[NETNS][IPV6]: Make sysctls route per namespace.

All the sysctl concerning the routes are moved to the network
namespace structure. A helper function is called to initialize the
variables.

Because the ipv6 protocol is not yet per namespace, the variables are
accessed relatively from the network namespace.

Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 56 insertions, 36 deletions

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 1a0698b1e86c..faac0eee1ef3 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -43,8 +43,6 @@ extern struct rt6_info	ip6_prohibit_entry;
 extern struct rt6_info  ip6_blk_hole_entry;
 #endif
 
-extern int ip6_rt_gc_interval;
-
 extern void                     ip6_route_input(struct sk_buff *skb);
 
 extern struct dst_entry *       ip6_route_output(struct sock *sk,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index ea4a71ac23d4..050d08809ef2 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -15,6 +15,14 @@ struct netns_sysctl_ipv6 {
 #endif
         struct inet_frags_ctl frags;
         int bindv6only;
+        int flush_delay;
+        int ip6_rt_max_size;
+        int ip6_rt_gc_min_interval;
+        int ip6_rt_gc_timeout;
+        int ip6_rt_gc_interval;
+        int ip6_rt_gc_elasticity;
+        int ip6_rt_mtu_expires;
+        int ip6_rt_min_advmss;
 };
 
 struct netns_ipv6 {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c4a1882fa80f..3aea84a1822a 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -726,6 +726,14 @@ static int inet6_net_init(struct net *net)
         net->ipv6.sysctl.frags.low_thresh = 192 * 1024;
         net->ipv6.sysctl.frags.timeout = IPV6_FRAG_TIMEOUT;
         net->ipv6.sysctl.frags.secret_interval = 10 * 60 * HZ;
+        net->ipv6.sysctl.flush_delay = 0;
+        net->ipv6.sysctl.ip6_rt_max_size = 4096;
+        net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
+        net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
+        net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
+        net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
+        net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
+        net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
         ipv6_frag_sysctl_init(net);
 
         return 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7165a5e90f45..0e83164aa3e6 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -681,13 +681,15 @@ static __inline__ void fib6_start_gc(struct rt6_info *rt)
 {
         if (ip6_fib_timer.expires == 0 &&
             (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE)))
-                mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
+                mod_timer(&ip6_fib_timer, jiffies +
+                          init_net.ipv6.sysctl.ip6_rt_gc_interval);
 }
 
 void fib6_force_start_gc(void)
 {
         if (ip6_fib_timer.expires == 0)
-                mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
+                mod_timer(&ip6_fib_timer, jiffies +
+                          init_net.ipv6.sysctl.ip6_rt_gc_interval);
 }
 
 /*
@@ -1447,7 +1449,8 @@ void fib6_run_gc(unsigned long dummy)
 {
         if (dummy != ~0UL) {
                 spin_lock_bh(&fib6_gc_lock);
-                gc_args.timeout = dummy ? (int)dummy : ip6_rt_gc_interval;
+                gc_args.timeout = dummy ? (int)dummy :
+                        init_net.ipv6.sysctl.ip6_rt_gc_interval;
         } else {
                 local_bh_disable();
                 if (!spin_trylock(&fib6_gc_lock)) {
@@ -1455,7 +1458,7 @@ void fib6_run_gc(unsigned long dummy)
                         local_bh_enable();
                         return;
                 }
-                gc_args.timeout = ip6_rt_gc_interval;
+                gc_args.timeout = init_net.ipv6.sysctl.ip6_rt_gc_interval;
         }
         gc_args.more = 0;
 
@@ -1463,7 +1466,8 @@ void fib6_run_gc(unsigned long dummy)
         fib6_clean_all(fib6_age, 0, NULL);
 
         if (gc_args.more)
-                mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval);
+                mod_timer(&ip6_fib_timer, jiffies +
+                          init_net.ipv6.sysctl.ip6_rt_gc_interval);
         else {
                 del_timer(&ip6_fib_timer);
                 ip6_fib_timer.expires = 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0c7382f4fb85..d2b3cf695aff 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -73,14 +73,6 @@
 
 #define CLONE_OFFLINK_ROUTE 0
 
-static int ip6_rt_max_size = 4096;
-static int ip6_rt_gc_min_interval = HZ / 2;
-static int ip6_rt_gc_timeout = 60*HZ;
-int ip6_rt_gc_interval = 30*HZ;
-static int ip6_rt_gc_elasticity = 9;
-static int ip6_rt_mtu_expires = 10*60*HZ;
-static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
-
 static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
 static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
 static struct dst_entry *ip6_negative_advice(struct dst_entry *);
@@ -894,8 +886,8 @@ static inline unsigned int ipv6_advmss(unsigned int mtu)
 {
         mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
 
-        if (mtu < ip6_rt_min_advmss)
-                mtu = ip6_rt_min_advmss;
+        if (mtu < init_net.ipv6.sysctl.ip6_rt_min_advmss)
+                mtu = init_net.ipv6.sysctl.ip6_rt_min_advmss;
 
         /*
          * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
@@ -995,19 +987,19 @@ static int ip6_dst_gc(void)
         static unsigned long last_gc;
         unsigned long now = jiffies;
 
