dst_fwd scope global"); - SYS(fail, "ip route add " IP6_DST "/128 dev veth_dst_fwd scope global"); + SYS(fail, "ip route add " IP4_SRC "/32 dev src_fwd scope global"); + SYS(fail, "ip route add " IP6_SRC "/128 dev src_fwd scope global"); + SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global"); + SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global"); close_netns(nstoken); @@ -218,16 +277,18 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) if (!ASSERT_OK_PTR(nstoken, "setns dst")) goto fail; - SYS(fail, "ip addr add " IP4_DST "/32 dev veth_dst"); - SYS(fail, "ip addr add " IP6_DST "/128 dev veth_dst nodad"); - SYS(fail, "ip link set dev veth_dst up"); + SYS(fail, "ip addr add " IP4_DST "/32 dev dst"); + SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad"); + SYS(fail, "ip link set dev dst up"); - SYS(fail, "ip route add " IP4_SRC "/32 dev veth_dst scope global"); - SYS(fail, "ip route add " IP4_NET "/16 dev veth_dst scope global"); - SYS(fail, "ip route add " IP6_SRC "/128 dev veth_dst scope global"); + SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global"); + SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global"); + SYS(fail, "ip route add " IP6_SRC "/128 dev dst scope global"); - SYS(fail, "ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD); - SYS(fail, "ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip neigh add " IP4_SRC " dev dst lladdr " MAC_DST_FWD); + SYS(fail, "ip neigh add " IP6_SRC " dev dst lladdr " MAC_DST_FWD); + } close_netns(nstoken); @@ -293,23 +354,23 @@ static int netns_load_bpf(const struct bpf_program *src_prog, const struct bpf_program *chk_prog, const struct netns_setup_result *setup_result) { - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd); int err; - /* tc qdisc add dev veth_src_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd); - /* tc filter add dev veth_src_fwd ingress bpf da src_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, src_prog, 0); - /* tc filter add dev veth_src_fwd egress bpf da chk_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, chk_prog, 0); + /* tc qdisc add dev src_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd); + /* tc filter add dev src_fwd ingress bpf da src_prog */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, src_prog, 0); + /* tc filter add dev src_fwd egress bpf da chk_prog */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, chk_prog, 0); - /* tc qdisc add dev veth_dst_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd); - /* tc filter add dev veth_dst_fwd ingress bpf da dst_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, dst_prog, 0); - /* tc filter add dev veth_dst_fwd egress bpf da chk_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, chk_prog, 0); + /* tc qdisc add dev dst_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd); + /* tc filter add dev dst_fwd ingress bpf da dst_prog */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, dst_prog, 0); + /* tc filter add dev dst_fwd egress bpf da chk_prog */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, chk_prog, 0); return 0; fail: @@ -539,10 +600,10 @@ done: static int netns_load_dtime_bpf(struct test_tc_dtime *skel, const struct netns_setup_result *setup_result) { - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst); + LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_src); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst); struct nstoken *nstoken; int err; @@ -550,58 +611,58 @@ static int netns_load_dtime_bpf(struct test_tc_dtime *skel, nstoken = open_netns(NS_SRC); if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) return -1; - /* tc qdisc add dev veth_src clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_src, setup_result->ifindex_veth_src); - /* tc filter add dev veth_src ingress bpf da ingress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0); - /* tc filter add dev veth_src egress bpf da egress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_EGRESS, skel->progs.egress_host, 0); + /* tc qdisc add dev src clsact */ + QDISC_CLSACT_CREATE(&qdisc_src, setup_result->ifindex_src); + /* tc filter add dev src ingress bpf da ingress_host */ + XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0); + /* tc filter add dev src egress bpf da egress_host */ + XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_EGRESS, skel->progs.egress_host, 0); close_netns(nstoken); /* setup ns_dst tc progs */ nstoken = open_netns(NS_DST); if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST)) return -1; - /* tc qdisc add dev veth_dst clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst, setup_result->ifindex_veth_dst); - /* tc filter add dev veth_dst ingress bpf da ingress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0); - /* tc filter add dev veth_dst egress bpf da egress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0); + /* tc qdisc add dev dst clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst, setup_result->ifindex_dst); + /* tc filter add dev dst ingress bpf da ingress_host */ + XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0); + /* tc filter add dev dst egress bpf da egress_host */ + XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0); close_netns(nstoken); /* setup ns_fwd tc progs */ nstoken = open_netns(NS_FWD); if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) return -1; - /* tc qdisc add dev veth_dst_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd); - /* tc filter add dev veth_dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, + /* tc qdisc add dev dst_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd); + /* tc filter add dev dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio100, 100); - /* tc filter add dev veth_dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, + /* tc filter add dev dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio101, 101); - /* tc filter add dev veth_dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, + /* tc filter add dev dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio100, 100); - /* tc filter add dev veth_dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, + /* tc filter add dev dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio101, 101); - /* tc qdisc add dev veth_src_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd); - /* tc filter add dev veth_src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, + /* tc qdisc add dev src_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd); + /* tc filter add dev src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio100, 100); - /* tc filter add dev veth_src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, + /* tc filter add dev src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio101, 101); - /* tc filter add dev veth_src_fwd egress prio 100 bpf da egress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, + /* tc filter add dev src_fwd egress prio 100 bpf da egress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio100, 100); - /* tc filter add dev veth_src_fwd egress prio 101 bpf da egress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, + /* tc filter add dev src_fwd egress prio 101 bpf da egress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio101, 101); close_netns(nstoken); return 0; @@ -777,8 +838,8 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open")) return; - skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_dtime__load(skel); if (!ASSERT_OK(err, "test_tc_dtime__load")) @@ -868,8 +929,8 @@ static void test_tc_redirect_neigh(struct netns_setup_result *setup_result) if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open")) goto done; - skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_neigh__load(skel); if (!ASSERT_OK(err, "test_tc_neigh__load")) @@ -904,8 +965,8 @@ static void test_tc_redirect_peer(struct netns_setup_result *setup_result) if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) goto done; - skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_peer__load(skel); if (!ASSERT_OK(err, "test_tc_peer__load")) @@ -996,7 +1057,7 @@ static int tun_relay_loop(int src_fd, int target_fd) static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) { LIBBPF_OPTS(bpf_tc_hook, qdisc_tun_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd); struct test_tc_peer *skel = NULL; struct nstoken *nstoken = NULL; int err; @@ -1045,7 +1106,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) goto fail; skel->rodata->IFINDEX_SRC = ifindex; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_peer__load(skel); if (!ASSERT_OK(err, "test_tc_peer__load")) @@ -1053,19 +1114,19 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) /* Load "tc_src_l3" to the tun_fwd interface to redirect packets * towards dst, and "tc_dst" to redirect packets - * and "tc_chk" on veth_dst_fwd to drop non-redirected packets. + * and "tc_chk" on dst_fwd to drop non-redirected packets. */ /* tc qdisc add dev tun_fwd clsact */ QDISC_CLSACT_CREATE(&qdisc_tun_fwd, ifindex); /* tc filter add dev tun_fwd ingress bpf da tc_src_l3 */ XGRESS_FILTER_ADD(&qdisc_tun_fwd, BPF_TC_INGRESS, skel->progs.tc_src_l3, 0); - /* tc qdisc add dev veth_dst_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd); - /* tc filter add dev veth_dst_fwd ingress bpf da tc_dst_l3 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0); - /* tc filter add dev veth_dst_fwd egress bpf da tc_chk */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0); + /* tc qdisc add dev dst_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd); + /* tc filter add dev dst_fwd ingress bpf da tc_dst_l3 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0); + /* tc filter add dev dst_fwd egress bpf da tc_chk */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0); /* Setup route and neigh tables */ SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24"); @@ -1074,17 +1135,17 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad"); SYS(fail, "ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad"); - SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global"); + SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev src scope global"); SYS(fail, "ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD " dev tun_src scope global"); - SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global"); - SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global"); + SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev dst scope global"); + SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev src scope global"); SYS(fail, "ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD " dev tun_src scope global"); - SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global"); + SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev dst scope global"); - SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); - SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev dst lladdr " MAC_DST_FWD); + SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev dst lladdr " MAC_DST_FWD); if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) goto fail; @@ -1106,9 +1167,9 @@ fail: close_netns(nstoken); } -#define RUN_TEST(name) \ +#define RUN_TEST(name, mode) \ ({ \ - struct netns_setup_result setup_result; \ + struct netns_setup_result setup_result = { .dev_mode = mode, }; \ if (test__start_subtest(#name)) \ if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \ if (ASSERT_OK(netns_setup_links_and_routes(&setup_result), \ @@ -1122,11 +1183,13 @@ static void *test_tc_redirect_run_tests(void *arg) { netns_setup_namespaces_nofail("delete"); - RUN_TEST(tc_redirect_peer); - RUN_TEST(tc_redirect_peer_l3); - RUN_TEST(tc_redirect_neigh); - RUN_TEST(tc_redirect_neigh_fib); - RUN_TEST(tc_redirect_dtime); + RUN_TEST(tc_redirect_peer, MODE_VETH); + RUN_TEST(tc_redirect_peer, MODE_NETKIT); + RUN_TEST(tc_redirect_peer_l3, MODE_VETH); + RUN_TEST(tc_redirect_peer_l3, MODE_NETKIT); + RUN_TEST(tc_redirect_neigh, MODE_VETH); + RUN_TEST(tc_redirect_neigh_fib, MODE_VETH); + RUN_TEST(tc_redirect_dtime, MODE_VETH); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index e5c61aa6604a..5cfa7a6316b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -31,6 +31,7 @@ #include "verifier_helper_restricted.skel.h" #include "verifier_helper_value_access.skel.h" #include "verifier_int_ptr.skel.h" +#include "verifier_iterating_callbacks.skel.h" #include "verifier_jeq_infer_not_null.skel.h" #include "verifier_ld_ind.skel.h" #include "verifier_ldsx.skel.h" @@ -139,6 +140,7 @@ void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_acces void test_verifier_helper_restricted(void) { RUN(verifier_helper_restricted); } void test_verifier_helper_value_access(void) { RUN(verifier_helper_value_access); } void test_verifier_int_ptr(void) { RUN(verifier_int_ptr); } +void test_verifier_iterating_callbacks(void) { RUN(verifier_iterating_callbacks); } void test_verifier_jeq_infer_not_null(void) { RUN(verifier_jeq_infer_not_null); } void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } void test_verifier_ldsx(void) { RUN(verifier_ldsx); } diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c index 4ce76eb064c4..d461746fd3c1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -15,13 +15,16 @@ static int empty_callback(__u32 index, void *data) return 0; } +static int outer_loop(__u32 index, void *data) +{ + bpf_loop(nr_loops, empty_callback, NULL, 0); + __sync_add_and_fetch(&hits, nr_loops); + return 0; +} + SEC("fentry/" SYS_PREFIX "sys_getpgid") int benchmark(void *ctx) { - for (int i = 0; i < 1000; i++) { - bpf_loop(nr_loops, empty_callback, NULL, 0); - - __sync_add_and_fetch(&hits, nr_loops); - } + bpf_loop(1000, outer_loop, NULL, 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 76d661b20e87..56c764df8196 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -33,6 +33,7 @@ int underflow_prog(void *ctx) if (!p) return 0; bpf_for_each_map_elem(&array_map, cb1, &p, 0); + bpf_kfunc_call_test_release(p); return 0; } diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c index 4c39e920dac2..8c0ef2742208 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_fail.c +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -171,6 +171,7 @@ int reject_with_rbtree_add_throw(void *ctx) return 0; bpf_spin_lock(&lock); bpf_rbtree_add(&rbtree, &f->node, rbless); + bpf_spin_unlock(&lock); return 0; } @@ -214,6 +215,7 @@ int reject_with_cb_reference(void *ctx) if (!f) return 0; bpf_loop(5, subprog_cb_ref, NULL, 0); + bpf_obj_drop(f); return 0; } diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index e02cfd380746..40df2cc26eaf 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -24,9 +24,11 @@ struct task_struct {}; #define STACK_TABLE_EPOCH_SHIFT 20 #define STROBE_MAX_STR_LEN 1 #define STROBE_MAX_CFGS 32 +#define READ_MAP_VAR_PAYLOAD_CAP \ + ((1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) #define STROBE_MAX_PAYLOAD \ (STROBE_MAX_STRS * STROBE_MAX_STR_LEN + \ - STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) + STROBE_MAX_MAPS * READ_MAP_VAR_PAYLOAD_CAP) struct strobe_value_header { /* @@ -355,7 +357,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, struct strobe_value_generic *value, struct strobemeta_payload *data, - void *payload) + size_t off) { void *location; uint64_t len; @@ -366,7 +368,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, return 0; bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, value->ptr); + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr); /* * if bpf_probe_read_user_str returns error (<0), due to casting to * unsinged int, it will become big number, so next check is @@ -378,14 +380,14 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, return 0; data->str_lens[idx] = len; - return len; + return off + len; } -static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, - size_t idx, void *tls_base, - struct strobe_value_generic *value, - struct strobemeta_payload *data, - void *payload) +static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, + size_t off) { struct strobe_map_descr* descr = &data->map_descrs[idx]; struct strobe_map_raw map; @@ -397,11 +399,11 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, location = calc_location(&cfg->map_locs[idx], tls_base); if (!location) - return payload; + return off; bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr)) - return payload; + return off; descr->id = map.id; descr->cnt = map.cnt; @@ -410,10 +412,10 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, data->req_meta_valid = 1; } - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag); + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.tag); if (len <= STROBE_MAX_STR_LEN) { descr->tag_len = len; - payload += len; + off += len; } #ifdef NO_UNROLL @@ -426,22 +428,22 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, break; descr->key_lens[i] = 0; - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.entries[i].key); if (len <= STROBE_MAX_STR_LEN) { descr->key_lens[i] = len; - payload += len; + off += len; } descr->val_lens[i] = 0; - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.entries[i].val); if (len <= STROBE_MAX_STR_LEN) { descr->val_lens[i] = len; - payload += len; + off += len; } } - return payload; + return off; } #ifdef USE_BPF_LOOP @@ -455,14 +457,20 @@ struct read_var_ctx { struct strobemeta_payload *data; void *tls_base; struct strobemeta_cfg *cfg; - void *payload; + size_t payload_off; /* value gets mutated */ struct strobe_value_generic *value; enum read_type type; }; -static int read_var_callback(__u32 index, struct read_var_ctx *ctx) +static int read_var_callback(__u64 index, struct read_var_ctx *ctx) { + /* lose precision info for ctx->payload_off, verifier won't track + * double xor, barrier_var() is needed to force clang keep both xors. + */ + ctx->payload_off ^= index; + barrier_var(ctx->payload_off); + ctx->payload_off ^= index; switch (ctx->type) { case READ_INT_VAR: if (index >= STROBE_MAX_INTS) @@ -472,14 +480,18 @@ static int read_var_callback(__u32 index, struct read_var_ctx *ctx) case READ_MAP_VAR: if (index >= STROBE_MAX_MAPS) return 1; - ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base, - ctx->value, ctx->data, ctx->payload); + if (ctx->payload_off > sizeof(ctx->data->payload) - READ_MAP_VAR_PAYLOAD_CAP) + return 1; + ctx->payload_off = read_map_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload_off); break; case READ_STR_VAR: if (index >= STROBE_MAX_STRS) return 1; - ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base, - ctx->value, ctx->data, ctx->payload); + if (ctx->payload_off > sizeof(ctx->data->payload) - STROBE_MAX_STR_LEN) + return 1; + ctx->payload_off = read_str_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload_off); break; } return 0; @@ -501,7 +513,8 @@ static void *read_strobe_meta(struct task_struct *task, pid_t pid = bpf_get_current_pid_tgid() >> 32; struct strobe_value_generic value = {0}; struct strobemeta_cfg *cfg; - void *tls_base, *payload; + size_t payload_off; + void *tls_base; cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid); if (!cfg) @@ -509,7 +522,7 @@ static void *read_strobe_meta(struct task_struct *task, data->int_vals_set_mask = 0; data->req_meta_valid = 0; - payload = data->payload; + payload_off = 0; /* * we don't have struct task_struct definition, it should be: * tls_base = (void *)task->thread.fsbase; @@ -522,7 +535,7 @@ static void *read_strobe_meta(struct task_struct *task, .tls_base = tls_base, .value = &value, .data = data, - .payload = payload, + .payload_off = 0, }; int err; @@ -540,6 +553,11 @@ static void *read_strobe_meta(struct task_struct *task, err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0); if (err != STROBE_MAX_MAPS) return NULL; + + payload_off = ctx.payload_off; + /* this should not really happen, here only to satisfy verifer */ + if (payload_off > sizeof(data->payload)) + payload_off = sizeof(data->payload); #else #ifdef NO_UNROLL #pragma clang loop unroll(disable) @@ -555,7 +573,7 @@ static void *read_strobe_meta(struct task_struct *task, #pragma unroll #endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_STRS; ++i) { - payload += read_str_var(cfg, i, tls_base, &value, data, payload); + payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off); } #ifdef NO_UNROLL #pragma clang loop unroll(disable) @@ -563,7 +581,7 @@ static void *read_strobe_meta(struct task_struct *task, #pragma unroll #endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_MAPS; ++i) { - payload = read_map_var(cfg, i, tls_base, &value, data, payload); + payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off); } #endif /* USE_BPF_LOOP */ @@ -571,7 +589,7 @@ static void *read_strobe_meta(struct task_struct *task, * return pointer right after end of payload, so it's possible to * calculate exact amount of useful data that needs to be sent */ - return payload; + return &data->payload[payload_off]; } SEC("raw_tracepoint/kfree_skb") diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c new file mode 100644 index 000000000000..5905e036e0ea --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_USER_RINGBUF); + __uint(max_entries, 8); +} ringbuf SEC(".maps"); + +struct vm_area_struct; +struct bpf_map; + +struct buf_context { + char *buf; +}; + +struct num_context { + __u64 i; + __u64 j; +}; + +__u8 choice_arr[2] = { 0, 1 }; + +static int unsafe_on_2nd_iter_cb(__u32 idx, struct buf_context *ctx) +{ + if (idx == 0) { + ctx->buf = (char *)(0xDEAD); + return 0; + } + + if (bpf_probe_read_user(ctx->buf, 8, (void *)(0xBADC0FFEE))) + return 1; + + return 0; +} + +SEC("?raw_tp") +__failure __msg("R1 type=scalar expected=fp") +int unsafe_on_2nd_iter(void *unused) +{ + char buf[4]; + struct buf_context loop_ctx = { .buf = buf }; + + bpf_loop(100, unsafe_on_2nd_iter_cb, &loop_ctx, 0); + return 0; +} + +static int unsafe_on_zero_iter_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i = 0; + return 0; +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_on_zero_iter(void *unused) +{ + struct num_context loop_ctx = { .i = 32 }; + + bpf_loop(100, unsafe_on_zero_iter_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static int widening_cb(__u32 idx, struct num_context *ctx) +{ + ++ctx->i; + return 0; +} + +SEC("?raw_tp") +__success +int widening(void *unused) +{ + struct num_context loop_ctx = { .i = 0, .j = 1 }; + + bpf_loop(100, widening_cb, &loop_ctx, 0); + /* loop_ctx.j is not changed during callback iteration, + * verifier should not apply widening to it. + */ + return choice_arr[loop_ctx.j]; +} + +static int loop_detection_cb(__u32 idx, struct num_context *ctx) +{ + for (;;) {} + return 0; +} + +SEC("?raw_tp") +__failure __msg("infinite loop detected") +int loop_detection(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_loop(100, loop_detection_cb, &loop_ctx, 0); + return 0; +} + +static __always_inline __u64 oob_state_machine(struct num_context *ctx) +{ + switch (ctx->i) { + case 0: + ctx->i = 1; + break; + case 1: + ctx->i = 32; + break; + } + return 0; +} + +static __u64 for_each_map_elem_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_for_each_map_elem(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_for_each_map_elem(&map, for_each_map_elem_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static __u64 ringbuf_drain_cb(struct bpf_dynptr *dynptr, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_ringbuf_drain(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_user_ringbuf_drain(&ringbuf, ringbuf_drain_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static __u64 find_vma_cb(struct task_struct *task, struct vm_area_struct *vma, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_find_vma(void *unused) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct num_context loop_ctx = { .i = 0 }; + + bpf_find_vma(task, 0, find_vma_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static int iter_limit_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i++; + return 0; +} + +SEC("?raw_tp") +__success +int bpf_loop_iter_limit_ok(void *unused) +{ + struct num_context ctx = { .i = 0 }; + + bpf_loop(1, iter_limit_cb, &ctx, 0); + return choice_arr[ctx.i]; +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=2 size=1") +int bpf_loop_iter_limit_overflow(void *unused) +{ + struct num_context ctx = { .i = 0 }; + + bpf_loop(2, iter_limit_cb, &ctx, 0); + return choice_arr[ctx.i]; +} + +static int iter_limit_level2a_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 