Merge branch 'bpf_sk_assign'

Joe Stringer says:

====================
Introduce a new helper that allows assigning a previously-found socket
to the skb as the packet is received towards the stack, to cause the
stack to guide the packet towards that socket subject to local routing
configuration. The intention is to support TProxy use cases more
directly from eBPF programs attached at TC ingress, to simplify and
streamline Linux stack configuration in scale environments with Cilium.

Normally in ip{,6}_rcv_core(), the skb will be orphaned, dropping any
existing socket reference associated with the skb. Existing tproxy
implementations in netfilter get around this restriction by running the
tproxy logic after ip_rcv_core() in the PREROUTING table. However, this
is not an option for TC-based logic (including eBPF programs attached at
TC ingress).

This series introduces the BPF helper bpf_sk_assign() to associate the
socket with the skb on the ingress path as the packet is passed up the
stack. The initial patch in the series simply takes a reference on the
socket to ensure safety, but later patches relax this for listen
sockets.

To ensure delivery to the relevant socket, we still consult the routing
table, for full examples of how to configure see the tests in patch #5;
the simplest form of the route would look like this:

  $ ip route add local default dev lo

This series is laid out as follows:
* Patch 1 extends the eBPF API to add sk_assign() and defines a new
  socket free function to allow the later paths to understand when the
  socket associated with the skb should be kept through receive.
* Patches 2-3 optimize the receive path to avoid taking a reference on
  listener sockets during receive.
* Patches 4-5 extends the selftests with examples of the new
  functionality and validation of correct behaviour.

Changes since v4:
* Fix build with CONFIG_INET disabled
* Rebase

Changes since v3:
* Use sock_gen_put() directly instead of sock_edemux() from sock_pfree()
* Commit message wording fixups
* Add acks from Martin, Lorenz
* Rebase

Changes since v2:
* Add selftests for UDP socket redirection
* Drop the early demux optimization patch (defer for more testing)
* Fix check for orphaning after TC act return
* Tidy up the tests to clean up properly and be less noisy.

Changes since v1:
* Replace the metadata_dst approach with using the skb->destructor to
  determine whether the socket has been prefetched. This is much
  simpler.
* Avoid taking a reference on listener sockets during receive
* Restrict assigning sockets across namespaces
* Restrict assigning SO_REUSEPORT sockets
* Fix cookie usage for socket dst check
* Rebase the tests against test_progs infrastructure
* Tidy up commit messages
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

4 files changed, 63 insertions, 14 deletions

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index fe96bf247aac..81b965953036 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -85,9 +85,8 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      int iif, int sdif,
 					      bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb);
+	struct sock *sk = skb_steal_sock(skb, refcounted);
 
-	*refcounted = true;
 	if (sk)
 		return sk;
 
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index d0019d3395cf..ad64ba6a057f 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,10 +379,9 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     const int sdif,
 					     bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb);
+	struct sock *sk = skb_steal_sock(skb, refcounted);
 	const struct iphdr *iph = ip_hdr(skb);
 
-	*refcounted = true;
 	if (sk)
 		return sk;
 
diff --git a/include/net/sock.h b/include/net/sock.h
index b5cca7bae69b..6d84784d33fa 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1659,6 +1659,7 @@ void sock_rfree(struct sk_buff *skb);
 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
@@ -2526,16 +2527,14 @@ void sock_net_set(struct sock *sk, struct net *net)
 	write_pnet(&sk->sk_net, net);
 }
 
-static inline struct sock *skb_steal_sock(struct sk_buff *skb)
+static inline bool
+skb_sk_is_prefetched(struct sk_buff *skb)
 {
-	if (skb->sk) {
-		struct sock *sk = skb->sk;
-
-		skb->destructor = NULL;
-		skb->sk = NULL;
-		return sk;
-	}
-	return NULL;
+#ifdef CONFIG_INET
+	return skb->destructor == sock_pfree;
+#else
+	return false;
+#endif /* CONFIG_INET */
 }
 
 /* This helper checks if a socket is a full socket,
@@ -2546,6 +2545,35 @@ static inline bool sk_fullsock(const struct sock *sk)
 	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
 }
 
+static inline bool
+sk_is_refcounted(struct sock *sk)
+{
+	/* Only full sockets have sk->sk_flags. */
+	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
+}
+
+/**
+ * skb_steal_sock
+ * @skb to steal the socket from
+ * @refcounted is set to true if the socket is reference-counted
+ */
+static inline struct sock *
+skb_steal_sock(struct sk_buff *skb, bool *refcounted)
+{
+	if (skb->sk) {
+		struct sock *sk = skb->sk;
+
+		*refcounted = true;
+		if (skb_sk_is_prefetched(skb))
+			*refcounted = sk_is_refcounted(sk);
+		skb->destructor = NULL;
+		skb->sk = NULL;
+		return sk;
+	}
+	*refcounted = false;
+	return NULL;
+}
+
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
  * Check decrypted mark in case skb_orphan() cleared socket.
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f1fbc36f58d3..9f786a5a44ac 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2983,6 +2983,28 @@ union bpf_attr {
  * 		**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),			\
@@ -3108,7 +3130,8 @@ union bpf_attr {
 	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