#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
+#include <linux/workqueue.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
+#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/route.h>
#define RTprint(a...) printk(KERN_DEBUG a)
static struct timer_list rt_flush_timer;
-static struct timer_list rt_periodic_timer;
+static void rt_check_expire(struct work_struct *work);
+static DECLARE_DELAYED_WORK(expires_work, rt_check_expire);
static struct timer_list rt_secret_timer;
/*
static struct rt_hash_bucket *rt_hash_table;
static unsigned rt_hash_mask;
-static int rt_hash_log;
+static unsigned int rt_hash_log;
static unsigned int rt_hash_rnd;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- struct seq_file *seq;
- int rc = -ENOMEM;
- struct rt_cache_iter_state *s;
-
- s = kzalloc(sizeof(*s), GFP_KERNEL);
- if (!s)
- goto out;
- rc = seq_open(file, &rt_cache_seq_ops);
- if (rc)
- goto out_kfree;
- seq = file->private_data;
- seq->private = s;
-out:
- return rc;
-out_kfree:
- kfree(s);
- goto out;
+ return seq_open_private(file, &rt_cache_seq_ops,
+ sizeof(struct rt_cache_iter_state));
}
static const struct file_operations rt_cache_seq_fops = {
(fl1->iif ^ fl2->iif)) == 0;
}
-/* This runs via a timer and thus is always in BH context. */
-static void rt_check_expire(unsigned long dummy)
+static void rt_check_expire(struct work_struct *work)
{
static unsigned int rover;
unsigned int i = rover, goal;
struct rtable *rth, **rthp;
- unsigned long now = jiffies;
u64 mult;
mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
if (ip_rt_gc_timeout > 1)
do_div(mult, ip_rt_gc_timeout);
goal = (unsigned int)mult;
- if (goal > rt_hash_mask) goal = rt_hash_mask + 1;
+ if (goal > rt_hash_mask)
+ goal = rt_hash_mask + 1;
for (; goal > 0; goal--) {
unsigned long tmo = ip_rt_gc_timeout;
i = (i + 1) & rt_hash_mask;
rthp = &rt_hash_table[i].chain;
- if (*rthp == 0)
+ if (need_resched())
+ cond_resched();
+
+ if (*rthp == NULL)
continue;
- spin_lock(rt_hash_lock_addr(i));
+ spin_lock_bh(rt_hash_lock_addr(i));
while ((rth = *rthp) != NULL) {
if (rth->u.dst.expires) {
/* Entry is expired even if it is in use */
- if (time_before_eq(now, rth->u.dst.expires)) {
+ if (time_before_eq(jiffies, rth->u.dst.expires)) {
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
continue;
*rthp = rth->u.dst.rt_next;
rt_free(rth);
}
- spin_unlock(rt_hash_lock_addr(i));
-
- /* Fallback loop breaker. */
- if (time_after(jiffies, now))
- break;
+ spin_unlock_bh(rt_hash_lock_addr(i));
}
rover = i;
- mod_timer(&rt_periodic_timer, jiffies + ip_rt_gc_interval);
+ schedule_delayed_work(&expires_work, ip_rt_gc_interval);
}
/* This can run from both BH and non-BH contexts, the latter
*/
rcu_assign_pointer(rt_hash_table[hash].chain, rth);
- rth->u.dst.__use++;
- dst_hold(&rth->u.dst);
- rth->u.dst.lastuse = now;
+ dst_use(&rth->u.dst, now);
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
rt->fl.oif);
#if RT_CACHE_DEBUG >= 1
- printk(KERN_DEBUG "ip_rt_advice: redirect to "
+ printk(KERN_DEBUG "ipv4_negative_advice: redirect to "
"%u.%u.%u.%u/%02x dropped\n",
NIPQUAD(rt->rt_dst), rt->fl.fl4_tos);
#endif
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
+ IP_INC_STATS_BH(IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
{
struct rtable *rt = (struct rtable *) dst;
struct in_device *idev = rt->idev;
- if (dev != &loopback_dev && idev && idev->dev == dev) {
- struct in_device *loopback_idev = in_dev_get(&loopback_dev);
+ if (dev != init_net.loopback_dev && idev && idev->dev == dev) {
+ struct in_device *loopback_idev = in_dev_get(init_net.loopback_dev);
if (loopback_idev) {
rt->idev = loopback_idev;
in_dev_put(idev);
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = &loopback_dev;
+ rth->u.dst.dev = init_net.loopback_dev;
dev_hold(rth->u.dst.dev);
rth->idev = in_dev_get(rth->u.dst.dev);
rth->fl.oif = 0;
if (res.type == RTN_LOCAL) {
int result;
result = fib_validate_source(saddr, daddr, tos,
- loopback_dev.ifindex,
+ init_net.loopback_dev->ifindex,
dev, &spec_dst, &itag);
if (result < 0)
goto martian_source;
goto martian_destination;
err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos);
- if (err == -ENOBUFS)
- goto e_nobufs;
- if (err == -EINVAL)
- goto e_inval;
-
done:
in_dev_put(in_dev);
if (free_res)
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = &loopback_dev;
+ rth->u.dst.dev = init_net.loopback_dev;
dev_hold(rth->u.dst.dev);
rth->idev = in_dev_get(rth->u.dst.dev);
rth->rt_gateway = daddr;
RT_CACHE_STAT_INC(in_no_route);
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
res.type = RTN_UNREACHABLE;
+ if (err == -ESRCH)
+ err = -ENETUNREACH;
goto local_input;
/*
rth->fl.oif == 0 &&
rth->fl.mark == skb->mark &&
rth->fl.fl4_tos == tos) {
- rth->u.dst.lastuse = jiffies;
- dst_hold(&rth->u.dst);
- rth->u.dst.__use++;
+ dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
skb->dst = (struct dst_entry*)rth;
RT_SCOPE_UNIVERSE),
} },
.mark = oldflp->mark,
- .iif = loopback_dev.ifindex,
+ .iif = init_net.loopback_dev->ifindex,
.oif = oldflp->oif };
struct fib_result res;
unsigned flags = 0;
if (oldflp->oif) {
- dev_out = dev_get_by_index(oldflp->oif);
+ dev_out = dev_get_by_index(&init_net, oldflp->oif);
err = -ENODEV;
if (dev_out == NULL)
goto out;
fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK);
if (dev_out)
dev_put(dev_out);
- dev_out = &loopback_dev;
+ dev_out = init_net.loopback_dev;
dev_hold(dev_out);
- fl.oif = loopback_dev.ifindex;
+ fl.oif = init_net.loopback_dev->ifindex;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
fl.fl4_src = fl.fl4_dst;
if (dev_out)
dev_put(dev_out);
- dev_out = &loopback_dev;
+ dev_out = init_net.loopback_dev;
dev_hold(dev_out);
fl.oif = dev_out->ifindex;
if (res.fi)
rth->fl.mark == flp->mark &&
!((rth->fl.fl4_tos ^ flp->fl4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK))) {
- rth->u.dst.lastuse = jiffies;
- dst_hold(&rth->u.dst);
- rth->u.dst.__use++;
+ dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
*rp = rth;
if (iif) {
struct net_device *dev;
- dev = __dev_get_by_index(iif);
+ dev = __dev_get_by_index(&init_net, iif);
if (dev == NULL) {
err = -ENODEV;
goto errout_free;
offset /= sizeof(u32);
if (length > 0) {
- u32 *src = ((u32 *) IP_RT_ACCT_CPU(0)) + offset;
u32 *dst = (u32 *) buffer;
- /* Copy first cpu. */
*start = buffer;
- memcpy(dst, src, length);
+ memset(dst, 0, length);
- /* Add the other cpus in, one int at a time */
for_each_possible_cpu(i) {
unsigned int j;
-
- src = ((u32 *) IP_RT_ACCT_CPU(i)) + offset;
+ u32 *src = ((u32 *) IP_RT_ACCT_CPU(i)) + offset;
for (j = 0; j < length/4; j++)
dst[j] += src[j];
init_timer(&rt_flush_timer);
rt_flush_timer.function = rt_run_flush;
- init_timer(&rt_periodic_timer);
- rt_periodic_timer.function = rt_check_expire;
init_timer(&rt_secret_timer);
rt_secret_timer.function = rt_secret_rebuild;
/* All the timers, started at system startup tend
to synchronize. Perturb it a bit.
*/
- rt_periodic_timer.expires = jiffies + net_random() % ip_rt_gc_interval +
- ip_rt_gc_interval;
- add_timer(&rt_periodic_timer);
+ schedule_delayed_work(&expires_work,
+ net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
rt_secret_timer.expires = jiffies + net_random() % ip_rt_secret_interval +
ip_rt_secret_interval;
#ifdef CONFIG_PROC_FS
{
struct proc_dir_entry *rtstat_pde = NULL; /* keep gcc happy */
- if (!proc_net_fops_create("rt_cache", S_IRUGO, &rt_cache_seq_fops) ||
+ if (!proc_net_fops_create(&init_net, "rt_cache", S_IRUGO, &rt_cache_seq_fops) ||
!(rtstat_pde = create_proc_entry("rt_cache", S_IRUGO,
- proc_net_stat))) {
+ init_net.proc_net_stat))) {
return -ENOMEM;
}
rtstat_pde->proc_fops = &rt_cpu_seq_fops;
}
#ifdef CONFIG_NET_CLS_ROUTE
- create_proc_read_entry("rt_acct", 0, proc_net, ip_rt_acct_read, NULL);
+ create_proc_read_entry("rt_acct", 0, init_net.proc_net, ip_rt_acct_read, NULL);
#endif
#endif
#ifdef CONFIG_XFRM