[stable,5.15,1/2] Revert "tcp: Fix NEW_SYN_RECV handling in inet_twsk_purge()"

Commit Message

shaozhengchao May 6, 2024, 3:05 a.m. UTC

This reverts commit 4fa0befa92f2adaef8eb268f724f38a213ab7dcc.

In order to revert commit 214a2dfbb84f("tcp: Clean up kernel listener's
reqsk in inet_twsk_purge()"), revert this patch.

Signed-off-by: Zhengchao Shao <[e-mail]>
---
 net/ipv4/inet_timewait_sock.c | 41 +++++++++++++++++++----------------
 1 file changed, 22 insertions(+), 19 deletions(-)

Patch

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 25809e06f111..9b891d6296ec 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -254,12 +254,12 @@  void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
-/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */
 void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
 {
+	struct inet_timewait_sock *tw;
+	struct sock *sk;
 	struct hlist_nulls_node *node;
 	unsigned int slot;
-	struct sock *sk;
 
 	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
@@ -268,35 +268,38 @@  void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
 		rcu_read_lock();
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->chain) {
-			int state = inet_sk_state_load(sk);
+			if (sk->sk_state != TCP_TIME_WAIT) {
+				/* A kernel listener socket might not hold refcnt for net,
+				 * so reqsk_timer_handler() could be fired after net is
+				 * freed.  Userspace listener and reqsk never exist here.
+				 */
+				if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV &&
+					     hashinfo->pernet)) {
+					struct request_sock *req = inet_reqsk(sk);
+
+					inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
+				}
 
-			if ((1 << state) & ~(TCPF_TIME_WAIT |
-					     TCPF_NEW_SYN_RECV))
 				continue;
+			}
 
-			if (sk->sk_family != family ||
-			    refcount_read(&sock_net(sk)->ns.count))
+			tw = inet_twsk(sk);
+			if ((tw->tw_family != family) ||
+				refcount_read(&twsk_net(tw)->ns.count))
 				continue;
 
-			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
 				continue;
 
-			if (unlikely(sk->sk_family != family ||
-				     refcount_read(&sock_net(sk)->ns.count))) {
-				sock_gen_put(sk);
+			if (unlikely((tw->tw_family != family) ||
+				     refcount_read(&twsk_net(tw)->ns.count))) {
+				inet_twsk_put(tw);
 				goto restart;
 			}
 
 			rcu_read_unlock();
 			local_bh_disable();
-			if (state == TCP_TIME_WAIT) {
-				inet_twsk_deschedule_put(inet_twsk(sk));
-			} else {
-				struct request_sock *req = inet_reqsk(sk);
-
-				inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
-								  req);
-			}
+			inet_twsk_deschedule_put(tw);
 			local_bh_enable();
 			goto restart_rcu;
 		}