netdev - [PATCH bpf-next v4 3/3] bpf: add SO_KEEPALIVE and related options to bpf

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20200602195147.56912-3-zeil@yandex-team.ru>
Date:   Tue,  2 Jun 2020 22:51:47 +0300
From:   Dmitry Yakunin <zeil@...dex-team.ru>
To:     alexei.starovoitov@...il.com
Cc:     davem@...emloft.net, brakmo@...com, eric.dumazet@...il.com,
        kafai@...com, bpf@...r.kernel.org, netdev@...r.kernel.org
Subject: [PATCH bpf-next v4 3/3] 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.

v2:
  - update kernel-doc (Nikita Vetoshkin <nekto0n@...dex-team.ru>)

Signed-off-by: Dmitry Yakunin <zeil@...dex-team.ru>
Acked-by: Martin KaFai Lau <kafai@...com>
---
 include/uapi/linux/bpf.h |  7 +++++--
 net/core/filter.c        | 36 +++++++++++++++++++++++++++++++++++-
 2 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b9ed9f1..3b8815d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1621,10 +1621,13 @@ 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 ae82bcb..674272c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4249,10 +4249,10 @@ 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;
@@ -4263,6 +4263,7 @@ 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) {
@@ -4324,6 +4325,11 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			ret = sock_bindtoindex(sk, ifindex, false);
 #endif
 			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;
 		}
@@ -4384,6 +4390,7 @@ 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))
@@ -4412,6 +4419,33 @@ 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;
 			}
-- 
2.7.4