From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
To: "David S . Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>,
Eric Dumazet <edumazet@google.com>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Martin KaFai Lau <kafai@fb.com>
Cc: Benjamin Herrenschmidt <benh@amazon.com>,
Kuniyuki Iwashima <kuniyu@amazon.co.jp>,
Kuniyuki Iwashima <kuni1840@gmail.com>, <bpf@vger.kernel.org>,
<netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: [PATCH v3 bpf-next 06/11] tcp: Migrate TCP_NEW_SYN_RECV requests at retransmitting SYN+ACKs.
Date: Wed, 21 Apr 2021 00:41:35 +0900 [thread overview]
Message-ID: <20210420154140.80034-7-kuniyu@amazon.co.jp> (raw)
In-Reply-To: <20210420154140.80034-1-kuniyu@amazon.co.jp>
As with the preceding patch, this patch changes reqsk_timer_handler() to
call reuseport_migrate_sock() and reqsk_clone() to migrate in-flight
requests at retransmitting SYN+ACKs. If we can select a new listener and
clone the request, we resume setting the SYN+ACK timer for the new req. If
we can set the timer, we call inet_ehash_insert() to unhash the old req and
put the new req into ehash.
The noteworthy point here is that by unhashing the old req, another CPU
processing it may lose the "own_req" race in tcp_v[46]_syn_recv_sock() and
drop the final ACK packet. However, the new timer will recover this
situation.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
---
net/core/request_sock.c | 1 +
net/ipv4/inet_connection_sock.c | 76 +++++++++++++++++++++++++++++----
2 files changed, 68 insertions(+), 9 deletions(-)
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 82cf9fbe2668..08c37ecd923b 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -151,6 +151,7 @@ struct request_sock *reqsk_clone(struct request_sock *req, struct sock *sk)
memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end,
req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end));
+ sk_node_init(&nreq_sk->sk_node);
nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
#ifdef CONFIG_XPS
nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 851992405826..dc984d1f352e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -695,10 +695,20 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req)
}
EXPORT_SYMBOL(inet_rtx_syn_ack);
+static void reqsk_queue_migrated(struct request_sock_queue *queue,
+ const struct request_sock *req)
+{
+ if (req->num_timeout == 0)
+ atomic_inc(&queue->young);
+ atomic_inc(&queue->qlen);
+}
+
static void reqsk_migrate_reset(struct request_sock *req)
{
+ req->saved_syn = NULL;
+ inet_rsk(req)->ireq_opt = NULL;
#if IS_ENABLED(CONFIG_IPV6)
- inet_rsk(req)->ipv6_opt = NULL;
+ inet_rsk(req)->pktopts = NULL;
#endif
}
@@ -741,16 +751,37 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
static void reqsk_timer_handler(struct timer_list *t)
{
- struct request_sock *req = from_timer(req, t, rsk_timer);
- struct sock *sk_listener = req->rsk_listener;
- struct net *net = sock_net(sk_listener);
- struct inet_connection_sock *icsk = inet_csk(sk_listener);
- struct request_sock_queue *queue = &icsk->icsk_accept_queue;
+ struct request_sock *req = from_timer(req, t, rsk_timer), *nreq = NULL, *oreq = req;
+ struct sock *sk_listener = req->rsk_listener, *nsk = NULL;
+ struct inet_connection_sock *icsk;
+ struct request_sock_queue *queue;
+ struct net *net;
int max_syn_ack_retries, qlen, expire = 0, resend = 0;
- if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
- goto drop;
+ if (inet_sk_state_load(sk_listener) != TCP_LISTEN) {
+ nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL);
+ if (!nsk)
+ goto drop;
+
+ nreq = reqsk_clone(req, nsk);
+ if (!nreq)
+ goto drop;
+
+ /* The new timer for the cloned req can decrease the 2
+ * by calling inet_csk_reqsk_queue_drop_and_put(), so
+ * hold another count to prevent use-after-free and
+ * call reqsk_put() just before return.
+ */
+ refcount_set(&nreq->rsk_refcnt, 2 + 1);
+ timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
+ reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req);
+
+ req = nreq;
+ sk_listener = nsk;
+ }
+ icsk = inet_csk(sk_listener);
+ net = sock_net(sk_listener);
max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
/* Normally all the openreqs are young and become mature
* (i.e. converted to established socket) for first timeout.
@@ -769,6 +800,7 @@ static void reqsk_timer_handler(struct timer_list *t)
* embrions; and abort old ones without pity, if old
* ones are about to clog our table.
*/
+ queue = &icsk->icsk_accept_queue;
qlen = reqsk_queue_len(queue);
if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) {
int young = reqsk_queue_len_young(queue) << 1;
@@ -793,10 +825,36 @@ static void reqsk_timer_handler(struct timer_list *t)
atomic_dec(&queue->young);
timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
mod_timer(&req->rsk_timer, jiffies + timeo);
+
+ if (!nreq)
+ return;
+
+ if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) {
+ /* delete timer */
+ inet_csk_reqsk_queue_drop(sk_listener, nreq);
+ goto drop;
+ }
+
+ reqsk_migrate_reset(oreq);
+ reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq);
+ reqsk_put(oreq);
+
+ reqsk_put(nreq);
return;
}
+
drop:
- inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
+ /* Even if we can clone the req, we may need not retransmit any more
+ * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another
+ * CPU may win the "own_req" race so that inet_ehash_insert() fails.
+ */
+ if (nreq) {
+ reqsk_migrate_reset(nreq);
+ reqsk_queue_removed(queue, nreq);
+ __reqsk_free(nreq);
+ }
+
+ inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
}
static void reqsk_queue_hash_req(struct request_sock *req,
--
2.30.2
next prev parent reply other threads:[~2021-04-20 15:44 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-20 15:41 [PATCH v3 bpf-next 00/11] Socket migration for SO_REUSEPORT Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 01/11] net: Introduce net.ipv4.tcp_migrate_req Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 02/11] tcp: Add num_closed_socks to struct sock_reuseport Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 03/11] tcp: Keep TCP_CLOSE sockets in the reuseport group Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 04/11] tcp: Add reuseport_migrate_sock() to select a new listener Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 05/11] tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues Kuniyuki Iwashima
2021-04-20 15:41 ` Kuniyuki Iwashima [this message]
2021-04-20 15:41 ` [PATCH v3 bpf-next 07/11] tcp: Migrate TCP_NEW_SYN_RECV requests at receiving the final ACK Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 08/11] bpf: Support BPF_FUNC_get_socket_cookie() for BPF_PROG_TYPE_SK_REUSEPORT Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 09/11] bpf: Support socket migration by eBPF Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 10/11] libbpf: Set expected_attach_type for BPF_PROG_TYPE_SK_REUSEPORT Kuniyuki Iwashima
2021-04-20 15:41 ` [PATCH v3 bpf-next 11/11] bpf: Test BPF_SK_REUSEPORT_SELECT_OR_MIGRATE Kuniyuki Iwashima
2021-04-20 22:57 ` Andrii Nakryiko
2021-04-21 11:34 ` Kuniyuki Iwashima
2021-04-20 16:43 ` [PATCH v3 bpf-next 00/11] Socket migration for SO_REUSEPORT Eric Dumazet
2021-04-21 11:30 ` Kuniyuki Iwashima
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210420154140.80034-7-kuniyu@amazon.co.jp \
--to=kuniyu@amazon.co.jp \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=benh@amazon.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kafai@fb.com \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).