From 710910e564d30fe918d6c7a3af144d6753564ee7 Mon Sep 17 00:00:00 2001 From: Nicolas Rybowski Date: Thu, 28 Jan 2021 06:43:37 +0000 Subject: [PATCH] bpf: expose is_mptcp flag to bpf_tcp_sock is_mptcp is a field from struct tcp_sock used to indicate that the current tcp_sock is part of the MPTCP protocol. In this protocol, a first socket (mptcp_sock) is created with sk_protocol set to IPPROTO_MPTCP (=262) for control purpose but it isn't directly on the wire. This is the role of the subflow (kernel) sockets which are classical tcp_sock with sk_protocol set to IPPROTO_TCP. The only way to differentiate such sockets from plain TCP sockets is the is_mptcp field from tcp_sock. Such an exposure in BPF is thus required to be able to differentiate plain TCP sockets from MPTCP subflow sockets in BPF_PROG_TYPE_SOCK_OPS programs. The choice has been made to silently pass the case when CONFIG_MPTCP is unset by defaulting is_mptcp to 0 in order to make BPF independent of the MPTCP configuration. Another solution is to make the verifier fail in 'bpf_tcp_sock_is_valid_ctx_access' but this will add an additional '#ifdef CONFIG_MPTCP' in the BPF code and a same injected BPF program will not run if MPTCP is not set. An example use-case is provided in https://github.com/multipath-tcp/mptcp_net-next/tree/scripts/bpf/examples Suggested-by: Matthieu Baerts Acked-by: Matthieu Baerts Acked-by: Mat Martineau Signed-off-by: Nicolas Rybowski --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 9 ++++++++- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c001766adcbc5..5d07a58a8a49b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4336,6 +4336,7 @@ struct bpf_tcp_sock { __u32 delivered; /* Total data packets delivered incl. rexmits */ __u32 delivered_ce; /* Like the above but only ECE marked packets */ __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ + __u32 is_mptcp; /* Is MPTCP subflow? */ }; struct bpf_sock_tuple { diff --git a/net/core/filter.c b/net/core/filter.c index 9ab94e90d6605..74cd7c17e6bd8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6249,7 +6249,7 @@ bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, - icsk_retransmits)) + is_mptcp)) return false; if (off % size != 0) @@ -6383,6 +6383,13 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_tcp_sock, icsk_retransmits): BPF_INET_SOCK_GET_COMMON(icsk_retransmits); break; + case offsetof(struct bpf_tcp_sock, is_mptcp): +#ifdef CONFIG_MPTCP + BPF_TCP_SOCK_GET_COMMON(is_mptcp); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; } return insn - insn_buf; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c001766adcbc5..5d07a58a8a49b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4336,6 +4336,7 @@ struct bpf_tcp_sock { __u32 delivered; /* Total data packets delivered incl. rexmits */ __u32 delivered_ce; /* Like the above but only ECE marked packets */ __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ + __u32 is_mptcp; /* Is MPTCP subflow? */ }; struct bpf_sock_tuple {