netdev - [RFC PATCH bpf-next 4/8] tcp: Migrate TFO requests causing RST during TCP_SYN

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20201117094023.3685-5-kuniyu@amazon.co.jp>
Date:   Tue, 17 Nov 2020 18:40:19 +0900
From:   Kuniyuki Iwashima <kuniyu@...zon.co.jp>
To:     "David S . Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Eric Dumazet <edumazet@...gle.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>
CC:     Benjamin Herrenschmidt <benh@...zon.com>,
        Kuniyuki Iwashima <kuniyu@...zon.co.jp>,
        Kuniyuki Iwashima <kuni1840@...il.com>, <bpf@...r.kernel.org>,
        <netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: [RFC PATCH bpf-next 4/8] tcp: Migrate TFO requests causing RST during TCP_SYN_RECV.

A TFO request socket is only freed after BOTH 3WHS has completed (or
aborted) and the child socket has been accepted (or its listener closed).
Hence, depending on the order, there can be two kinds of request sockets in
the accept queue.

  3WHS -> accept : TCP_ESTABLISHED
  accept -> 3WHS : TCP_SYN_RECV

Unlike TCP_ESTABLISHED socket, accept() does not free the request socket
for TCP_SYN_RECV socket. It is freed later at reqsk_fastopen_remove().
Also, it accesses request_sock.rsk_listener. So, in order to complete TFO
socket migration, we have to set the current listener to it at accept()
before reqsk_fastopen_remove().

Moreover, if TFO request caused RST before 3WHS has completed, it is held
in the listener's TFO queue to prevent DDoS attack. Thus, we also have to
migrate the requests in TFO queue.

Reviewed-by: Benjamin Herrenschmidt <benh@...zon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@...zon.co.jp>
---
 net/ipv4/inet_connection_sock.c | 35 ++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 583db7e2b1da..398c5c708bc5 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -500,6 +500,16 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 	    tcp_rsk(req)->tfo_listener) {
 		spin_lock_bh(&queue->fastopenq.lock);
 		if (tcp_rsk(req)->tfo_listener) {
+			if (req->rsk_listener != sk) {
+				/* TFO request was migrated to another listener so
+				 * the new listener must be used in reqsk_fastopen_remove()
+				 * to hold requests which cause RST.
+				 */
+				sock_put(req->rsk_listener);
+				sock_hold(sk);
+				req->rsk_listener = sk;
+			}
+
 			/* We are still waiting for the final ACK from 3WHS
 			 * so can't free req now. Instead, we set req->sk to
 			 * NULL to signify that the child socket is taken
@@ -954,7 +964,6 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 
 	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
 		BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
-		BUG_ON(sk != req->rsk_listener);
 
 		/* Paranoid, to prevent race condition if
 		 * an inbound pkt destined for child is
@@ -995,6 +1004,7 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
 void inet_csk_reqsk_queue_migrate(struct sock *sk, struct sock *nsk)
 {
 	struct request_sock_queue *old_accept_queue, *new_accept_queue;
+	struct fastopen_queue *old_fastopenq, *new_fastopenq;
 
 	old_accept_queue = &inet_csk(sk)->icsk_accept_queue;
 	new_accept_queue = &inet_csk(nsk)->icsk_accept_queue;
@@ -1019,6 +1029,29 @@ void inet_csk_reqsk_queue_migrate(struct sock *sk, struct sock *nsk)
 
 	spin_unlock(&new_accept_queue->rskq_lock);
 	spin_unlock(&old_accept_queue->rskq_lock);
+
+	old_fastopenq = &old_accept_queue->fastopenq;
+	new_fastopenq = &new_accept_queue->fastopenq;
+
+	spin_lock_bh(&old_fastopenq->lock);
+	spin_lock_bh(&new_fastopenq->lock);
+
+	new_fastopenq->qlen += old_fastopenq->qlen;
+	old_fastopenq->qlen = 0;
+
+	if (old_fastopenq->rskq_rst_head) {
+		if (new_fastopenq->rskq_rst_head)
+			old_fastopenq->rskq_rst_tail->dl_next = new_fastopenq->rskq_rst_head;
+		else
+			old_fastopenq->rskq_rst_tail = new_fastopenq->rskq_rst_tail;
+
+		new_fastopenq->rskq_rst_head = old_fastopenq->rskq_rst_head;
+		old_fastopenq->rskq_rst_head = NULL;
+		old_fastopenq->rskq_rst_tail = NULL;
+	}
+
+	spin_unlock_bh(&new_fastopenq->lock);
+	spin_unlock_bh(&old_fastopenq->lock);
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_migrate);
 
-- 
2.17.2 (Apple Git-113)