bpf: Add socket assign support

Add support for TPROXY via a new bpf helper, bpf_sk_assign().

This helper requires the BPF program to discover the socket via a call
to bpf_sk*_lookup_*(), then pass this socket to the new helper. The
helper takes its own reference to the socket in addition to any existing
reference that may or may not currently be obtained for the duration of
BPF processing. For the destination socket to receive the traffic, the
traffic must be routed towards that socket via local route. The
simplest example route is below, but in practice you may want to route
traffic more narrowly (eg by CIDR):

$ ip route add local default dev lo

This patch avoids trying to introduce an extra bit into the skb->sk, as
that would require more invasive changes to all code interacting with
the socket to ensure that the bit is handled correctly, such as all
error-handling cases along the path from the helper in BPF through to
the orphan path in the input. Instead, we opt to use the destructor
variable to switch on the prefetch of the socket.

Signed-off-by: Joe Stringer <[e-mail]>
Signed-off-by: Alexei Starovoitov <[e-mail]>
Acked-by: Martin KaFai Lau <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

include/net/sock.h

···
 void sock_efree(struct sk_buff *skb);
 #ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb);
+void sock_pfree(struct sk_buff *skb);
 #else
 #define sock_edemux sock_efree
 #endif
···
 void sock_net_set(struct sock *sk, struct net *net)
 {
 	write_pnet(&sk->sk_net, net);
+}
+
+static inline bool
+skb_sk_is_prefetched(struct sk_buff *skb)
+{
+#ifdef CONFIG_INET
+	return skb->destructor == sock_pfree;
+#else
+	return false;
+#endif /* CONFIG_INET */
 }
 
 static inline struct sock *skb_steal_sock(struct sk_buff *skb)

include/uapi/linux/bpf.h

···
  * 		**bpf_get_current_cgroup_id**\ ().
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ *	Description
+ *		Assign the *sk* to the *skb*. When combined with appropriate
+ *		routing configuration to receive the packet towards the socket,
+ *		will cause *skb* to be delivered to the specified socket.
+ *		Subsequent redirection of *skb* via  **bpf_redirect**\ (),
+ *		**bpf_clone_redirect**\ () or other methods outside of BPF may
+ *		interfere with successful delivery to the socket.
+ *
+ *		This operation is only valid from TC ingress path.
+ *
+ *		The *flags* argument must be zero.
+ *	Return
+ *		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EINVAL**		Unsupported flags specified.
+ *		* **-ENOENT**		Socket is unavailable for assignment.
+ *		* **-ENETUNREACH**	Socket is unreachable (wrong netns).
+ *		* **-EOPNOTSUPP**	Unsupported operation, for example a
+ *					call from outside of TC ingress.
+ *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
···
 	FN(get_ns_current_pid_tgid),	\
 	FN(xdp_output),			\
 	FN(get_netns_cookie),		\
-	FN(get_current_ancestor_cgroup_id),
+	FN(get_current_ancestor_cgroup_id),	\
+	FN(sk_assign),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

net/core/filter.c

···
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
+{
+	if (flags != 0)
+		return -EINVAL;
+	if (!skb_at_tc_ingress(skb))
+		return -EOPNOTSUPP;
+	if (unlikely(dev_net(skb->dev) != sock_net(sk)))
+		return -ENETUNREACH;
+	if (unlikely(sk->sk_reuseport))
+		return -ESOCKTNOSUPPORT;
+	if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+		return -ENOENT;
+
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = sock_pfree;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sk_assign_proto = {
+	.func		= bpf_sk_assign,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_SOCK_COMMON,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
···
 		return &bpf_skb_ecn_set_ce_proto;
 	case BPF_FUNC_tcp_gen_syncookie:
 		return &bpf_tcp_gen_syncookie_proto;
+	case BPF_FUNC_sk_assign:
+		return &bpf_sk_assign_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);

net/core/sock.c

···
 }
 EXPORT_SYMBOL(sock_efree);
 
+/* Buffer destructor for prefetch/receive path where reference count may
+ * not be held, e.g. for listen sockets.
+ */
+#ifdef CONFIG_INET
+void sock_pfree(struct sk_buff *skb)
+{
+	sock_gen_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_pfree);
+#endif /* CONFIG_INET */
+
 kuid_t sock_i_uid(struct sock *sk)
 {
 	kuid_t uid;

net/ipv4/ip_input.c

···
 	IPCB(skb)->iif = skb->skb_iif;
 
 	/* Must drop socket now because of tproxy. */
-	skb_orphan(skb);
+	if (!skb_sk_is_prefetched(skb))
+		skb_orphan(skb);
 
 	return skb;
 

net/ipv6/ip6_input.c

···
 	rcu_read_unlock();
 
 	/* Must drop socket now because of tproxy. */
-	skb_orphan(skb);
+	if (!skb_sk_is_prefetched(skb))
+		skb_orphan(skb);
 
 	return skb;
 err:

net/sched/act_bpf.c

···
 #include <linux/bpf.h>
 
 #include <net/netlink.h>
+#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 
···
 		bpf_compute_data_pointers(skb);
 		filter_res = BPF_PROG_RUN(filter, skb);
 	}
+	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
+		skb_orphan(skb);
 	rcu_read_unlock();
 
 	/* A BPF program may overwrite the default action opcode.

tools/include/uapi/linux/bpf.h

···
  * 		**bpf_get_current_cgroup_id**\ ().
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ *	Description
+ *		Assign the *sk* to the *skb*. When combined with appropriate
+ *		routing configuration to receive the packet towards the socket,
+ *		will cause *skb* to be delivered to the specified socket.
+ *		Subsequent redirection of *skb* via  **bpf_redirect**\ (),
+ *		**bpf_clone_redirect**\ () or other methods outside of BPF may
+ *		interfere with successful delivery to the socket.
+ *
+ *		This operation is only valid from TC ingress path.
+ *
+ *		The *flags* argument must be zero.
+ *	Return
+ *		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EINVAL**		Unsupported flags specified.
+ *		* **-ENOENT**		Socket is unavailable for assignment.
+ *		* **-ENETUNREACH**	Socket is unreachable (wrong netns).
+ *		* **-EOPNOTSUPP**	Unsupported operation, for example a
+ *					call from outside of TC ingress.
+ *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
···
 	FN(get_ns_current_pid_tgid),	\
 	FN(xdp_output),			\
 	FN(get_netns_cookie),		\
-	FN(get_current_ancestor_cgroup_id),
+	FN(get_current_ancestor_cgroup_id),	\
+	FN(sk_assign),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call