net/tcp: Fix tcp memory limits initialization when !CONFIG_SYSCTL

sysctl_tcp_mem() initialization was moved to sysctl_tcp_ipv4.c
in commit 3dc43e3e4d0b52197d3205214fe8f162f9e0c334, since it
became a per-ns value.

That code, however, will never run when CONFIG_SYSCTL is
disabled, leading to bogus values on those fields - causing hung
TCP sockets.

This patch fixes it by keeping an initialization code in
tcp_init(). It will be overwritten by the first net namespace
init if CONFIG_SYSCTL is compiled in, and do the right thing if
it is compiled out.

It is also named properly as tcp_init_mem(), to properly signal
its non-sysctl side effect on TCP limits.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Glauber Costa <glommer@parallels.com>
Cc: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/4F22D05A.8030604@parallels.com
[ renamed the function, tidied up the changelog a bit ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0118ea999f67a882f6e4e389aa9f2b685e571955..d49db0113a069d4b085ffb62d413d5983cfb2445 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -311,6 +311,8 @@ extern struct proto tcp_prot;
 #define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val)
 #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
 
+extern void tcp_init_mem(struct net *net);
+
 extern void tcp_v4_err(struct sk_buff *skb, u32);
 
 extern void tcp_shutdown (struct sock *sk, int how);

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4aa7e9dc0cbb961ab75fedea9944304a609dd2fc..4cb9cd2f2c390fc14289f918da8098af0549f5f2 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -814,6 +814,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 
        net->ipv4.sysctl_rt_cache_rebuild_count = 4;
 
+       tcp_init_mem(net);
        limit = nr_free_buffer_pages() / 8;
        limit = max(limit, 128UL);
        net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9bcdec3ad772171a6aa71584b86bc5c1c998db83..06373b4a449a158451d3c99ec482b80e65a0ab87 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3216,6 +3216,16 @@ static int __init set_thash_entries(char *str)
 }
 __setup("thash_entries=", set_thash_entries);
 
+void tcp_init_mem(struct net *net)
+{
+       /* Set per-socket limits to no more than 1/128 the pressure threshold */
+       unsigned long limit = nr_free_buffer_pages() / 8;
+       limit = max(limit, 128UL);
+       net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
+       net->ipv4.sysctl_tcp_mem[1] = limit;
+       net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+}
+
 void __init tcp_init(void)
 {
        struct sk_buff *skb = NULL;
@@ -3276,9 +3286,9 @@ void __init tcp_init(void)
        sysctl_tcp_max_orphans = cnt / 2;
        sysctl_max_syn_backlog = max(128, cnt / 256);
 
-       /* Set per-socket limits to no more than 1/128 the pressure threshold */
-       limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
-               << (PAGE_SHIFT - 7);
+       tcp_init_mem(&init_net);
+       limit = nr_free_buffer_pages() / 8;
+       limit = max(limit, 128UL);
        max_share = min(4UL*1024*1024, limit);
 
        sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;