* (rco@di.uminho.pt) Routing table insertion and update
* Linus Torvalds : Rewrote bits to be sensible
* Alan Cox : Added BSD route gw semantics
- * Alan Cox : Super /proc >4K
+ * Alan Cox : Super /proc >4K
* Alan Cox : MTU in route table
* Alan Cox : MSS actually. Also added the window
* clamper.
* Alan Cox : Faster /proc handling
* Alexey Kuznetsov : Massive rework to support tree based routing,
* routing caches and better behaviour.
- *
+ *
* Olaf Erb : irtt wasn't being copied right.
* Bjorn Ekwall : Kerneld route support.
* Alan Cox : Multicast fixed (I hope)
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
-#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/string.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
+#include <linux/workqueue.h>
#include <linux/skbuff.h>
-#include <linux/rtnetlink.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/pkt_sched.h>
#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
+#include <net/dst.h>
+#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
-#include <net/ip_mp_alg.h>
#include <net/netevent.h>
+#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
static int ip_rt_min_pmtu = 512 + 20 + 20;
static int ip_rt_min_advmss = 256;
static int ip_rt_secret_interval = 10 * 60 * HZ;
+static int ip_rt_flush_expected;
static unsigned long rt_deadline;
#define RTprint(a...) printk(KERN_DEBUG a)
static struct timer_list rt_flush_timer;
-static struct timer_list rt_periodic_timer;
+static void rt_worker_func(struct work_struct *work);
+static DECLARE_DELAYED_WORK(expires_work, rt_worker_func);
static struct timer_list rt_secret_timer;
/*
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static int rt_garbage_collect(void);
+static int rt_garbage_collect(struct dst_ops *ops);
static struct dst_ops ipv4_dst_ops = {
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
+ .local_out = ip_local_out,
.entry_size = sizeof(struct rtable),
};
#define ECN_OR_COST(class) TC_PRIO_##class
-__u8 ip_tos2prio[16] = {
+const __u8 ip_tos2prio[16] = {
TC_PRIO_BESTEFFORT,
ECN_OR_COST(FILLER),
TC_PRIO_BESTEFFORT,
static spinlock_t *rt_hash_locks;
# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
-# define rt_hash_lock_init() { \
- int i; \
- rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, GFP_KERNEL); \
- if (!rt_hash_locks) panic("IP: failed to allocate rt_hash_locks\n"); \
- for (i = 0; i < RT_HASH_LOCK_SZ; i++) \
- spin_lock_init(&rt_hash_locks[i]); \
- }
+
+static __init void rt_hash_lock_init(void)
+{
+ int i;
+
+ rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ,
+ GFP_KERNEL);
+ if (!rt_hash_locks)
+ panic("IP: failed to allocate rt_hash_locks\n");
+
+ for (i = 0; i < RT_HASH_LOCK_SZ; i++)
+ spin_lock_init(&rt_hash_locks[i]);
+}
#else
# define rt_hash_lock_addr(slot) NULL
-# define rt_hash_lock_init()
+
+static inline void rt_hash_lock_init(void)
+{
+}
#endif
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);
& rt_hash_mask);
}
+#define rt_hash(daddr, saddr, idx) \
+ rt_hash_code((__force u32)(__be32)(daddr),\
+ (__force u32)(__be32)(saddr) ^ ((idx) << 5))
+
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
int bucket;
break;
rcu_read_unlock_bh();
}
- return r;
+ return rcu_dereference(r);
}
static struct rtable *rt_cache_get_next(struct seq_file *seq, struct rtable *r)
{
- struct rt_cache_iter_state *st = rcu_dereference(seq->private);
+ struct rt_cache_iter_state *st = seq->private;
- r = r->u.rt_next;
+ r = r->u.dst.rt_next;
while (!r) {
rcu_read_unlock_bh();
if (--st->bucket < 0)
rcu_read_lock_bh();
r = rt_hash_table[st->bucket].chain;
}
- return r;
+ return rcu_dereference(r);
}
static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
dev_queue_xmit) : 0,
r->rt_spec_dst);
seq_printf(seq, "%-127s\n", temp);
- }
- return 0;
+ }
+ return 0;
}
-static struct seq_operations rt_cache_seq_ops = {
+static const struct seq_operations rt_cache_seq_ops = {
.start = rt_cache_seq_start,
.next = rt_cache_seq_next,
.stop = rt_cache_seq_stop,
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 = kmalloc(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;