-        if (time_after(last_gc + ip6_rt_gc_min_interval, now) &&
-            atomic_read(&ip6_dst_ops.entries) <= ip6_rt_max_size)
+        if (time_after(last_gc + init_net.ipv6.sysctl.ip6_rt_gc_min_interval, now) &&
+            atomic_read(&ip6_dst_ops.entries) <= init_net.ipv6.sysctl.ip6_rt_max_size)
                 goto out;
 
         expire++;
         fib6_run_gc(expire);
         last_gc = now;
         if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh)
-                expire = ip6_rt_gc_timeout>>1;
+                expire = init_net.ipv6.sysctl.ip6_rt_gc_timeout>>1;
 
 out:
-        expire -= expire>>ip6_rt_gc_elasticity;
-        return (atomic_read(&ip6_dst_ops.entries) > ip6_rt_max_size);
+        expire -= expire>>init_net.ipv6.sysctl.ip6_rt_gc_elasticity;
+        return (atomic_read(&ip6_dst_ops.entries) > init_net.ipv6.sysctl.ip6_rt_max_size);
 }
 
 /* Clean host part of a prefix. Not necessary in radix tree,
@@ -1513,7 +1505,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
                 rt->u.dst.metrics[RTAX_MTU-1] = pmtu;
                 if (allfrag)
                         rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
-                dst_set_expires(&rt->u.dst, ip6_rt_mtu_expires);
+                dst_set_expires(&rt->u.dst, init_net.ipv6.sysctl.ip6_rt_mtu_expires);
                 rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
                 goto out;
         }
@@ -1539,7 +1531,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
                  * which is 10 mins. After 10 mins the decreased pmtu is expired
                  * and detecting PMTU increase will be automatically happened.
                  */
-                dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires);
+                dst_set_expires(&nrt->u.dst, init_net.ipv6.sysctl.ip6_rt_mtu_expires);
                 nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;
 
                 ip6_ins_rt(nrt);
@@ -2395,15 +2387,14 @@ static inline void ipv6_route_proc_fini(struct net *net)
 
 #ifdef CONFIG_SYSCTL
 
-static int flush_delay;
-
 static
 int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
                               void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+        int delay = init_net.ipv6.sysctl.flush_delay;
         if (write) {
                 proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
-                fib6_run_gc(flush_delay <= 0 ? ~0UL : (unsigned long)flush_delay);
+                fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay);
                 return 0;
         } else
                 return -EINVAL;
@@ -2412,7 +2403,7 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
 ctl_table ipv6_route_table_template[] = {
         {
                 .procname       =       "flush",
-                .data           =       &flush_delay,
+                .data           =       &init_net.ipv6.sysctl.flush_delay,
                 .maxlen         =       sizeof(int),
                 .mode           =       0200,
                 .proc_handler   =       &ipv6_sysctl_rtcache_flush
@@ -2428,7 +2419,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_MAX_SIZE,
                 .procname       =       "max_size",
-                .data           =       &ip6_rt_max_size,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_max_size,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec,
@@ -2436,7 +2427,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_GC_MIN_INTERVAL,
                 .procname       =       "gc_min_interval",
-                .data           =       &ip6_rt_gc_min_interval,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_jiffies,
@@ -2445,7 +2436,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_GC_TIMEOUT,
                 .procname       =       "gc_timeout",
-                .data           =       &ip6_rt_gc_timeout,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_gc_timeout,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_jiffies,
@@ -2454,7 +2445,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_GC_INTERVAL,
                 .procname       =       "gc_interval",
-                .data           =       &ip6_rt_gc_interval,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_gc_interval,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_jiffies,
@@ -2463,7 +2454,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_GC_ELASTICITY,
                 .procname       =       "gc_elasticity",
-                .data           =       &ip6_rt_gc_elasticity,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_jiffies,
@@ -2472,7 +2463,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_MTU_EXPIRES,
                 .procname       =       "mtu_expires",
-                .data           =       &ip6_rt_mtu_expires,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_mtu_expires,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_jiffies,
@@ -2481,7 +2472,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_MIN_ADVMSS,
                 .procname       =       "min_adv_mss",
-                .data           =       &ip6_rt_min_advmss,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_min_advmss,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_jiffies,
@@ -2490,7 +2481,7 @@ ctl_table ipv6_route_table_template[] = {
         {
                 .ctl_name       =       NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,
                 .procname       =       "gc_min_interval_ms",
-                .data           =       &ip6_rt_gc_min_interval,
+                .data           =       &init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
                 .maxlen         =       sizeof(int),
                 .mode           =       0644,
                 .proc_handler   =       &proc_dointvec_ms_jiffies,
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index d223159638d3..b4ba422f2714 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -113,7 +113,18 @@ static int ipv6_sysctl_net_init(struct net *net)
         if (!ipv6_icmp_table)
                 goto out_ipv6_route_table;
 
+        ipv6_route_table[0].data = &net->ipv6.sysctl.flush_delay;
+        /* ipv6_route_table[1].data will be handled when we have
+           routes per namespace */
+        ipv6_route_table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
+        ipv6_route_table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
+        ipv6_route_table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout;
+        ipv6_route_table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval;
+        ipv6_route_table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity;
+        ipv6_route_table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
+        ipv6_route_table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
         ipv6_table[0].child = ipv6_route_table;
+
         ipv6_table[1].child = ipv6_icmp_table;
 
         ipv6_table[2].data = &net->ipv6.sysctl.bindv6only;