This is a note to let you know that I've just added the patch titled
tcp: Use BPF timeout setting for SYN ACK RTO
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
tcp-use-bpf-timeout-setting-for-syn-ack-rto.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 51aa83486c6ba6445c1fd90207ab09714f7e1b99
Author: Akhmat Karakotov <hmukos@xxxxxxxxxxxxxx>
Date: Fri Jan 28 22:26:21 2022 +0300
tcp: Use BPF timeout setting for SYN ACK RTO
[ Upstream commit 5903123f662ed18483f05cac3f9e800a074c29ff ]
When setting RTO through BPF program, some SYN ACK packets were unaffected
and continued to use TCP_TIMEOUT_INIT constant. This patch adds timeout
option to struct request_sock. Option is initialized with TCP_TIMEOUT_INIT
and is reassigned through BPF using tcp_timeout_init call. SYN ACK
retransmits now use newly added timeout option.
Signed-off-by: Akhmat Karakotov <hmukos@xxxxxxxxxxxxxx>
Acked-by: Martin KaFai Lau <kafai@xxxxxx>
v2:
- Add timeout option to struct request_sock. Do not call
tcp_timeout_init on every syn ack retransmit.
v3:
- Use unsigned long for min. Bound tcp_timeout_init to TCP_RTO_MAX.
v4: - Refactor duplicate code by adding reqsk_timeout function.
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Stable-dep-of: ff46e3b44219 ("Fix race for duplicate reqsk on identical SYN")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index b6b7e210f9d7a..7794cf2b5ef50 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -284,6 +284,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
+static inline unsigned long
+reqsk_timeout(struct request_sock *req, unsigned long max_timeout)
+{
+ u64 timeout = (u64)req->timeout << req->num_timeout;
+
+ return (unsigned long)min_t(u64, timeout, max_timeout);
+}
+
static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
{
/* The below has to be done to allow calling inet_csk_destroy_sock */
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 29e41ff3ec933..144c39db9898a 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -70,6 +70,7 @@ struct request_sock {
struct saved_syn *saved_syn;
u32 secid;
u32 peer_secid;
+ u32 timeout;
};
static inline struct request_sock *inet_reqsk(const struct sock *sk)
@@ -104,6 +105,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
sk_node_init(&req_to_sk(req)->sk_node);
sk_tx_queue_clear(req_to_sk(req));
req->saved_syn = NULL;
+ req->timeout = 0;
req->num_timeout = 0;
req->num_retrans = 0;
req->sk = NULL;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 08923ed4278f0..30f8111f750b5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2362,7 +2362,7 @@ static inline u32 tcp_timeout_init(struct sock *sk)
if (timeout <= 0)
timeout = TCP_TIMEOUT_INIT;
- return timeout;
+ return min_t(int, timeout, TCP_RTO_MAX);
}
static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 27975a44d1f9d..43e370f45b81d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -889,12 +889,9 @@ static void reqsk_timer_handler(struct timer_list *t)
(!resend ||
!inet_rtx_syn_ack(sk_listener, req) ||
inet_rsk(req)->acked)) {
- unsigned long timeo;
-
if (req->num_timeout++ == 0)
atomic_dec(&queue->young);
- timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
- mod_timer(&req->rsk_timer, jiffies + timeo);
+ mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX));
if (!nreq)
return;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5ad7e6965a645..ca72dbaa27b46 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6769,6 +6769,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
ireq->ireq_state = TCP_NEW_SYN_RECV;
write_pnet(&ireq->ireq_net, sock_net(sk_listener));
ireq->ireq_family = sk_listener->sk_family;
+ req->timeout = TCP_TIMEOUT_INIT;
}
return req;
@@ -6991,9 +6992,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
sock_put(fastopen_sk);
} else {
tcp_rsk(req)->tfo_listener = false;
- if (!want_cookie)
- inet_csk_reqsk_queue_hash_add(sk, req,
- tcp_timeout_init((struct sock *)req));
+ if (!want_cookie) {
+ req->timeout = tcp_timeout_init((struct sock *)req);
+ inet_csk_reqsk_queue_hash_add(sk, req, req->timeout);
+ }
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :
TCP_SYNACK_COOKIE,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 2606a5571116a..d84b71f70766b 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -593,7 +593,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
* it can be estimated (approximately)
* from another data.
*/
- tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
+ tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ;
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
@@ -632,8 +632,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
!inet_rtx_syn_ack(sk, req)) {
unsigned long expires = jiffies;
- expires += min(TCP_TIMEOUT_INIT << req->num_timeout,
- TCP_RTO_MAX);
+ expires += reqsk_timeout(req, TCP_RTO_MAX);
if (!fastopen)
mod_timer_pending(&req->rsk_timer, expires);
else
