Merge branch 'make-time-wait-reuse-delay-deterministic-and-configurable'

Jakub Sitnicki says:

====================
Make TIME-WAIT reuse delay deterministic and configurable

This patch set is an effort to enable faster reuse of TIME-WAIT sockets.
We have recently talked about the motivation and the idea at Plumbers [1].

Experiment in production
------------------------

We are restarting our experiment on a small set of production nodes as the
code has slightly changed since v1 [2], and there are still a few weeks of
development window to soak the changes. We will report back if we observe
any regressions.

Packetdrill tests
-----------------

The packetdrill tests for TIME-WAIT reuse [3] did not change since v1.
Although we are not touching PAWS code any more, I would still like to add
tests to cover PAWS reject after TW reuse. This, however, requires patching
packetdrill as I mentioned in the last cover letter [2].

[1] https://lpc.events/event/18/contributions/1962/
[2] https://lore.kernel.org/r/20241113-jakub-krn-909-poc-msec-tw-tstamp-v2-0-b0a335247304@cloudflare.com
[3] https://github.com/google/packetdrill/pull/90

v1: https://lore.kernel.org/20241204-jakub-krn-909-poc-msec-tw-tstamp-v1-0-8b54467a0f34@cloudflare.com
RFCv2: https://lore.kernel.org/20241113-jakub-krn-909-poc-msec-tw-tstamp-v2-0-b0a335247304@cloudflare.com
RFCv1: https://lore.kernel.org/20240819-jakub-krn-909-poc-msec-tw-tstamp-v1-1-6567b5006fbe@cloudflare.com
====================

Link: https://patch.msgid.link/20241209-jakub-krn-909-poc-msec-tw-tstamp-v2-0-66aca0eed03e@cloudflare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 41 insertions, 3 deletions

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index eacf8983e230..2f2b00295836 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1000,6 +1000,20 @@ tcp_tw_reuse - INTEGER
 
 	Default: 2
 
+tcp_tw_reuse_delay - UNSIGNED INTEGER
+        The delay in milliseconds before a TIME-WAIT socket can be reused by a
+        new connection, if TIME-WAIT socket reuse is enabled. The actual reuse
+        threshold is within [N, N+1] range, where N is the requested delay in
+        milliseconds, to ensure the delay interval is never shorter than the
+        configured value.
+
+        This setting contains an assumption about the other TCP timestamp clock
+        tick interval. It should not be set to a value lower than the peer's
+        clock tick for PAWS (Protection Against Wrapped Sequence numbers)
+        mechanism work correctly for the reused connection.
+
+        Default: 1000 (milliseconds)
+
 tcp_window_scaling - BOOLEAN
 	Enable window scaling as defined in RFC1323.
 
diff --git a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
index 629da6dc6d74..de0263302f16 100644
--- a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
+++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
@@ -79,6 +79,7 @@ u8                              sysctl_tcp_retries1
 u8                              sysctl_tcp_retries2
 u8                              sysctl_tcp_orphan_retries
 u8                              sysctl_tcp_tw_reuse                                                                  timewait_sock_ops
+unsigned_int                    sysctl_tcp_tw_reuse_delay                                                            timewait_sock_ops
 int                             sysctl_tcp_fin_timeout                                                               TCP_LAST_ACK/tcp_rcv_state_process
 unsigned_int                    sysctl_tcp_notsent_lowat                     read_mostly                             tcp_notsent_lowat/tcp_stream_memory_free
 u8                              sysctl_tcp_sack                                                                      tcp_syn_options
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 62c0a7e65d6b..67a313575780 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -74,6 +74,10 @@ struct inet_timewait_sock {
 				tw_tos		: 8;
 	u32			tw_txhash;
 	u32			tw_priority;
+	/**
+	 * @tw_reuse_stamp: Time of entry into %TCP_TIME_WAIT state in msec.
+	 */
+	u32			tw_entry_stamp;
 	struct timer_list	tw_timer;
 	struct inet_bind_bucket	*tw_tb;
 	struct inet_bind2_bucket	*tw_tb2;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 3c014170e001..46452da35206 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -175,6 +175,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_retries2;
 	u8 sysctl_tcp_orphan_retries;
 	u8 sysctl_tcp_tw_reuse;
+	unsigned int sysctl_tcp_tw_reuse_delay;
 	int sysctl_tcp_fin_timeout;
 	u8 sysctl_tcp_sack;
 	u8 sysctl_tcp_window_scaling;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a79b2a52ce01..42cb5dc9cb24 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,6 +45,7 @@ static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024;
 static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX;
 static int tcp_plb_max_rounds = 31;
 static int tcp_plb_max_cong_thresh = 256;
+static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -1066,6 +1067,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra2		= SYSCTL_TWO,
 	},
 	{
+		.procname	= "tcp_tw_reuse_delay",
+		.data		= &init_net.ipv4.sysctl_tcp_tw_reuse_delay,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &tcp_tw_reuse_delay_max,
+	},
+	{
 		.procname	= "tcp_max_syn_backlog",
 		.data		= &init_net.ipv4.sysctl_max_syn_backlog,
 		.maxlen		= sizeof(int),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a38c8b1f44db..e45222d5fc2e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -120,6 +120,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int ts_recent_stamp;
+	u32 reuse_thresh;
 
 	if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2)
 		reuse = 0;
@@ -162,9 +163,10 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
+	reuse_thresh = READ_ONCE(tw->tw_entry_stamp) +
+		       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse_delay);
 	if (ts_recent_stamp &&
-	    (!twp || (reuse && time_after32(ktime_get_seconds(),
-					    ts_recent_stamp)))) {
+	    (!twp || (reuse && time_after32(tcp_clock_ms(), reuse_thresh)))) {
 		/* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk
 		 * and releasing the bucket lock.
 		 */
@@ -3457,6 +3459,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
 	net->ipv4.sysctl_tcp_tw_reuse = 2;
+	net->ipv4.sysctl_tcp_tw_reuse_delay = 1 * MSEC_PER_SEC;
 	net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1;
 
 	refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7121d8573928..b089b08e9617 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -157,8 +157,11 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 				    rcv_nxt);
 
 		if (tmp_opt.saw_tstamp) {
+			u64 ts = tcp_clock_ms();
+
+			WRITE_ONCE(tw->tw_entry_stamp, ts);
 			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
-				  ktime_get_seconds());
+				   div_u64(ts, MSEC_PER_SEC));
 			WRITE_ONCE(tcptw->tw_ts_recent,
 				   tmp_opt.rcv_tsval);
 		}
@@ -316,6 +319,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		tw->tw_mark		= sk->sk_mark;
 		tw->tw_priority		= READ_ONCE(sk->sk_priority);
 		tw->tw_rcv_wscale	= tp->rx_opt.rcv_wscale;
+		/* refreshed when we enter true TIME-WAIT state */
+		tw->tw_entry_stamp	= tcp_time_stamp_ms(tp);
 		tcptw->tw_rcv_nxt	= tp->rcv_nxt;
 		tcptw->tw_snd_nxt	= tp->snd_nxt;
 		tcptw->tw_rcv_wnd	= tcp_receive_window(tp);