diff options
author | Alexei Starovoitov <ast@kernel.org> | 2020-10-11 10:21:05 -0700 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2020-10-11 10:21:05 -0700 |
commit | 673e3752456180de804cf4f43de26ef1d6b90a1b (patch) | |
tree | c6559345e3b01dbd0ab5a39bad0e73ec1bb5b263 /net | |
parent | ac53a0d3107c6582b690a8ab348bd637dbd0883f (diff) | |
parent | 9f4c53ca23a28c891d2bd3ff4738f7d95ba0303b (diff) | |
download | linux-673e3752456180de804cf4f43de26ef1d6b90a1b.tar.bz2 |
Merge branch 'Follow-up BPF helper improvements'
Daniel Borkmann says:
====================
This series addresses most of the feedback [0] that was to be followed
up from the last series, that is, UAPI helper comment improvements and
getting rid of the ifindex obj file hacks in the selftest by using a
BPF map instead. The __sk_buff data/data_end pointer work, I'm planning
to do in a later round as well as the mem*() BPF improvements we have
in Cilium for libbpf. Next, the series adds two features, i) a helper
called redirect_peer() to improve latency on netns switch, and ii) to
allow map in map with dynamic inner array map sizes. Selftests for each
are added as well. For details, please check individual patches, thanks!
[0] https://lore.kernel.org/bpf/cover.1601477936.git.daniel@iogearbox.net/
v5 -> v6:
- Going with Andrii's suggestion to make the misconfigured verifier
test more robust, and only probe on -EOPNOTSUPP (Andrii)
v4 -> v5:
- Replace cnt == -EOPNOTSUPP check with cnt < 0; I've used < 0
here as I think it's useful to keep the existing cnt == 0 ||
cnt >= ARRAY_SIZE(insn_buf) for error detection (Andrii)
v3 -> v4:
- Rename new array map flag to BPF_F_INNER_MAP (Alexei)
v2 -> v3:
- Remove tab that slipped into uapi helper desc (Jakub)
- Rework map in map for array to error from map_gen_lookup (Andrii)
v1 -> v2:
- Fixed selftest comment wrt inner1/inner2 value (Yonghong)
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'net')
-rw-r--r-- | net/core/dev.c | 15 | ||||
-rw-r--r-- | net/core/filter.c | 54 | ||||
-rw-r--r-- | net/xdp/xskmap.c | 2 |
3 files changed, 60 insertions, 11 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 9d55bf5d1a65..7dd015823593 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4930,7 +4930,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); static inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) + struct net_device *orig_dev, bool *another) { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); @@ -4974,7 +4974,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, * redirecting to another netdev */ __skb_push(skb, skb->mac_len); - skb_do_redirect(skb); + if (skb_do_redirect(skb) == -EAGAIN) { + __skb_pull(skb, skb->mac_len); + *another = true; + break; + } return NULL; case TC_ACT_CONSUMED: return NULL; @@ -5163,7 +5167,12 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { - skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); + bool another = false; + + skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, + &another); + if (another) + goto another_round; if (!skb) goto out; diff --git a/net/core/filter.c b/net/core/filter.c index 5da44b11e1ec..fab951c6be57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2380,8 +2380,9 @@ out: /* Internal, non-exposed redirect flags. */ enum { - BPF_F_NEIGH = (1ULL << 1), -#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH) + BPF_F_NEIGH = (1ULL << 1), + BPF_F_PEER = (1ULL << 2), +#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER) }; BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) @@ -2430,19 +2431,35 @@ EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; - dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index); + dev = dev_get_by_index_rcu(net, ri->tgt_index); ri->tgt_index = 0; - if (unlikely(!dev)) { - kfree_skb(skb); - return -EINVAL; + ri->flags = 0; + 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))) + goto out_drop; + dev = ops->ndo_get_peer_dev(dev); + if (unlikely(!dev || + !is_skb_forwardable(dev, skb) || + net_eq(net, dev_net(dev)))) + goto out_drop; + skb->dev = dev; + return -EAGAIN; } - return flags & BPF_F_NEIGH ? __bpf_redirect_neigh(skb, dev) : __bpf_redirect(skb, dev, flags); +out_drop: + kfree_skb(skb); + return -EINVAL; } BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) @@ -2466,6 +2483,27 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + if (unlikely(flags)) + return TC_ACT_SHOT; + + ri->flags = BPF_F_PEER; + ri->tgt_index = ifindex; + + return TC_ACT_REDIRECT; +} + +static const struct bpf_func_proto bpf_redirect_peer_proto = { + .func = bpf_redirect_peer, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); @@ -7053,6 +7091,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_redirect_proto; case BPF_FUNC_redirect_neigh: return &bpf_redirect_neigh_proto; + case BPF_FUNC_redirect_peer: + return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 0c5df593bc56..49da2b8ace8b 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -132,7 +132,7 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2; struct bpf_insn *insn = insn_buf; |