bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt()

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.

Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061826.4180990-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/net/ip.h b/include/net/ip.h
index 1c979fd1904ce371d372ce42f3359fa277202295..34fa5b0f0a0e384d46835664e810076fe1d29956 100644 (file)
--- 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 66877605bb78a44abfc7b4037a716e8f773bcfc7..4d1b42b8f4a894a4c9afb79a31a0b0d954f64222 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5114,6 +5114,25 @@ 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)
 {
@@ -5125,26 +5144,7 @@ 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 a3c496580e6b0e1f390277d793957351e38ca12a..751fa69cb557f8770c75b267fe0fc6fe22b117fa 100644 (file)
--- 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);