Merge branch 'net-avoid-ehash-lookup-races'

Xuanqiang Luo says:

====================
net: Avoid ehash lookup races

After replacing R/W locks with RCU in commit 3ab5aee7fe ("net: Convert
TCP & DCCP hash tables to use RCU / hlist_nulls"), a race window emerged
during the switch from reqsk/sk to sk/tw.

Now that both timewait sock (tw) and full sock (sk) reside on the same
ehash chain, it is appropriate to introduce hlist_nulls replace
operations, to eliminate the race conditions caused by this window.

Before this series of patches, I previously sent another version of the
patch, attempting to avoid the issue using a lock mechanism. However, it
seems there are some problems with that approach now, so I've switched to
the "replace" method in the current patches to resolve the issue.
For details, refer to:
https://lore.kernel.org/netdev/20250903024406.2418362-1-xuanqiang.luo@linux.dev/

Before I encountered this type of issue recently, I found there had been
several historical discussions about it. Therefore, I'm adding this
background information for those interested to reference:
1. https://lore.kernel.org/lkml/20230118015941.1313-1-kerneljasonxing@gmail.com/
2. https://lore.kernel.org/netdev/20230606064306.9192-1-duanmuquan@baidu.com/
====================

Link: https://patch.msgid.link/20251015020236.431822-1-xuanqiang.luo@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/rculist_nulls.h

@@ -52,6 +52,13 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
 #define hlist_nulls_next_rcu(node) \
 	(*((struct hlist_nulls_node __rcu __force **)&(node)->next))
 
+/**
+ * hlist_nulls_pprev_rcu - returns the dereferenced pprev of @node.
+ * @node: element of the list.
+ */
+#define hlist_nulls_pprev_rcu(node) \
+	(*((struct hlist_nulls_node __rcu __force **)(node)->pprev))
+
 /**
  * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
  * @n: the element to delete from the hash list.
@@ -152,6 +159,58 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
 	n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL);
 }
 
+/**
+ * hlist_nulls_replace_rcu - replace an old entry by a new one
+ * @old: the element to be replaced
+ * @new: the new element to insert
+ *
+ * Description:
+ * Replace the old entry with the new one in a RCU-protected 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().
+ */
+static inline void hlist_nulls_replace_rcu(struct hlist_nulls_node *old,
+					   struct hlist_nulls_node *new)
+{
+	struct hlist_nulls_node *next = old->next;
+
+	WRITE_ONCE(new->next, next);
+	WRITE_ONCE(new->pprev, old->pprev);
+	rcu_assign_pointer(hlist_nulls_pprev_rcu(new), new);
+	if (!is_a_nulls(next))
+		WRITE_ONCE(next->pprev, &new->next);
+}
+
+/**
+ * hlist_nulls_replace_init_rcu - replace an old entry by a new one and
+ * initialize the old
+ * @old: the element to be replaced
+ * @new: the new element to insert
+ *
+ * Description:
+ * Replace the old entry with the new one in a RCU-protected hlist_nulls, while
+ * permitting racing traversals, and reinitialize the old entry.
+ *
+ * Note: @old must be hashed.
+ *
+ * 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().
+ */
+static inline void hlist_nulls_replace_init_rcu(struct hlist_nulls_node *old,
+						struct hlist_nulls_node *new)
+{
+	hlist_nulls_replace_rcu(old, new);
+	WRITE_ONCE(old->pprev, NULL);
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.

include/net/sock.h

@@ -856,6 +856,19 @@ static inline bool sk_nulls_del_node_init_rcu(struct sock *sk)
 	return rc;
 }
 
+static inline bool sk_nulls_replace_node_init_rcu(struct sock *old,
+						  struct sock *new)
+{
+	if (sk_hashed(old)) {
+		hlist_nulls_replace_init_rcu(&old->sk_nulls_node,
+					     &new->sk_nulls_node);
+		__sock_put(old);
+		return true;
+	}
+
+	return false;
+}
+
 static inline void __sk_add_node(struct sock *sk, struct hlist_head *list)
 {
 	hlist_add_head(&sk->sk_node, list);

net/ipv4/inet_hashtables.c

@@ -720,8 +720,11 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	spin_lock(lock);
 	if (osk) {
 		WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
-		ret = sk_nulls_del_node_init_rcu(osk);
-	} else if (found_dup_sk) {
+		ret = sk_nulls_replace_node_init_rcu(osk, sk);
+		goto unlock;
+	}
+
+	if (found_dup_sk) {
 		*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
 		if (*found_dup_sk)
 			ret = false;
@@ -730,6 +733,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	if (ret)
 		__sk_nulls_add_node_rcu(sk, list);
 
+unlock:
 	spin_unlock(lock);
 
 	return ret;

net/ipv4/inet_timewait_sock.c

@@ -88,12 +88,6 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(inet_twsk_put);
 
-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
-				   struct hlist_nulls_head *list)
-{
-	hlist_nulls_add_head_rcu(&tw->tw_node, list);
-}
-
 static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
 {
 	__inet_twsk_schedule(tw, timeo, false);
@@ -113,13 +107,12 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
 	spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
 	struct inet_bind_hashbucket *bhead, *bhead2;
 
-	/* Step 1: Put TW into bind hash. Original socket stays there too.
-	   Note, that any socket with inet->num != 0 MUST be bound in
-	   binding cache, even if it is closed.
+	/* Put TW into bind hash. Original socket stays there too.
+	 * Note, that any socket with inet->num != 0 MUST be bound in
+	 * binding cache, even if it is closed.
 	 */
 	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
 			hashinfo->bhash_size)];
@@ -141,19 +134,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 
 	spin_lock(lock);
 
-	/* Step 2: Hash TW into tcp ehash chain */
-	inet_twsk_add_node_rcu(tw, &ehead->chain);
-
-	/* Step 3: Remove SK from hash chain */
-	if (__sk_nulls_del_node_init_rcu(sk))
-		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-
-
-	/* Ensure above writes are committed into memory before updating the
-	 * refcount.
-	 * Provides ordering vs later refcount_inc().
-	 */
-	smp_wmb();
 	/* tw_refcnt is set to 3 because we have :
 	 * - one reference for bhash chain.
 	 * - one reference for ehash chain.
@@ -163,6 +143,15 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
 	 */
 	refcount_set(&tw->tw_refcnt, 3);
 
+	/* Ensure tw_refcnt has been set before tw is published.
+	 * smp_wmb() provides the necessary memory barrier to enforce this
+	 * ordering.
+	 */
+	smp_wmb();
+
+	hlist_nulls_replace_init_rcu(&sk->sk_nulls_node, &tw->tw_node);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+
 	inet_twsk_schedule(tw, timeo);
 
 	spin_unlock(lock);