- memset(s, 0, sizeof(*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 struct file_operations rt_cache_seq_fops = {
+static const struct file_operations rt_cache_seq_fops = {
.owner = THIS_MODULE,
.open = rt_cache_seq_open,
.read = seq_read,
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
-
+
}
static void rt_cpu_seq_stop(struct seq_file *seq, void *v)
seq_printf(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n");
return 0;
}
-
+
seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x "
" %08x %08x %08x %08x %08x %08x %08x %08x %08x \n",
atomic_read(&ipv4_dst_ops.entries),
st->out_hit,
st->out_slow_tot,
- st->out_slow_mc,
+ st->out_slow_mc,
st->gc_total,
st->gc_ignored,
return 0;
}
-static struct seq_operations rt_cpu_seq_ops = {
+static const struct seq_operations rt_cpu_seq_ops = {
.start = rt_cpu_seq_start,
.next = rt_cpu_seq_next,
.stop = rt_cpu_seq_stop,
return seq_open(file, &rt_cpu_seq_ops);
}
-static struct file_operations rt_cpu_seq_fops = {
+static const struct file_operations rt_cpu_seq_fops = {
.owner = THIS_MODULE,
.open = rt_cpu_seq_open,
.read = seq_read,
.release = seq_release,
};
+#ifdef CONFIG_NET_CLS_ROUTE
+static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
+ int length, int *eof, void *data)
+{
+ unsigned int i;
+
+ if ((offset & 3) || (length & 3))
+ return -EIO;
+
+ if (offset >= sizeof(struct ip_rt_acct) * 256) {
+ *eof = 1;
+ return 0;
+ }
+
+ if (offset + length >= sizeof(struct ip_rt_acct) * 256) {
+ length = sizeof(struct ip_rt_acct) * 256 - offset;
+ *eof = 1;
+ }
+
+ offset /= sizeof(u32);
+
+ if (length > 0) {
+ u32 *dst = (u32 *) buffer;
+
+ *start = buffer;
+ memset(dst, 0, length);
+
+ for_each_possible_cpu(i) {
+ unsigned int j;
+ u32 *src;
+
+ src = ((u32 *) per_cpu_ptr(ip_rt_acct, i)) + offset;
+ for (j = 0; j < length/4; j++)
+ dst[j] += src[j];
+ }
+ }
+ return length;
+}
+#endif
+
+static __init int ip_rt_proc_init(struct net *net)
+{
+ struct proc_dir_entry *pde;
+
+ pde = proc_net_fops_create(net, "rt_cache", S_IRUGO,
+ &rt_cache_seq_fops);
+ if (!pde)
+ goto err1;
+
+ pde = create_proc_entry("rt_cache", S_IRUGO, net->proc_net_stat);
+ if (!pde)
+ goto err2;
+
+ pde->proc_fops = &rt_cpu_seq_fops;
+
+#ifdef CONFIG_NET_CLS_ROUTE
+ pde = create_proc_read_entry("rt_acct", 0, net->proc_net,
+ ip_rt_acct_read, NULL);
+ if (!pde)
+ goto err3;
+#endif
+ return 0;
+
+#ifdef CONFIG_NET_CLS_ROUTE
+err3:
+ remove_proc_entry("rt_cache", net->proc_net_stat);
+#endif
+err2:
+ remove_proc_entry("rt_cache", net->proc_net);
+err1:
+ return -ENOMEM;
+}
+#else
+static inline int ip_rt_proc_init(struct net *net)
+{
+ return 0;
+}
#endif /* CONFIG_PROC_FS */
-
+
static __inline__ void rt_free(struct rtable *rt)
{
- multipath_remove(rt);
call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}
static __inline__ void rt_drop(struct rtable *rt)
{
- multipath_remove(rt);
ip_rt_put(rt);
call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}
/* Kill broadcast/multicast entries very aggresively, if they
collide in hash table with more useful entries */
return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
- rth->fl.iif && rth->u.rt_next;
+ rth->fl.iif && rth->u.dst.rt_next;
}
static __inline__ int rt_valuable(struct rtable *rth)
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return memcmp(&fl1->nl_u.ip4_u, &fl2->nl_u.ip4_u, sizeof(fl1->nl_u.ip4_u)) == 0 &&
- fl1->oif == fl2->oif &&
- fl1->iif == fl2->iif;
+ return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
+ (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
+ (fl1->mark ^ fl2->mark) |
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^
+ *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (fl1->oif ^ fl2->oif) |
+ (fl1->iif ^ fl2->iif)) == 0;
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
-static struct rtable **rt_remove_balanced_route(struct rtable **chain_head,
- struct rtable *expentry,
- int *removed_count)
+/*
+ * Perform a full scan of hash table and free all entries.
+ * Can be called by a softirq or a process.
+ * In the later case, we want to be reschedule if necessary
+ */
+static void rt_do_flush(int process_context)
{
- int passedexpired = 0;
- struct rtable **nextstep = NULL;
- struct rtable **rthp = chain_head;
- struct rtable *rth;
-
- if (removed_count)
- *removed_count = 0;
+ unsigned int i;
+ struct rtable *rth, *next;
- while ((rth = *rthp) != NULL) {
- if (rth == expentry)
- passedexpired = 1;
+ for (i = 0; i <= rt_hash_mask; i++) {
+ if (process_context && need_resched())
+ cond_resched();
+ rth = rt_hash_table[i].chain;
+ if (!rth)
+ continue;
- if (((*rthp)->u.dst.flags & DST_BALANCED) != 0 &&
- compare_keys(&(*rthp)->fl, &expentry->fl)) {
- if (*rthp == expentry) {
- *rthp = rth->u.rt_next;
- continue;
- } else {
- *rthp = rth->u.rt_next;
- rt_free(rth);
- if (removed_count)
- ++(*removed_count);
- }
- } else {
- if (!((*rthp)->u.dst.flags & DST_BALANCED) &&
- passedexpired && !nextstep)
- nextstep = &rth->u.rt_next;
+ spin_lock_bh(rt_hash_lock_addr(i));
+ rth = rt_hash_table[i].chain;
+ rt_hash_table[i].chain = NULL;
+ spin_unlock_bh(rt_hash_lock_addr(i));
- rthp = &rth->u.rt_next;
+ for (; rth; rth = next) {
+ next = rth->u.dst.rt_next;
+ rt_free(rth);
}
}
-
- rt_free(expentry);
- if (removed_count)
- ++(*removed_count);
-
- return nextstep;
}
-#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
-
-/* 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(void)
{
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.rt_next;
+ rthp = &rth->u.dst.rt_next;
continue;
}
} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
tmo >>= 1;
- rthp = &rth->u.rt_next;
+ rthp = &rth->u.dst.rt_next;
continue;
}
/* Cleanup aged off entries. */
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- /* remove all related balanced entries if necessary */
- if (rth->u.dst.flags & DST_BALANCED) {
- rthp = rt_remove_balanced_route(
- &rt_hash_table[i].chain,
- rth, NULL);
- if (!rthp)
- break;
- } else {
- *rthp = rth->u.rt_next;
- rt_free(rth);
- }
-#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
- *rthp = rth->u.rt_next;
- rt_free(rth);
-#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
+ *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);
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * If a whole flush was scheduled, it is done.
+ * Else, we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+ if (ip_rt_flush_expected) {
+ ip_rt_flush_expected = 0;
+ rt_do_flush(1);
+ } else
+ rt_check_expire();
+ schedule_delayed_work(&expires_work, ip_rt_gc_interval);
}
/* This can run from both BH and non-BH contexts, the latter
* in the case of a forced flush event.
*/
-static void rt_run_flush(unsigned long dummy)
+static void rt_run_flush(unsigned long process_context)
{
- int i;
- struct rtable *rth, *next;
-
rt_deadline = 0;
get_random_bytes(&rt_hash_rnd, 4);
- for (i = rt_hash_mask; i >= 0; i--) {
- spin_lock_bh(rt_hash_lock_addr(i));
- rth = rt_hash_table[i].chain;
- if (rth)
- rt_hash_table[i].chain = NULL;
- spin_unlock_bh(rt_hash_lock_addr(i));
-
- for (; rth; rth = next) {
- next = rth->u.rt_next;
- rt_free(rth);
- }
- }
+ rt_do_flush(process_context);
}
static DEFINE_SPINLOCK(rt_flush_lock);
if (delay < 0)
delay = ip_rt_min_delay;
- /* flush existing multipath state*/
- multipath_flush();
-
spin_lock_bh(&rt_flush_lock);
if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) {
if (user_mode && tmo < ip_rt_max_delay-ip_rt_min_delay)
tmo = 0;
-
+
if (delay > tmo)
delay = tmo;
}
if (delay <= 0) {
spin_unlock_bh(&rt_flush_lock);
- rt_run_flush(0);
+ rt_run_flush(user_mode);
return;
}
spin_unlock_bh(&rt_flush_lock);
}
+/*
+ * We change rt_hash_rnd and ask next rt_worker_func() invocation
+ * to perform a flush in process context
+ */
static void rt_secret_rebuild(unsigned long dummy)
{
- unsigned long now = jiffies;
-
- rt_cache_flush(0);
- mod_timer(&rt_secret_timer, now + ip_rt_secret_interval);
+ get_random_bytes(&rt_hash_rnd, 4);
+ ip_rt_flush_expected = 1;
+ cancel_delayed_work(&expires_work);
+ schedule_delayed_work(&expires_work, HZ/10);
+ mod_timer(&rt_secret_timer, jiffies + ip_rt_secret_interval);
}
/*
and when load increases it reduces to limit cache size.
*/
-static int rt_garbage_collect(void)
+static int rt_garbage_collect(struct dst_ops *ops)
{
static unsigned long expire = RT_GC_TIMEOUT;
static unsigned long last_gc;
equilibrium = ipv4_dst_ops.gc_thresh;
goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
if (goal > 0) {
- equilibrium += min_t(unsigned int, goal / 2, rt_hash_mask + 1);
+ equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
}
} else {
/* We are in dangerous area. Try to reduce cache really
* aggressively.
