ipv4: Namespaceify tcp_max_syn_backlog knob

Different namespace application might require different maximal
number of remembered connection requests.

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 fffd384..8e3f5b6 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -122,6 +122,7 @@ struct netns_ipv4 {
        unsigned int sysctl_tcp_notsent_lowat;
        int sysctl_tcp_tw_reuse;
        struct inet_timewait_death_row tcp_death_row;
+       int sysctl_max_syn_backlog;
 
        int sysctl_igmp_max_memberships;
        int sysctl_igmp_max_msf;

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 6ebe13e..a12a5d2 100644 (file)
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -1,7 +1,7 @@
 /*
  * NET         Generic infrastructure for Network protocols.
  *
- *             Definitions for request_sock 
+ *             Definitions for request_sock
  *
  * Authors:    Arnaldo Carvalho de Melo <acme@conectiva.com.br>
  *
@@ -123,8 +123,6 @@ static inline void reqsk_put(struct request_sock *req)
                reqsk_free(req);
 }
 
-extern int sysctl_max_syn_backlog;
-
 /*
  * For a TCP Fast Open listener -
  *     lock - protects the access to all the reqsk, which is co-owned by

diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 5d26056..9b8727c 100644 (file)
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -34,8 +34,6 @@
  * and it will increase in proportion to the memory of machine.
  * Note : Dont forget somaxconn that may limit backlog too.
  */
-int sysctl_max_syn_backlog = 256;
-EXPORT_SYMBOL(sysctl_max_syn_backlog);
 
 void reqsk_queue_alloc(struct request_sock_queue *queue)
 {

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 66f8f1b..134d8e1 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -324,13 +324,6 @@ static struct ctl_table ipv4_table[] = {
                .proc_handler   = proc_dointvec
        },
        {
-               .procname       = "tcp_max_syn_backlog",
-               .data           = &sysctl_max_syn_backlog,
-               .maxlen         = sizeof(int),
-               .mode           = 0644,
-               .proc_handler   = proc_dointvec
-       },
-       {
                .procname       = "inet_peer_threshold",
                .data           = &inet_peer_threshold,
                .maxlen         = sizeof(int),
@@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec
        },
+       {
+               .procname       = "tcp_max_syn_backlog",
+               .data           = &init_net.ipv4.sysctl_max_syn_backlog,
+               .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.c b/net/ipv4/tcp.c
index 7f0d81c..2e3807d 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3378,9 +3378,7 @@ void __init tcp_init(void)
 
 
        cnt = tcp_hashinfo.ehash_mask + 1;
-
        sysctl_tcp_max_orphans = cnt / 2;
-       sysctl_max_syn_backlog = max(128, cnt / 256);
 
        tcp_init_mem();
        /* Set per-socket limits to no more than 1/128 the pressure threshold */

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c614802..ec6d843 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6377,8 +6377,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
                }
                /* Kill the following clause, if you dislike this way. */
                else if (!net->ipv4.sysctl_tcp_syncookies &&
-                        (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
-                         (sysctl_max_syn_backlog >> 2)) &&
+                        (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+                         (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
                         !tcp_peer_is_proven(req, dst, false,
                                             tmp_opt.saw_tstamp)) {
                        /* Without syncookies last quarter of

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 56b5f49..7e4be4f 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2419,7 +2419,7 @@ static void __net_exit tcp_sk_exit(struct net *net)
 
 static int __net_init tcp_sk_init(struct net *net)
 {
-       int res, cpu;
+       int res, cpu, cnt;
 
        net->ipv4.tcp_sk = alloc_percpu(struct sock *);
        if (!net->ipv4.tcp_sk)
@@ -2458,10 +2458,13 @@ static int __net_init tcp_sk_init(struct net *net)
        net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
        net->ipv4.sysctl_tcp_tw_reuse = 0;
 
+       cnt = tcp_hashinfo.ehash_mask + 1;
        net->ipv4.tcp_death_row.sysctl_tw_recycle = 0;
-       net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (tcp_hashinfo.ehash_mask + 1) / 2;
+       net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2;
        net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
+       net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+
        return 0;
 fail:
        tcp_sk_exit(net);