bpf: Add new cgroup attach type to enable sock modifications

Add new cgroup based program type, BPF_PROG_TYPE_CGROUP_SOCK. Similar to
BPF_PROG_TYPE_CGROUP_SKB programs can be attached to a cgroup and run
any time a process in the cgroup opens an AF_INET or AF_INET6 socket.
Currently only sk_bound_dev_if is exported to userspace for modification
by a bpf program.

This allows a cgroup to be configured such that AF_INET{6} sockets opened
by processes are automatically bound to a specific device. In turn, this
enables the running of programs that do not support SO_BINDTODEVICE in a
specific VRF context / L3 domain.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 81 insertions, 1 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 1c4d0faf22c8..0ab252e462aa 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2818,6 +2818,32 @@ static bool lwt_is_valid_access(int off, int size,
 	return __is_valid_access(off, size, type);
 }
 
+static bool sock_filter_is_valid_access(int off, int size,
+					enum bpf_access_type type,
+					enum bpf_reg_type *reg_type)
+{
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case offsetof(struct bpf_sock, bound_dev_if):
+			break;
+		default:
+			return false;
+		}
+	}
+
+	if (off < 0 || off + size > sizeof(struct bpf_sock))
+		return false;
+
+	/* The verifier guarantees that size > 0. */
+	if (off % size != 0)
+		return false;
+
+	if (size != sizeof(__u32))
+		return false;
+
+	return true;
+}
+
 static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
 			       const struct bpf_prog *prog)
 {
@@ -3076,6 +3102,30 @@ static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
 	return insn - insn_buf;
 }
 
+static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
+					  int dst_reg, int src_reg,
+					  int ctx_off,
+					  struct bpf_insn *insn_buf,
+					  struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (ctx_off) {
+	case offsetof(struct bpf_sock, bound_dev_if):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4);
+
+		if (type == BPF_WRITE)
+			*insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
+					offsetof(struct sock, sk_bound_dev_if));
+		else
+			*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+				      offsetof(struct sock, sk_bound_dev_if));
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
 static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, int dst_reg,
 					 int src_reg, int ctx_off,
 					 struct bpf_insn *insn_buf,
@@ -3162,6 +3212,12 @@ static const struct bpf_verifier_ops lwt_xmit_ops = {
 	.gen_prologue		= tc_cls_act_prologue,
 };
 
+static const struct bpf_verifier_ops cg_sock_ops = {
+	.get_func_proto		= sk_filter_func_proto,
+	.is_valid_access	= sock_filter_is_valid_access,
+	.convert_ctx_access	= sock_filter_convert_ctx_access,
+};
+
 static struct bpf_prog_type_list sk_filter_type __read_mostly = {
 	.ops	= &sk_filter_ops,
 	.type	= BPF_PROG_TYPE_SOCKET_FILTER,
@@ -3202,6 +3258,11 @@ static struct bpf_prog_type_list lwt_xmit_type __read_mostly = {
 	.type	= BPF_PROG_TYPE_LWT_XMIT,
 };
 
+static struct bpf_prog_type_list cg_sock_type __read_mostly = {
+	.ops	= &cg_sock_ops,
+	.type	= BPF_PROG_TYPE_CGROUP_SOCK
+};
+
 static int __init register_sk_filter_ops(void)
 {
 	bpf_register_prog_type(&sk_filter_type);
@@ -3209,6 +3270,7 @@ static int __init register_sk_filter_ops(void)
 	bpf_register_prog_type(&sched_act_type);
 	bpf_register_prog_type(&xdp_type);
 	bpf_register_prog_type(&cg_skb_type);
+	bpf_register_prog_type(&cg_sock_type);
 	bpf_register_prog_type(&lwt_in_type);
 	bpf_register_prog_type(&lwt_out_type);
 	bpf_register_prog_type(&lwt_xmit_type);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5ddf5cda07f4..24d2550492ee 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -374,8 +374,18 @@ lookup_protocol:
 
 	if (sk->sk_prot->init) {
 		err = sk->sk_prot->init(sk);
-		if (err)
+		if (err) {
+			sk_common_release(sk);
+			goto out;
+		}
+	}
+
+	if (!kern) {
+		err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
+		if (err) {
 			sk_common_release(sk);
+			goto out;
+		}
 	}
 out:
 	return err;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d424f3a3737a..237e654ba717 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -258,6 +258,14 @@ lookup_protocol:
 			goto out;
 		}
 	}
+
+	if (!kern) {
+		err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
+		if (err) {
+			sk_common_release(sk);
+			goto out;
+		}
+	}
 out:
 	return err;
 out_rcu_unlock: