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>

include/linux/bpf-cgroup.h

@@ -40,6 +40,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
 				enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_sk(struct sock *sk,
+			       enum bpf_attach_type type);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -63,6 +66,16 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	__ret;								       \
 })
 
+#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk)				       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled && sk) {					       \
+		__ret = __cgroup_bpf_run_filter_sk(sk,			       \
+						 BPF_CGROUP_INET_SOCK_CREATE); \
+	}								       \
+	__ret;								       \
+})
+
 #else
 
 struct cgroup_bpf {};
@@ -72,6 +85,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
 
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 
 #endif /* CONFIG_CGROUP_BPF */
 

include/uapi/linux/bpf.h

@@ -101,6 +101,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_XDP,
 	BPF_PROG_TYPE_PERF_EVENT,
 	BPF_PROG_TYPE_CGROUP_SKB,
+	BPF_PROG_TYPE_CGROUP_SOCK,
 	BPF_PROG_TYPE_LWT_IN,
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
@@ -109,6 +110,7 @@ enum bpf_prog_type {
 enum bpf_attach_type {
 	BPF_CGROUP_INET_INGRESS,
 	BPF_CGROUP_INET_EGRESS,
+	BPF_CGROUP_INET_SOCK_CREATE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -567,6 +569,10 @@ enum bpf_ret_code {
 	/* >127 are reserved for prog type specific return codes */
 };
 
+struct bpf_sock {
+	__u32 bound_dev_if;
+};
+
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
  * return codes are reserved for future use. Unknown return codes will result

kernel/bpf/cgroup.c

@@ -165,3 +165,36 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	return ret;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
+
+/**
+ * __cgroup_bpf_run_filter_sk() - Run a program on a sock
+ * @sk: sock structure to manipulate
+ * @type: The type of program to be exectuted
+ *
+ * socket is passed is expected to be of type INET or INET6.
+ *
+ * The program type passed in via @type must be suitable for sock
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sk(struct sock *sk,
+			       enum bpf_attach_type type)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_prog *prog;
+	int ret = 0;
+
+
+	rcu_read_lock();
+
+	prog = rcu_dereference(cgrp->bpf.effective[type]);
+	if (prog)
+		ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM;
+
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);

kernel/bpf/syscall.c

@@ -869,7 +869,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_INET_EGRESS:
 		ptype = BPF_PROG_TYPE_CGROUP_SKB;
 		break;
-
+	case BPF_CGROUP_INET_SOCK_CREATE:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -905,6 +907,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
+	case BPF_CGROUP_INET_SOCK_CREATE:
 		cgrp = cgroup_get_from_fd(attr->target_fd);
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);

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);

net/ipv4/af_inet.c

@@ -374,8 +374,18 @@ static int inet_create(struct net *net, struct socket *sock, int 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;

net/ipv6/af_inet6.c

@@ -258,6 +258,14 @@ static int inet6_create(struct net *net, struct socket *sock, int 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: