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