*/
- goal = max_t(unsigned int, goal / 2, rt_hash_mask + 1);
+ goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
}
while ((rth = *rthp) != NULL) {
if (!rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
- rthp = &rth->u.rt_next;
+ rthp = &rth->u.dst.rt_next;
continue;
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- /* remove all related balanced entries
- * if necessary
- */
- if (rth->u.dst.flags & DST_BALANCED) {
- int r;
-
- rthp = rt_remove_balanced_route(
- &rt_hash_table[k].chain,
- rth,
- &r);
- goal -= r;
- if (!rthp)
- break;
- } else {
- *rthp = rth->u.rt_next;
- rt_free(rth);
- goal--;
- }
-#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
- *rthp = rth->u.rt_next;
+ *rthp = rth->u.dst.rt_next;
rt_free(rth);
goal--;
-#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
}
spin_unlock_bh(rt_hash_lock_addr(k));
if (goal <= 0)
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- if (!(rth->u.dst.flags & DST_BALANCED) &&
- compare_keys(&rth->fl, &rt->fl)) {
-#else
if (compare_keys(&rth->fl, &rt->fl)) {
-#endif
/* Put it first */
- *rthp = rth->u.rt_next;
+ *rthp = rth->u.dst.rt_next;
/*
* Since lookup is lockfree, the deletion
* must be visible to another weakly ordered CPU before
* the insertion at the start of the hash chain.
*/
- rcu_assign_pointer(rth->u.rt_next,
+ rcu_assign_pointer(rth->u.dst.rt_next,
rt_hash_table[hash].chain);
/*
* Since lookup is lockfree, the update writes
*/
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);
chain_length++;
- rthp = &rth->u.rt_next;
+ rthp = &rth->u.dst.rt_next;
}
if (cand) {
* only 2 entries per bucket. We will see.
*/
if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->u.rt_next;
+ *candp = cand->u.dst.rt_next;
rt_free(cand);
}
}
int saved_int = ip_rt_gc_min_interval;
ip_rt_gc_elasticity = 1;
ip_rt_gc_min_interval = 0;
- rt_garbage_collect();
+ rt_garbage_collect(&ipv4_dst_ops);
ip_rt_gc_min_interval = saved_int;
ip_rt_gc_elasticity = saved_elasticity;
goto restart;
}
}
- rt->u.rt_next = rt_hash_table[hash].chain;
+ rt->u.dst.rt_next = rt_hash_table[hash].chain;
#if RT_CACHE_DEBUG >= 2
- if (rt->u.rt_next) {
+ if (rt->u.dst.rt_next) {
struct rtable *trt;
printk(KERN_DEBUG "rt_cache @%02x: %u.%u.%u.%u", hash,
NIPQUAD(rt->rt_dst));
- for (trt = rt->u.rt_next; trt; trt = trt->u.rt_next)
+ for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
printk(" . %u.%u.%u.%u", NIPQUAD(trt->rt_dst));
printk("\n");
}
u32 salt;
spin_lock_bh(&ip_fb_id_lock);
- salt = secure_ip_id(ip_fallback_id ^ iph->daddr);
+ salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
iph->id = htons(salt & 0xFFFF);
ip_fallback_id = salt;
spin_unlock_bh(&ip_fb_id_lock);
return;
}
} else
- printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
+ printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
__builtin_return_address(0));
ip_select_fb_ident(iph);
spin_lock_bh(rt_hash_lock_addr(hash));
ip_rt_put(rt);
for (rthp = &rt_hash_table[hash].chain; *rthp;
- rthp = &(*rthp)->u.rt_next)
+ rthp = &(*rthp)->u.dst.rt_next)
if (*rthp == rt) {
- *rthp = rt->u.rt_next;
+ *rthp = rt->u.dst.rt_next;
rt_free(rt);
break;
}
spin_unlock_bh(rt_hash_lock_addr(hash));
}
-void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
- u32 saddr, struct net_device *dev)
+void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
+ __be32 saddr, struct net_device *dev)
{
int i, k;
struct in_device *in_dev = in_dev_get(dev);
struct rtable *rth, **rthp;
- u32 skeys[2] = { saddr, 0 };
+ __be32 skeys[2] = { saddr, 0 };
int ikeys[2] = { dev->ifindex, 0 };
struct netevent_redirect netevent;
return;
if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
- || MULTICAST(new_gw) || BADCLASS(new_gw) || ZERONET(new_gw))
+ || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw)
+ || ipv4_is_zeronet(new_gw))
goto reject_redirect;
if (!IN_DEV_SHARED_MEDIA(in_dev)) {
if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
goto reject_redirect;
} else {
- if (inet_addr_type(new_gw) != RTN_UNICAST)
+ if (inet_addr_type(&init_net, new_gw) != RTN_UNICAST)
goto reject_redirect;
}
for (i = 0; i < 2; i++) {
for (k = 0; k < 2; k++) {
- unsigned hash = rt_hash_code(daddr,
- skeys[i] ^ (ikeys[k] << 5));
+ unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]);
rthp=&rt_hash_table[hash].chain;
rth->fl.fl4_src != skeys[i] ||
rth->fl.oif != ikeys[k] ||
rth->fl.iif != 0) {
- rthp = &rth->u.rt_next;
+ rthp = &rth->u.dst.rt_next;
continue;
}
/* Copy all the information. */
*rt = *rth;
- INIT_RCU_HEAD(&rt->u.dst.rcu_head);
+ INIT_RCU_HEAD(&rt->u.dst.rcu_head);
rt->u.dst.__use = 1;
atomic_set(&rt->u.dst.__refcnt, 1);
rt->u.dst.child = NULL;
rt_drop(rt);
goto do_next;
}
-
+
netevent.old = &rth->u.dst;
netevent.new = &rt->u.dst;
- call_netevent_notifiers(NETEVENT_REDIRECT,
- &netevent);
+ call_netevent_notifiers(NETEVENT_REDIRECT,
+ &netevent);
rt_del(hash, rth);
if (!rt_intern_hash(hash, rt, &rt))
ret = NULL;
} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
rt->u.dst.expires) {
- unsigned hash = rt_hash_code(rt->fl.fl4_dst,
- rt->fl.fl4_src ^
- (rt->fl.oif << 5));
+ 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
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
- if (time_after(jiffies,
+ if (rt->u.dst.rate_tokens == 0 ||
+ time_after(jiffies,
(rt->u.dst.rate_last +
(ip_rt_redirect_load << rt->u.dst.rate_tokens)))) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
#endif
}
out:
- in_dev_put(in_dev);
+ in_dev_put(in_dev);
}
static int ip_error(struct sk_buff *skb)
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
+ IP_INC_STATS_BH(IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
out: kfree_skb(skb);
return 0;
-}
+}
/*
* The last two values are not from the RFC but
static __inline__ unsigned short guess_mtu(unsigned short old_mtu)
{
int i;
-
+
for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++)
if (old_mtu > mtu_plateau[i])
return mtu_plateau[i];
int i;
unsigned short old_mtu = ntohs(iph->tot_len);
struct rtable *rth;
- u32 skeys[2] = { iph->saddr, 0, };
- u32 daddr = iph->daddr;
+ __be32 skeys[2] = { iph->saddr, 0, };
+ __be32 daddr = iph->daddr;
unsigned short est_mtu = 0;
if (ipv4_config.no_pmtu_disc)
return 0;
for (i = 0; i < 2; i++) {
- unsigned hash = rt_hash_code(daddr, skeys[i]);
+ unsigned hash = rt_hash(daddr, skeys[i], 0);
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.rt_next)) {
+ rth = rcu_dereference(rth->u.dst.rt_next)) {
if (rth->fl.fl4_dst == daddr &&
rth->fl.fl4_src == skeys[i] &&
rth->rt_dst == daddr &&
mtu = guess_mtu(old_mtu);
}
if (mtu <= rth->u.dst.metrics[RTAX_MTU-1]) {
- if (mtu < rth->u.dst.metrics[RTAX_MTU-1]) {
+ if (mtu < rth->u.dst.metrics[RTAX_MTU-1]) {
dst_confirm(&rth->u.dst);
if (mtu < ip_rt_min_pmtu) {
mtu = ip_rt_min_pmtu;
{
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 != dev->nd_net->loopback_dev && idev && idev->dev == dev) {
+ struct in_device *loopback_idev =
+ in_dev_get(dev->nd_net->loopback_dev);
if (loopback_idev) {
rt->idev = loopback_idev;
in_dev_put(idev);
static int ip_rt_bug(struct sk_buff *skb)
{
printk(KERN_DEBUG "ip_rt_bug: %u.%u.%u.%u -> %u.%u.%u.%u, %s\n",
- NIPQUAD(skb->nh.iph->saddr), NIPQUAD(skb->nh.iph->daddr),
+ NIPQUAD(ip_hdr(skb)->saddr), NIPQUAD(ip_hdr(skb)->daddr),
skb->dev ? skb->dev->name : "?");
kfree_skb(skb);
return 0;
void ip_rt_get_source(u8 *addr, struct rtable *rt)
{
- u32 src;
+ __be32 src;
struct fib_result res;
if (rt->fl.iif == 0)
src = rt->rt_src;
- else if (fib_lookup(&rt->fl, &res) == 0) {
+ else if (fib_lookup(rt->u.dst.dev->nd_net, &rt->fl, &res) == 0) {
src = FIB_RES_PREFSRC(res);
fib_res_put(&res);
} else
#endif
set_class_tag(rt, itag);
#endif
- rt->rt_type = res->type;
+ rt->rt_type = res->type;
}
-static int ip_route_input_mc(struct sk_buff *skb, u32 daddr, u32 saddr,
+static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
unsigned hash;
struct rtable *rth;
- u32 spec_dst;
+ __be32 spec_dst;
struct in_device *in_dev = in_dev_get(dev);
u32 itag = 0;
if (in_dev == NULL)
return -EINVAL;
- if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr) ||
- skb->protocol != htons(ETH_P_IP))
+ if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
+ ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP))
goto e_inval;
- if (ZERONET(saddr)) {
- if (!LOCAL_MCAST(daddr))
+ if (ipv4_is_zeronet(saddr)) {
+ if (!ipv4_is_local_multicast(daddr))
goto e_inval;
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
} else if (fib_validate_source(saddr, 0, tos, 0,
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
- if (in_dev->cnf.no_policy)
+ if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
rth->u.dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark= skb->nfmark;
-#endif
+ rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
#ifdef CONFIG_NET_CLS_ROUTE
#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;
}
#ifdef CONFIG_IP_MROUTE
- if (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
+ if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
rth->u.dst.input = ip_mr_input;
#endif
RT_CACHE_STAT_INC(in_slow_mc);
in_dev_put(in_dev);
- hash = rt_hash_code(daddr, saddr ^ (dev->ifindex << 5));
+ hash = rt_hash(daddr, saddr, dev->ifindex);
return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst);
e_nobufs:
static void ip_handle_martian_source(struct net_device *dev,
struct in_device *in_dev,
struct sk_buff *skb,
- u32 daddr,
- u32 saddr)
+ __be32 daddr,
+ __be32 saddr)
{
RT_CACHE_STAT_INC(in_martian_src);
