ipv4: Namespaceify tcp_tw_reuse knob

Different namespaces might have different requirements to reuse
TIME-WAIT sockets for new connections. This might be required in
cases where different namespace applications are in place which
require TIME_WAIT socket connections to be reduced independently
of the host.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f0cf5a1b777e4d4c37c0b927f5c9ee7bfd78fd64..0378e88f6fd3d6076f0393d67343cdb92643dbb4 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -110,6 +110,7 @@ struct netns_ipv4 {
        int sysctl_tcp_orphan_retries;
        int sysctl_tcp_fin_timeout;
        unsigned int sysctl_tcp_notsent_lowat;
+       int sysctl_tcp_tw_reuse;
 
        int sysctl_igmp_max_memberships;
        int sysctl_igmp_max_msf;

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 207147b4c6b2a126af103e715d99c8914b290d48..6061963cca98ed84ef09f788ee0ebdc3867a07c8 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -252,7 +252,6 @@ extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
 extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 80bc36b25de21d5e6b1c3e6f6001258b38656d41..22cbd61079b5a9d2661583b7d96eea46eddb685d 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -432,13 +432,6 @@ static struct ctl_table ipv4_table[] = {
                .extra1         = &tcp_adv_win_scale_min,
                .extra2         = &tcp_adv_win_scale_max,
        },
-       {
-               .procname       = "tcp_tw_reuse",
-               .data           = &sysctl_tcp_tw_reuse,
-               .maxlen         = sizeof(int),
-               .mode           = 0644,
-               .proc_handler   = proc_dointvec
-       },
        {
                .procname       = "tcp_frto",
                .data           = &sysctl_tcp_frto,
@@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
+       {
+               .procname       = "tcp_tw_reuse",
+               .data           = &init_net.ipv4.sysctl_tcp_tw_reuse,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec
+       },
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
        {
                .procname       = "fib_multipath_use_neigh",

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30d81f533ada5708a61155b589e3835d9af4128d..fe9da4fb96bf967ab27f5179fc5a9ac3576cc693 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,7 +84,6 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -120,7 +119,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
           and use initial timestamp retrieved from peer table.
         */
        if (tcptw->tw_ts_recent_stamp &&
-           (!twp || (sysctl_tcp_tw_reuse &&
+           (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
                             get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
                tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
                if (tp->write_seq == 0)
@@ -2456,6 +2455,7 @@ static int __net_init tcp_sk_init(struct net *net)
        net->ipv4.sysctl_tcp_orphan_retries = 0;
        net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
        net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+       net->ipv4.sysctl_tcp_tw_reuse = 0;
 
        return 0;
 fail: