From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lawrence Brakmo Subject: [PATCH bpf-next v4 08/11] bpf: Add sock_ops R/W access to tclass & sk_txhash Date: Thu, 4 Jan 2018 15:55:30 -0800 Message-ID: <20180104235533.3672006-9-brakmo@fb.com> References: <20180104235533.3672006-1-brakmo@fb.com> Mime-Version: 1.0 Content-Type: text/plain Cc: Kernel Team , Blake Matheny , Alexei Starovoitov , Daniel Borkmann , Eric Dumazet , Neal Cardwell , Yuchung Cheng To: netdev Return-path: Received: from mx0a-00082601.pphosted.com ([67.231.145.42]:38244 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751208AbeADXzi (ORCPT ); Thu, 4 Jan 2018 18:55:38 -0500 Received: from pps.filterd (m0044012.ppops.net [127.0.0.1]) by mx0a-00082601.pphosted.com (8.16.0.21/8.16.0.21) with SMTP id w04NtJ8S010401 for ; Thu, 4 Jan 2018 15:55:38 -0800 Received: from mail.thefacebook.com ([199.201.64.23]) by mx0a-00082601.pphosted.com with ESMTP id 2f9wg5r400-6 (version=TLSv1 cipher=ECDHE-RSA-AES256-SHA bits=256 verify=NOT) for ; Thu, 04 Jan 2018 15:55:38 -0800 In-Reply-To: <20180104235533.3672006-1-brakmo@fb.com> Sender: netdev-owner@vger.kernel.org List-ID: Adds direct R/W access to sk_txhash and access to tclass for ipv6 flows through getsockopt and setsockopt. Sample usage for tclass: bpf_getsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, sizeof(v)) where skops is a pointer to the ctx (struct bpf_sock_ops). Signed-off-by: Lawrence Brakmo --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 48 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a8f4cf0..df1e73e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -982,6 +982,7 @@ struct bpf_sock_ops { __u32 data_segs_out; __u64 bytes_received; __u64 bytes_acked; + __u32 sk_txhash; }; /* List of known BPF sock_ops operators. diff --git a/net/core/filter.c b/net/core/filter.c index d4c5c1a..4d2ff88 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3230,6 +3230,29 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, ret = -EINVAL; } #ifdef CONFIG_INET +#if IS_ENABLED(CONFIG_IPV6) + } else if (level == SOL_IPV6) { + if (optlen != sizeof(int) || sk->sk_family != AF_INET6) + return -EINVAL; + + val = *((int *)optval); + /* Only some options are supported */ + switch (optname) { + case IPV6_TCLASS: + if (val < -1 || val > 0xff) { + ret = -EINVAL; + } else { + struct ipv6_pinfo *np = inet6_sk(sk); + + if (val == -1) + val = 0; + np->tclass = val; + } + break; + default: + ret = -EINVAL; + } +#endif } else if (level == SOL_TCP && sk->sk_prot->setsockopt == tcp_setsockopt) { if (optname == TCP_CONGESTION) { @@ -3239,7 +3262,8 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, strncpy(name, optval, min_t(long, optlen, TCP_CA_NAME_MAX-1)); name[TCP_CA_NAME_MAX-1] = 0; - ret = tcp_set_congestion_control(sk, name, false, reinit); + ret = tcp_set_congestion_control(sk, name, false, + reinit); } else { struct tcp_sock *tp = tcp_sk(sk); @@ -3305,6 +3329,22 @@ BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, } else { goto err_clear; } +#if IS_ENABLED(CONFIG_IPV6) + } else if (level == SOL_IPV6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + if (optlen != sizeof(int) || sk->sk_family != AF_INET6) + goto err_clear; + + /* Only some options are supported */ + switch (optname) { + case IPV6_TCLASS: + *((int *)optval) = (int)np->tclass; + break; + default: + goto err_clear; + } +#endif } else { goto err_clear; } @@ -3844,6 +3884,7 @@ static bool sock_ops_is_valid_access(int off, int size, case offsetof(struct bpf_sock_ops, op) ... offsetof(struct bpf_sock_ops, replylong[3]): case offsetof(struct bpf_sock_ops, bpf_sock_ops_flags): + case offsetof(struct bpf_sock_ops, sk_txhash): break; default: return false; @@ -4631,6 +4672,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, bytes_acked): SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock); break; + + case offsetof(struct bpf_sock_ops, sk_txhash): + SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, + struct sock, type); + break; } return insn - insn_buf; } -- 2.9.5