diff options
| -rw-r--r-- | Documentation/networking/ip-sysctl.rst | 14 | ||||
| -rw-r--r-- | Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst | 1 | ||||
| -rw-r--r-- | include/net/netns/ipv4.h | 1 | ||||
| -rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 10 | ||||
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 4 |
5 files changed, 29 insertions, 1 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/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 3b6ba1d16921..e45222d5fc2e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -163,7 +163,8 @@ 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) + MSEC_PER_SEC; + 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(tcp_clock_ms(), reuse_thresh)))) { /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk @@ -3458,6 +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); |