#ifdef CONFIG_IP_ROUTE_VERBOSE
printk(KERN_WARNING "martian source %u.%u.%u.%u from "
"%u.%u.%u.%u, on dev %s\n",
NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
- if (dev->hard_header_len && skb->mac.raw) {
+ if (dev->hard_header_len && skb_mac_header_was_set(skb)) {
int i;
- unsigned char *p = skb->mac.raw;
+ const unsigned char *p = skb_mac_header(skb);
printk(KERN_WARNING "ll header: ");
for (i = 0; i < dev->hard_header_len; i++, p++) {
printk("%02x", *p);
#endif
}
-static inline int __mkroute_input(struct sk_buff *skb,
- struct fib_result* res,
- struct in_device *in_dev,
- u32 daddr, u32 saddr, u32 tos,
- struct rtable **result)
+static inline int __mkroute_input(struct sk_buff *skb,
+ struct fib_result* res,
+ struct in_device *in_dev,
+ __be32 daddr, __be32 saddr, u32 tos,
+ struct rtable **result)
{
struct rtable *rth;
int err;
struct in_device *out_dev;
unsigned flags = 0;
- u32 spec_dst, itag;
+ __be32 spec_dst;
+ u32 itag;
/* get a working reference to the output device */
out_dev = in_dev_get(FIB_RES_DEV(*res));
}
- err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res),
+ err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, &spec_dst, &itag);
if (err < 0) {
- ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
+ ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
-
+
err = -EINVAL;
goto cleanup;
}
if (err)
flags |= RTCF_DIRECTSRC;
- if (out_dev == in_dev && err && !(flags & (RTCF_NAT | RTCF_MASQ)) &&
+ if (out_dev == in_dev && err && !(flags & RTCF_MASQ) &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
flags |= RTCF_DOREDIRECT;
/* Not IP (i.e. ARP). Do not create route, if it is
* invalid for proxy arp. DNAT routes are always valid.
*/
- if (out_dev == in_dev && !(flags & RTCF_DNAT)) {
+ if (out_dev == in_dev) {
err = -EINVAL;
goto cleanup;
}
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- if (res->fi->fib_nhs > 1)
- rth->u.dst.flags |= DST_BALANCED;
-#endif
- if (in_dev->cnf.no_policy)
+ if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
rth->u.dst.flags |= DST_NOPOLICY;
- if (in_dev->cnf.no_xfrm)
+ if (IN_DEV_CONF_GET(out_dev, NOXFRM))
rth->u.dst.flags |= DST_NOXFRM;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark= skb->nfmark;
-#endif
+ rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
rth->rt_gateway = daddr;
/* release the working reference to the output device */
in_dev_put(out_dev);
return err;
-}
+}
-static inline int ip_mkroute_input_def(struct sk_buff *skb,
- struct fib_result* res,
- const struct flowi *fl,
- struct in_device *in_dev,
- u32 daddr, u32 saddr, u32 tos)
+static inline int ip_mkroute_input(struct sk_buff *skb,
+ struct fib_result* res,
+ const struct flowi *fl,
+ struct in_device *in_dev,
+ __be32 daddr, __be32 saddr, u32 tos)
{
struct rtable* rth = NULL;
int err;
return err;
/* put it into the cache */
- hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5));
- return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
-}
-
-static inline int ip_mkroute_input(struct sk_buff *skb,
- struct fib_result* res,
- const struct flowi *fl,
- struct in_device *in_dev,
- u32 daddr, u32 saddr, u32 tos)
-{
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- struct rtable* rth = NULL, *rtres;
- unsigned char hop, hopcount;
- int err = -EINVAL;
- unsigned int hash;
-
- if (res->fi)
- hopcount = res->fi->fib_nhs;
- else
- hopcount = 1;
-
- /* distinguish between multipath and singlepath */
- if (hopcount < 2)
- return ip_mkroute_input_def(skb, res, fl, in_dev, daddr,
- saddr, tos);
-
- /* add all alternatives to the routing cache */
- for (hop = 0; hop < hopcount; hop++) {
- res->nh_sel = hop;
-
- /* put reference to previous result */
- if (hop)
- ip_rt_put(rtres);
-
- /* create a routing cache entry */
- err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos,
- &rth);
- if (err)
- return err;
-
- /* put it into the cache */
- hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5));
- err = rt_intern_hash(hash, rth, &rtres);
- if (err)
- return err;
-
- /* forward hop information to multipath impl. */
- multipath_set_nhinfo(rth,
- FIB_RES_NETWORK(*res),
- FIB_RES_NETMASK(*res),
- res->prefixlen,
- &FIB_RES_NH(*res));
- }
- skb->dst = &rtres->u.dst;
- return err;
-#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
- return ip_mkroute_input_def(skb, res, fl, in_dev, daddr, saddr, tos);
-#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
+ hash = rt_hash(daddr, saddr, fl->iif);
+ return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
}
-
/*
* NOTE. We drop all the packets that has local source
* addresses, because every properly looped back packet
* 2. IP spoofing attempts are filtered with 100% of guarantee.
*/
-static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr,
+static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct fib_result res;
.saddr = saddr,
.tos = tos,
.scope = RT_SCOPE_UNIVERSE,
-#ifdef CONFIG_IP_ROUTE_FWMARK
- .fwmark = skb->nfmark
-#endif
} },
+ .mark = skb->mark,
.iif = dev->ifindex };
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
unsigned hash;
- u32 spec_dst;
+ __be32 spec_dst;
int err = -EINVAL;
int free_res = 0;
+ struct net * net = dev->nd_net;
/* IP on this device is disabled. */
by fib_lookup.
*/
- if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr))
+ if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
+ ipv4_is_loopback(saddr))
goto martian_source;
- if (daddr == 0xFFFFFFFF || (saddr == 0 && daddr == 0))
+ if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0))
goto brd_input;
/* Accept zero addresses only to limited broadcast;
* I even do not know to fix it or not. Waiting for complains :-)
*/
- if (ZERONET(saddr))
+ if (ipv4_is_zeronet(saddr))
goto martian_source;
- if (BADCLASS(daddr) || ZERONET(daddr) || LOOPBACK(daddr))
+ if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) ||
+ ipv4_is_loopback(daddr))
goto martian_destination;
/*
* Now we are ready to route packet.
*/
- if ((err = fib_lookup(&fl, &res)) != 0) {
+ if ((err = fib_lookup(net, &fl, &res)) != 0) {
if (!IN_DEV_FORWARD(in_dev))
goto e_hostunreach;
goto no_route;
if (res.type == RTN_LOCAL) {
int result;
result = fib_validate_source(saddr, daddr, tos,
- loopback_dev.ifindex,
+ 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)
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
- if (ZERONET(saddr))
+ if (ipv4_is_zeronet(saddr))
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
else {
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
- if (in_dev->cnf.no_policy)
+ if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
rth->u.dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark= skb->nfmark;
-#endif
+ rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
#ifdef CONFIG_NET_CLS_ROUTE
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = &loopback_dev;
+ rth->u.dst.dev = net->loopback_dev;
dev_hold(rth->u.dst.dev);
rth->idev = in_dev_get(rth->u.dst.dev);
rth->rt_gateway = daddr;
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
- hash = rt_hash_code(daddr, saddr ^ (fl.iif << 5));
+ hash = rt_hash(daddr, saddr, fl.iif);
err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
goto done;
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;
/*
#endif
e_hostunreach:
- err = -EHOSTUNREACH;
- goto done;
+ err = -EHOSTUNREACH;
+ goto done;
e_inval:
err = -EINVAL;
goto e_inval;
}
-int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr,
+int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct rtable * rth;
int iif = dev->ifindex;
tos &= IPTOS_RT_MASK;
- hash = rt_hash_code(daddr, saddr ^ (iif << 5));
+ hash = rt_hash(daddr, saddr, iif);
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.rt_next)) {
+ rth = rcu_dereference(rth->u.dst.rt_next)) {
if (rth->fl.fl4_dst == daddr &&
rth->fl.fl4_src == saddr &&
rth->fl.iif == iif &&
rth->fl.oif == 0 &&
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark == skb->nfmark &&
-#endif
+ 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;
Note, that multicast routers are not affected, because
route cache entry is created eventually.
