bpf: Support bpf_setsockopt() for BPF_CGROUP_INET_SOCK_CREATE.

We will support flagging SK_MEMCG_EXCLUSIVE via bpf_setsockopt() at
the BPF_CGROUP_INET_SOCK_CREATE hook.

BPF_CGROUP_INET_SOCK_CREATE is invoked by __cgroup_bpf_run_filter_sk()
that passes a pointer to struct sock to the bpf prog as void *ctx.

But there are no bpf_func_proto for bpf_setsockopt() that receives
the ctx as a pointer to struct sock.

Also, bpf_getsockopt() will be necessary for a cgroup with multiple
bpf progs running.

Let's add new bpf_setsockopt() and bpf_getsockopt() variants for
BPF_CGROUP_INET_SOCK_CREATE.

Note that inet_create() is not under lock_sock() and has the same
semantics with bpf_lsm_unlocked_sockopt_hooks.

Signed-off-by: Kuniyuki Iwashima <[email protected]>

Author: q2ven

net/core/filter.c

@@ -5723,6 +5723,40 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_sock_create_setsockopt, struct sock *, sk, int, level,
+	   int, optname, char *, optval, int, optlen)
+{
+	return __bpf_setsockopt(sk, level, optname, optval, optlen);
+}
+
+static const struct bpf_func_proto bpf_sock_create_setsockopt_proto = {
+	.func		= bpf_sock_create_setsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sock_create_getsockopt, struct sock *, sk, int, level,
+	   int, optname, char *, optval, int, optlen)
+{
+	return __bpf_getsockopt(sk, level, optname, optval, optlen);
+}
+
+static const struct bpf_func_proto bpf_sock_create_getsockopt_proto = {
+	.func		= bpf_sock_create_getsockopt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
@@ -8051,6 +8085,20 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_cg_sock_proto;
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
+	case BPF_FUNC_setsockopt:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET_SOCK_CREATE:
+			return &bpf_sock_create_setsockopt_proto;
+		default:
+			return NULL;
+		}
+	case BPF_FUNC_getsockopt:
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET_SOCK_CREATE:
+			return &bpf_sock_create_getsockopt_proto;
+		default:
+			return NULL;
+		}
 	default:
 		return bpf_base_func_proto(func_id, prog);
 	}