[rds-devel] [PATCH v2 net 2/5] Revert "tcp: Clean up kernel listener's reqsk in inet_twsk_purge()"

[Kuniyuki Iwashima]

This reverts commit 740ea3c4a0b2e326b23d7cdf05472a0e92aa39bc.

The change actually fixed a use-after-free of struct net by kernel
listener's reqsk in per-netns ehash.

However, the fix was incomplete, as the same issue exists for the
global ehash.

We should have fixed it on the RDS side without slowing down netns
dismantle for the normal TCP use case.

The following patches will fix the issue on the RDS side.

Fixes: 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()")
Signed-off-by: Kuniyuki Iwashima <kuniyu at amazon.com>
---
 net/ipv4/inet_timewait_sock.c | 16 +---------------
 net/ipv4/tcp_minisocks.c      |  9 ++++-----
 2 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 00cbebaa2c68..6b65f5f97478 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -277,22 +277,8 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
 		rcu_read_lock();
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->chain) {
-			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);
-
-					goto restart;
-				}
-
+			if (sk->sk_state != TCP_TIME_WAIT)
 				continue;
-			}
 
 			tw = inet_twsk(sk);
 			if ((tw->tw_family != family) ||
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 9e85f2a0bddd..baecfa4c70ef 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -394,14 +394,13 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)
 	struct net *net;
 
 	list_for_each_entry(net, net_exit_list, exit_list) {
+		/* The last refcount is decremented in tcp_sk_exit_batch() */
+		if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
+			continue;
+
 		if (net->ipv4.tcp_death_row.hashinfo->pernet) {
-			/* Even if tw_refcount == 1, we must clean up kernel reqsk */
 			inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family);
 		} else if (!purged_once) {
-			/* The last refcount is decremented in tcp_sk_exit_batch() */
-			if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
-				continue;
-
 			inet_twsk_purge(&tcp_hashinfo, family);
 			purged_once = true;
 		}
-- 
2.30.2