100; + return 0; +} + +static int iter_limit_level2b_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 10; + return 0; +} + +static int iter_limit_level1_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 1; + bpf_loop(1, iter_limit_level2a_cb, ctx, 0); + bpf_loop(1, iter_limit_level2b_cb, ctx, 0); + return 0; +} + +/* Check that path visiting every callback function once had been + * reached by verifier. Variables 'ctx{1,2}i' below serve as flags, + * with each decimal digit corresponding to a callback visit marker. + */ +SEC("socket") +__success __retval(111111) +int bpf_loop_iter_limit_nested(void *unused) +{ + struct num_context ctx1 = { .i = 0 }; + struct num_context ctx2 = { .i = 0 }; + __u64 a, b, c; + + bpf_loop(1, iter_limit_level1_cb, &ctx1, 0); + bpf_loop(1, iter_limit_level1_cb, &ctx2, 0); + a = ctx1.i; + b = ctx2.i; + /* Force 'ctx1.i' and 'ctx2.i' precise. */ + c = choice_arr[(a + b) % 2]; + /* This makes 'c' zero, but neither clang nor verifier know it. */ + c /= 10; + /* Make sure that verifier does not visit 'impossible' states: + * enumerate all possible callback visit masks. + */ + if (a != 0 && a != 1 && a != 11 && a != 101 && a != 111 && + b != 0 && b != 1 && b != 11 && b != 101 && b != 111) + asm volatile ("r0 /= 0;" ::: "r0"); + return 1000 * a + b + c; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index db6b3143338b..f61d623b1ce8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -119,15 +119,41 @@ __naked int global_subprog_result_precise(void) SEC("?raw_tp") __success __log_level(2) +/* First simulated path does not include callback body, + * r1 and r4 are always precise for bpf_loop() calls. + */ +__msg("9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: parent state regs=r4 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r4 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: parent state regs=r1 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r1 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r1 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r1 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r1 stack= before 5: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* r6 precision propagation */ __msg("14: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: last_idx 14 first_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") __msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") -__msg("mark_precise: frame0: parent state regs=r0 stack=:") -__msg("mark_precise: frame0: last_idx 18 first_idx 0") -__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit") +__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop") +/* State entering callback body popped from states stack */ +__msg("from 9 to 17: frame1:") +__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("17: (b7) r0 = 0") +__msg("18: (95) exit") +__msg("returning from callee:") +__msg("to caller at 9:") +__msg("frame 0: propagating r1,r4") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit") +__msg("from 18 to 9: safe") __naked int callback_result_precise(void) { asm volatile ( @@ -233,20 +259,36 @@ __naked int parent_callee_saved_reg_precise_global(void) SEC("?raw_tp") __success __log_level(2) +/* First simulated path does not include callback body */ __msg("12: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 12 first_idx 10") +__msg("mark_precise: frame0: last_idx 12 first_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 9: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs=r6 stack=:") -__msg("mark_precise: frame0: last_idx 16 first_idx 0") -__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit") -__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") -__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") __msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") __msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") __msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* State entering callback body popped from states stack */ +__msg("from 9 to 15: frame1:") +__msg("15: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("15: (b7) r0 = 0") +__msg("16: (95) exit") +__msg("returning from callee:") +__msg("to caller at 9:") +/* r1, r4 are always precise for bpf_loop(), + * r6 was marked before backtracking to callback body. + */ +__msg("frame 0: propagating r1,r4,r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop") +__msg("mark_precise: frame0: parent state regs= stack=:") +__msg("from 16 to 9: safe") __naked int parent_callee_saved_reg_precise_with_callback(void) { asm volatile ( @@ -373,22 +415,38 @@ __naked int parent_stack_slot_precise_global(void) SEC("?raw_tp") __success __log_level(2) +/* First simulated path does not include callback body */ __msg("14: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 14 first_idx 11") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-8 before 