4 files changed, 61 insertions, 4 deletions

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index bc8206a8f30e..61974c4c566b 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -101,6 +101,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 }
 
 /**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist_nulls,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					    struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	/* Note: write side code, so rcu accessors are not needed. */
+	for (i = h->first; !is_a_nulls(i); i = i->next)
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
+/**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct hlist_nulls_node to use as a loop cursor.
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index af2b4c065a04..d0019d3395cf 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -103,13 +103,19 @@ struct inet_bind_hashbucket {
 	struct hlist_head	chain;
 };
 
-/*
- * Sockets can be hashed in established or listening table
+/* Sockets can be hashed in established or listening table.
+ * We must use different 'nulls' end-of-chain value for all hash buckets :
+ * A socket might transition from ESTABLISH to LISTEN state without
+ * RCU grace period. A lookup in ehash table needs to handle this case.
  */
+#define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
 	unsigned int		count;
-	struct hlist_head	head;
+	union {
+		struct hlist_head	head;
+		struct hlist_nulls_head	nulls_head;
+	};
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */
diff --git a/include/net/sock.h b/include/net/sock.h
index 87d54ef57f00..04c274a20620 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -722,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
+static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+}
+
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	sock_hold(sk);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 86b9a8766648..e460ea7f767b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1766,9 +1766,18 @@ static inline bool tcp_skb_is_last(const struct sock *sk,
 	return skb_queue_is_last(&sk->sk_write_queue, skb);
 }
 
+/**
+ * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue
+ * @sk: socket
+ *
+ * Since the write queue can have a temporary empty skb in it,
+ * we must not use "return skb_queue_empty(&sk->sk_write_queue)"
+ */
 static inline bool tcp_write_queue_empty(const struct sock *sk)
 {
-	return skb_queue_empty(&sk->sk_write_queue);
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	return tp->write_seq == tp->snd_nxt;
 }
 
 static inline bool tcp_rtx_queue_empty(const struct sock *sk)