summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKuniyuki Iwashima <kuniyu@amazon.co.jp>2021-06-12 21:32:20 +0900
committerDaniel Borkmann <daniel@iogearbox.net>2021-06-15 18:01:06 +0200
commitd4f2c86b2b7e2e606e0868b38c8c6c49cc193a8e (patch)
tree8d45fc1c5bf3ba6c1726e3212dc54ed8e488abaa
parentc905dee62232db583b50fe214080b98db623151e (diff)
tcp: Migrate TCP_NEW_SYN_RECV requests at receiving the final ACK.
This patch also changes the code to call reuseport_migrate_sock() and inet_reqsk_clone(), but unlike the other cases, we do not call inet_reqsk_clone() right after reuseport_migrate_sock(). Currently, in the receive path for TCP_NEW_SYN_RECV sockets, its listener has three kinds of refcnt: (A) for listener itself (B) carried by reuqest_sock (C) sock_hold() in tcp_v[46]_rcv() While processing the req, (A) may disappear by close(listener). Also, (B) can disappear by accept(listener) once we put the req into the accept queue. So, we have to hold another refcnt (C) for the listener to prevent use-after-free. For socket migration, we call reuseport_migrate_sock() to select a listener with (A) and to increment the new listener's refcnt in tcp_v[46]_rcv(). This refcnt corresponds to (C) and is cleaned up later in tcp_v[46]_rcv(). Thus we have to take another refcnt (B) for the newly cloned request_sock. In inet_csk_complete_hashdance(), we hold the count (B), clone the req, and try to put the new req into the accept queue. By migrating req after winning the "own_req" race, we can avoid such a worst situation: CPU 1 looks up req1 CPU 2 looks up req1, unhashes it, then CPU 1 loses the race CPU 3 looks up req2, unhashes it, then CPU 2 loses the race ... Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Eric Dumazet <edumazet@google.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20210612123224.12525-8-kuniyu@amazon.co.jp
-rw-r--r--net/ipv4/inet_connection_sock.c34
-rw-r--r--net/ipv4/tcp_ipv4.c20
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv6/tcp_ipv6.c14
4 files changed, 58 insertions, 14 deletions
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f4b771e45ac1..0eea878edc30 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1114,12 +1114,40 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
struct request_sock *req, bool own_req)
{
if (own_req) {
- inet_csk_reqsk_queue_drop(sk, req);
- reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
- if (inet_csk_reqsk_queue_add(sk, req, child))
+ inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+ reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
+
+ if (sk != req->rsk_listener) {
+ /* another listening sk has been selected,
+ * migrate the req to it.
+ */
+ struct request_sock *nreq;
+
+ /* hold a refcnt for the nreq->rsk_listener
+ * which is assigned in inet_reqsk_clone()
+ */
+ sock_hold(sk);
+ nreq = inet_reqsk_clone(req, sk);
+ if (!nreq) {
+ inet_child_forget(sk, req, child);
+ goto child_put;
+ }
+
+ refcount_set(&nreq->rsk_refcnt, 1);
+ if (inet_csk_reqsk_queue_add(sk, nreq, child)) {
+ reqsk_migrate_reset(req);
+ reqsk_put(req);
+ return child;
+ }
+
+ reqsk_migrate_reset(nreq);
+ __reqsk_free(nreq);
+ } else if (inet_csk_reqsk_queue_add(sk, req, child)) {
return child;
+ }
}
/* Too bad, another child took ownership of the request, undo. */
+child_put:
bh_unlock_sock(child);
sock_put(child);
return NULL;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4f5b68a90be9..6cb8e269f1ab 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2002,13 +2002,21 @@ process:
goto csum_error;
}
if (unlikely(sk->sk_state != TCP_LISTEN)) {
- inet_csk_reqsk_queue_drop_and_put(sk, req);
- goto lookup;
+ nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb);
+ if (!nsk) {
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ goto lookup;
+ }
+ sk = nsk;
+ /* reuseport_migrate_sock() has already held one sk_refcnt
+ * before returning.
+ */
+ } else {
+ /* We own a reference on the listener, increase it again
+ * as we might lose it too soon.
+ */
+ sock_hold(sk);
}
- /* We own a reference on the listener, increase it again
- * as we might lose it too soon.
- */
- sock_hold(sk);
refcounted = true;
nsk = NULL;
if (!tcp_filter(sk, skb)) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7513ba45553d..f258a4c0da71 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -775,8 +775,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
goto listen_overflow;
if (own_req && rsk_drop_req(req)) {
- reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
- inet_csk_reqsk_queue_drop_and_put(sk, req);
+ reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
+ inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
return child;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4435fa342e7a..4d71464094b3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1664,10 +1664,18 @@ process:
goto csum_error;
}
if (unlikely(sk->sk_state != TCP_LISTEN)) {
- inet_csk_reqsk_queue_drop_and_put(sk, req);
- goto lookup;
+ nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb);
+ if (!nsk) {
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ goto lookup;
+ }
+ sk = nsk;
+ /* reuseport_migrate_sock() has already held one sk_refcnt
+ * before returning.
+ */
+ } else {
+ sock_hold(sk);
}
- sock_hold(sk);
refcounted = true;
nsk = NULL;
if (!tcp_filter(sk, skb)) {