10: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs= stack=-8:") -__msg("mark_precise: frame0: last_idx 18 first_idx 0") -__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") -__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") -__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 9 first_idx 0 subseq_idx 10") __msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") __msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") __msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") __msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") __msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* State entering callback body popped from states stack */ +__msg("from 10 to 17: frame1:") +__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("17: (b7) r0 = 0") +__msg("18: (95) exit") +__msg("returning from callee:") +__msg("to caller at 10:") +/* r1, r4 are always precise for bpf_loop(), + * fp-8 was marked before backtracking to callback body. + */ +__msg("frame 0: propagating r1,r4,fp-8") +__msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: parent state regs= stack=:") +__msg("from 18 to 10: safe") __naked int parent_stack_slot_precise_with_callback(void) { asm volatile ( diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index e959336c7a73..80f620602d50 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -53,6 +53,8 @@ #define DEFAULT_TTL 64 #define MAX_ALLOWED_PORTS 8 +#define MAX_PACKET_OFF 0xffff + #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) @@ -183,63 +185,76 @@ static __always_inline __u32 tcp_clock_ms(void) } struct tcpopt_context { - __u8 *ptr; - __u8 *end; + void *data; void *data_end; __be32 *tsecr; __u8 wscale; bool option_timestamp; bool option_sack; + __u32 off; }; -static int tscookie_tcpopt_parse(struct tcpopt_context *ctx) +static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz) { - __u8 opcode, opsize; + __u64 off = ctx->off; + __u8 *data; - if (ctx->ptr >= ctx->end) - return 1; - if (ctx->ptr >= ctx->data_end) - return 1; + /* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */ + if (off > MAX_PACKET_OFF - sz) + return NULL; - opcode = ctx->ptr[0]; + data = ctx->data + off; + barrier_var(data); + if (data + sz >= ctx->data_end) + return NULL; - if (opcode == TCPOPT_EOL) - return 1; - if (opcode == TCPOPT_NOP) { - ++ctx->ptr; - return 0; - } + ctx->off += sz; + return data; +} - if (ctx->ptr + 1 >= ctx->end) - return 1; - if (ctx->ptr + 1 >= ctx->data_end) +static int tscookie_tcpopt_parse(struct tcpopt_context *ctx) +{ + __u8 *opcode, *opsize, *wscale, *tsecr; + __u32 off = ctx->off; + + opcode = next(ctx, 1); + if (!opcode) return 1; - opsize = ctx->ptr[1]; - if (opsize < 2) + + if (*opcode == TCPOPT_EOL) return 1; + if (*opcode == TCPOPT_NOP) + return 0; - if (ctx->ptr + opsize > ctx->end) + opsize = next(ctx, 1); + if (!opsize || *opsize < 2) return 1; - switch (opcode) { + switch (*opcode) { case TCPOPT_WINDOW: - if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end) - ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE; + wscale = next(ctx, 1); + if (!wscale) + return 1; + if (*opsize == TCPOLEN_WINDOW) + ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE; break; case TCPOPT_TIMESTAMP: - if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) { + tsecr = next(ctx, 4); + if (!tsecr) + return 1; + if (*opsize == TCPOLEN_TIMESTAMP) { ctx->option_timestamp = true; /* Client's tsval becomes our tsecr. */ - *ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2)); + *ctx->tsecr = get_unaligned((__be32 *)tsecr); } break; case TCPOPT_SACK_PERM: - if (opsize == TCPOLEN_SACK_PERM) + if (*opsize == TCPOLEN_SACK_PERM) ctx->option_sack = true; break; } - ctx->ptr += opsize; + ctx->off = off + *opsize; return 0; } @@ -256,16 +271,21 @@ static int tscookie_tcpopt_parse_batch(__u32 index, void *context) static __always_inline bool tscookie_init(struct tcphdr *tcp_header, __u16 tcp_len, __be32 *tsval, - __be32 *tsecr, void *data_end) + __be32 *tsecr, void *data, void *data_end) { struct tcpopt_context loop_ctx = { - .ptr = (__u8 *)(tcp_header + 1), - .end = (__u8 *)tcp_header + tcp_len, + .data = data, .data_end = data_end, .tsecr = tsecr, .wscale = TS_OPT_WSCALE_MASK, .option_timestamp = false, .option_sack = false, + /* Note: currently verifier would track .off as unbound scalar. + * In case if verifier would at some point get smarter and + * compute bounded value for this var, beware that it might + * hinder bpf_loop() convergence validation. + */ + .off = (__u8 *)(tcp_header + 1) - (__u8 *)data, }; u32 cookie; @@ -635,7 +655,7 @@ static __always_inline int syncookie_handle_syn(struct header_pointers *hdr, cookie = (__u32)value; if (tscookie_init((void *)hdr->tcp, hdr->tcp_len, - &tsopt_buf[0], &tsopt_buf[1], data_end)) + &tsopt_buf[0], &tsopt_buf[1], data, data_end)) tsopt = tsopt_buf; /* Check that there is enough space for a SYNACK. It also covers |