[PATCH v3 bpf-next 12/15] bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt()

From: Martin KaFai Lau <kafai@fb.com>
To: <bpf@vger.kernel.org>, <netdev@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
	Andrii Nakryiko <andrii@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	David Miller <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, <kernel-team@fb.com>,
	Paolo Abeni <pabeni@redhat.com>,
	Stanislav Fomichev <sdf@google.com>
Subject: [PATCH v3 bpf-next 12/15] bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt()
Date: Wed, 10 Aug 2022 12:08:43 -0700	[thread overview]
Message-ID: <20220810190843.2701858-1-kafai@fb.com> (raw)
In-Reply-To: <20220810190724.2692127-1-kafai@fb.com>

After the prep work in the previous patches,
this patch removes the dup code from bpf_setsockopt(SOL_IP)
and reuses the implementation in do_ip_setsockopt().

The existing optname white-list is refactored into a new
function sol_ip_setsockopt().

NOTE,
the current bpf_setsockopt(IP_TOS) is quite different from the
the do_ip_setsockopt(IP_TOS).  For example, it does not take
the INET_ECN_MASK into the account for tcp and also does not adjust
sk->sk_priority.  It looks like the current bpf_setsockopt(IP_TOS)
was referencing the IPV6_TCLASS implementation instead of IP_TOS.
This patch tries to rectify that by using the do_ip_setsockopt(IP_TOS).
While this is a behavior change,  the do_ip_setsockopt(IP_TOS) behavior
is arguably what the user is expecting.  At least, the INET_ECN_MASK bits
should be masked out for tcp.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
 include/net/ip.h       |  2 ++
 net/core/filter.c      | 40 ++++++++++++++++++++--------------------
 net/ipv4/ip_sockglue.c |  4 ++--
 3 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 1c979fd1904c..34fa5b0f0a0e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -743,6 +743,8 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 DECLARE_STATIC_KEY_FALSE(ip4_min_ttl);
+int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		     unsigned int optlen);
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		  unsigned int optlen);
 int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
diff --git a/net/core/filter.c b/net/core/filter.c
index 0c5361b8906d..d236f71ff501 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5123,6 +5123,25 @@ static int sol_tcp_setsockopt(struct sock *sk, int optname,
 				 KERNEL_SOCKPTR(optval), optlen);
 }
 
+static int sol_ip_setsockopt(struct sock *sk, int optname,
+			     char *optval, int optlen)
+{
+	if (sk->sk_family != AF_INET)
+		return -EINVAL;
+
+	switch (optname) {
+	case IP_TOS:
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return do_ip_setsockopt(sk, SOL_IP, optname,
+				KERNEL_SOCKPTR(optval), optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
@@ -5134,26 +5153,7 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	if (level == SOL_SOCKET) {
 		return sol_socket_setsockopt(sk, optname, optval, optlen);
 	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
-			return -EINVAL;
-
-		val = *((int *)optval);
-		/* Only some options are supported */
-		switch (optname) {
-		case IP_TOS:
-			if (val < -1 || val > 0xff) {
-				ret = -EINVAL;
-			} else {
-				struct inet_sock *inet = inet_sk(sk);
-
-				if (val == -1)
-					val = 0;
-				inet->tos = val;
-			}
-			break;
-		default:
-			ret = -EINVAL;
-		}
+		return sol_ip_setsockopt(sk, optname, optval, optlen);
 	} else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) {
 		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
 			return -EINVAL;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index a3c496580e6b..751fa69cb557 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -888,8 +888,8 @@ static int compat_ip_mcast_join_leave(struct sock *sk, int optname,
 
 DEFINE_STATIC_KEY_FALSE(ip4_min_ttl);
 
-static int do_ip_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
+int do_ip_setsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, unsigned int optlen)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
-- 
2.30.2

