From e4810fd04eb97f8435c24ca78e6f89be68ef3e28 Mon Sep 17 00:00:00 2001 From: Dmitry Yakunin Date: Sat, 20 Jun 2020 18:30:52 +0300 Subject: [PATCH] BACKPORT: bpf: Add SO_KEEPALIVE and related options to bpf_setsockopt This patch adds support of SO_KEEPALIVE flag and TCP related options to bpf_setsockopt() routine. This is helpful if we want to enable or tune TCP keepalive for applications which don't do it in the userspace code. v3: - update kernel-doc in uapi (Nikita Vetoshkin ) v4: - update kernel-doc in tools too (Alexei Starovoitov) - add test to selftests (Alexei Starovoitov) Change-Id: Ie16bf737964360c59ab9a8d796343863b3883b59 Signed-off-by: Dmitry Yakunin Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200620153052.9439-3-zeil@yandex-team.ru --- include/uapi/linux/bpf.h | 7 +++++-- net/core/filter.c | 36 +++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 7 +++++-- 3 files changed, 45 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7f2d17b7276e..c6e9acdfbe17 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1623,10 +1623,13 @@ union bpf_attr { * * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, - * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**. + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return diff --git a/net/core/filter.c b/net/core/filter.c index ed3bc8719df1..3301c07bc8f9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4351,10 +4351,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen, u32 flags) { char devname[IFNAMSIZ]; + int val, valbool; struct net *net; int ifindex; int ret = 0; - int val; if (!sk_fullsock(sk)) return -EINVAL; @@ -4365,6 +4365,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, if (optlen != sizeof(int) && optname != SO_BINDTODEVICE) return -EINVAL; val = *((int *)optval); + valbool = val ? 1 : 0; /* Only some socketops are supported */ switch (optname) { @@ -4426,6 +4427,11 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } ret = sock_bindtoindex(sk, ifindex, false); break; + case SO_KEEPALIVE: + if (sk->sk_prot->keepalive) + sk->sk_prot->keepalive(sk, valbool); + sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); + break; default: ret = -EINVAL; } @@ -4486,6 +4492,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, ret = tcp_set_congestion_control(sk, name, false, reinit, true); } else { + struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if (optlen != sizeof(int)) @@ -4514,6 +4521,33 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, else tp->save_syn = val; break; + case TCP_KEEPIDLE: + ret = tcp_sock_set_keepidle_locked(sk, val); + break; + case TCP_KEEPINTVL: + if (val < 1 || val > MAX_TCP_KEEPINTVL) + ret = -EINVAL; + else + tp->keepalive_intvl = val * HZ; + break; + case TCP_KEEPCNT: + if (val < 1 || val > MAX_TCP_KEEPCNT) + ret = -EINVAL; + else + tp->keepalive_probes = val; + break; + case TCP_SYNCNT: + if (val < 1 || val > MAX_TCP_SYNCNT) + ret = -EINVAL; + else + icsk->icsk_syn_retries = val; + break; + case TCP_USER_TIMEOUT: + if (val < 0) + ret = -EINVAL; + else + icsk->icsk_user_timeout = val; + break; default: ret = -EINVAL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7a8512c42553..0c8f34a2b1d7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1608,10 +1608,13 @@ union bpf_attr { * * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, - * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**. + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. * Return