netdev - [PATCH net-next 3/3] tcp: add hrtimer slack to sack compression

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]

Date:   Thu, 30 Apr 2020 10:35:43 -0700
From:   Eric Dumazet <edumazet@...gle.com>
To:     "David S . Miller" <davem@...emloft.net>
Cc:     netdev <netdev@...r.kernel.org>,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        Neal Cardwell <ncardwell@...gle.com>,
        Eric Dumazet <edumazet@...gle.com>,
        Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH net-next 3/3] tcp: add hrtimer slack to sack compression

Add a sysctl to control hrtimer slack, default of 100 usec.

This gives the opportunity to reduce system overhead,
and help very short RTT flows.

Signed-off-by: Eric Dumazet <edumazet@...gle.com>
Acked-by: Soheil Hassas Yeganeh <soheil@...gle.com>
Acked-by: Neal Cardwell <ncardwell@...gle.com>
---
 Documentation/networking/ip-sysctl.rst | 8 ++++++++
 include/net/netns/ipv4.h               | 1 +
 net/ipv4/sysctl_net_ipv4.c             | 7 +++++++
 net/ipv4/tcp_input.c                   | 5 +++--
 net/ipv4/tcp_ipv4.c                    | 1 +
 5 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 38f811d4b2f09fa81cd2ec22cefe95f9353858c9..bbefd5c6d96db4115a8aa7948a93868c0ae55a2f 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -651,6 +651,14 @@ tcp_comp_sack_delay_ns - LONG INTEGER
 
 	Default : 1,000,000 ns (1 ms)
 
+tcp_comp_sack_slack_ns - LONG INTEGER
+	This sysctl control the slack used when arming the
+	timer used by SACK compression. This gives extra time
+	for small RTT flows, and reduces system overhead by allowing
+	opportunistic reduction of timer interrupts.
+
+	Default : 100,000 ns (100 us)
+
 tcp_comp_sack_nr - INTEGER
 	Max number of SACK that can be compressed.
 	Using 0 disables SACK compression.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 5acdb4d414c4fe3cb96b62e6bf3500f447371247..9e36738c1fe164fa75cb6c4a0802773925f73b9a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -173,6 +173,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_rmem[3];
 	int sysctl_tcp_comp_sack_nr;
 	unsigned long sysctl_tcp_comp_sack_delay_ns;
+	unsigned long sysctl_tcp_comp_sack_slack_ns;
 	struct inet_timewait_death_row tcp_death_row;
 	int sysctl_max_syn_backlog;
 	int sysctl_tcp_fastopen;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 95ad71e76cc3f62348c416e296be777decbc1e12..3a628423d27bfe28d5dfc5b70c5b9f980275fc7f 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1329,6 +1329,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
+	{
+		.procname	= "tcp_comp_sack_slack_ns",
+		.data		= &init_net.ipv4.sysctl_tcp_comp_sack_slack_ns,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{
 		.procname	= "tcp_comp_sack_nr",
 		.data		= &init_net.ipv4.sysctl_tcp_comp_sack_nr,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ef921ecba4155abe9d078152ca8bd6a0be68317e..d68128a672ab05899d26eb9b1978c4a34023d51f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5324,8 +5324,9 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
 		      rtt * (NSEC_PER_USEC >> 3)/20);
 	sock_hold(sk);
-	hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay),
-		      HRTIMER_MODE_REL_PINNED_SOFT);
+	hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
+			       sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+			       HRTIMER_MODE_REL_PINNED_SOFT);
 }
 
 static inline void tcp_ack_snd_check(struct sock *sk)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 83a5d24e13b8c0079d80950acde13c232b4a845e..6c05f1ceb538cbb9981835440163485de2ccf716 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2780,6 +2780,7 @@ static int __net_init tcp_sk_init(struct net *net)
 		       sizeof(init_net.ipv4.sysctl_tcp_wmem));
 	}
 	net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC;
+	net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC;
 	net->ipv4.sysctl_tcp_comp_sack_nr = 44;
 	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
 	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
-- 
2.26.2.303.gf8c07b1a785-goog