diff options
author | brakmo <brakmo@fb.com> | 2019-03-01 12:38:46 -0800 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2019-03-02 10:48:27 -0800 |
commit | f7c917ba11a67632a8452ea99fe132f626a7a2cc (patch) | |
tree | 6fd6f53d18bace334814e47970875eeea4ded599 /net/core | |
parent | b74e21ab7d438117a10d2d331bdfc275fcab2970 (diff) | |
download | linux-stable-f7c917ba11a67632a8452ea99fe132f626a7a2cc.tar.gz linux-stable-f7c917ba11a67632a8452ea99fe132f626a7a2cc.tar.bz2 linux-stable-f7c917ba11a67632a8452ea99fe132f626a7a2cc.zip |
bpf: add bpf helper bpf_skb_ecn_set_ce
This patch adds a new bpf helper BPF_FUNC_skb_ecn_set_ce
"int bpf_skb_ecn_set_ce(struct sk_buff *skb)". It is added to
BPF_PROG_TYPE_CGROUP_SKB typed bpf_prog which currently can
be attached to the ingress and egress path. The helper is needed
because his type of bpf_prog cannot modify the skb directly.
This helper is used to set the ECN field of ECN capable IP packets to ce
(congestion encountered) in the IPv6 or IPv4 header of the skb. It can be
used by a bpf_prog to manage egress or ingress network bandwdith limit
per cgroupv2 by inducing an ECN response in the TCP sender.
This works best when using DCTCP.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/filter.c | 28 |
1 files changed, 28 insertions, 0 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index 85749f6ec789..558ca72f2254 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5426,6 +5426,32 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = { .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; +BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) +{ + unsigned int iphdr_len; + + if (skb->protocol == cpu_to_be16(ETH_P_IP)) + iphdr_len = sizeof(struct iphdr); + else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) + iphdr_len = sizeof(struct ipv6hdr); + else + return 0; + + if (skb_headlen(skb) < iphdr_len) + return 0; + + if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len)) + return 0; + + return INET_ECN_set_ce(skb); +} + +static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { + .func = bpf_skb_ecn_set_ce, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -5585,6 +5611,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; + case BPF_FUNC_skb_ecn_set_ce: + return &bpf_skb_ecn_set_ce_proto; #endif default: return sk_filter_func_proto(func_id, prog); |