*/
- if (MULTICAST(daddr)) {
+ if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev;
rcu_read_lock();
if ((in_dev = __in_dev_get_rcu(dev)) != NULL) {
int our = ip_check_mc(in_dev, daddr, saddr,
- skb->nh.iph->protocol);
+ ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
- || (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
+ || (!ipv4_is_local_multicast(daddr) &&
+ IN_DEV_MFORWARD(in_dev))
#endif
) {
rcu_read_unlock();
}
static inline int __mkroute_output(struct rtable **result,
- struct fib_result* res,
+ struct fib_result* res,
const struct flowi *fl,
- const struct flowi *oldflp,
- struct net_device *dev_out,
- unsigned flags)
+ const struct flowi *oldflp,
+ struct net_device *dev_out,
+ unsigned flags)
{
struct rtable *rth;
struct in_device *in_dev;
u32 tos = RT_FL_TOS(oldflp);
int err = 0;
- if (LOOPBACK(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
+ if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
return -EINVAL;
- if (fl->fl4_dst == 0xFFFFFFFF)
+ if (fl->fl4_dst == htonl(0xFFFFFFFF))
res->type = RTN_BROADCAST;
- else if (MULTICAST(fl->fl4_dst))
+ else if (ipv4_is_multicast(fl->fl4_dst))
res->type = RTN_MULTICAST;
- else if (BADCLASS(fl->fl4_dst) || ZERONET(fl->fl4_dst))
+ else if (ipv4_is_lbcast(fl->fl4_dst) || ipv4_is_zeronet(fl->fl4_dst))
return -EINVAL;
if (dev_out->flags & IFF_LOOPBACK)
}
} else if (res->type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST|RTCF_LOCAL;
- if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
+ if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
oldflp->proto))
flags &= ~RTCF_LOCAL;
/* If multicast route do not exist use
if (!rth) {
err = -ENOBUFS;
goto cleanup;
- }
+ }
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- if (res->fi) {
- rth->rt_multipath_alg = res->fi->fib_mp_alg;
- if (res->fi->fib_nhs > 1)
- rth->u.dst.flags |= DST_BALANCED;
- }
-#endif
- if (in_dev->cnf.no_xfrm)
+ if (IN_DEV_CONF_GET(in_dev, NOXFRM))
rth->u.dst.flags |= DST_NOXFRM;
- if (in_dev->cnf.no_policy)
+ if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
rth->u.dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = oldflp->fl4_dst;
rth->fl.fl4_tos = tos;
rth->fl.fl4_src = oldflp->fl4_src;
rth->fl.oif = oldflp->oif;
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark= oldflp->fl4_fwmark;
-#endif
+ rth->fl.mark = oldflp->mark;
rth->rt_dst = fl->fl4_dst;
rth->rt_src = fl->fl4_src;
rth->rt_iif = oldflp->oif ? : dev_out->ifindex;
- /* get references to the devices that are to be hold by the routing
+ /* get references to the devices that are to be hold by the routing
cache entry */
rth->u.dst.dev = dev_out;
dev_hold(dev_out);
}
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
rth->rt_spec_dst = fl->fl4_src;
- if (flags & RTCF_LOCAL &&
+ if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
rth->u.dst.output = ip_mc_output;
RT_CACHE_STAT_INC(out_slow_mc);
#ifdef CONFIG_IP_MROUTE
if (res->type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
- !LOCAL_MCAST(oldflp->fl4_dst)) {
+ !ipv4_is_local_multicast(oldflp->fl4_dst)) {
rth->u.dst.input = ip_mr_input;
rth->u.dst.output = ip_mc_output;
}
return err;
}
-static inline int ip_mkroute_output_def(struct rtable **rp,
- struct fib_result* res,
- const struct flowi *fl,
- const struct flowi *oldflp,
- struct net_device *dev_out,
- unsigned flags)
-{
- struct rtable *rth = NULL;
- int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
- unsigned hash;
- if (err == 0) {
- hash = rt_hash_code(oldflp->fl4_dst,
- oldflp->fl4_src ^ (oldflp->oif << 5));
- err = rt_intern_hash(hash, rth, rp);
- }
-
- return err;
-}
-
-static inline int ip_mkroute_output(struct rtable** rp,
+static inline int ip_mkroute_output(struct rtable **rp,
struct fib_result* res,
const struct flowi *fl,
const struct flowi *oldflp,
struct net_device *dev_out,
unsigned flags)
{
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- unsigned char hop;
- unsigned hash;
- int err = -EINVAL;
struct rtable *rth = NULL;
-
- if (res->fi && res->fi->fib_nhs > 1) {
- unsigned char hopcount = res->fi->fib_nhs;
-
- for (hop = 0; hop < hopcount; hop++) {
- struct net_device *dev2nexthop;
-
- res->nh_sel = hop;
-
- /* hold a work reference to the output device */
- dev2nexthop = FIB_RES_DEV(*res);
- dev_hold(dev2nexthop);
-
- /* put reference to previous result */
- if (hop)
- ip_rt_put(*rp);
-
- err = __mkroute_output(&rth, res, fl, oldflp,
- dev2nexthop, flags);
-
- if (err != 0)
- goto cleanup;
-
- hash = rt_hash_code(oldflp->fl4_dst,
- oldflp->fl4_src ^
- (oldflp->oif << 5));
- err = rt_intern_hash(hash, rth, rp);
-
- /* forward hop information to multipath impl. */
- multipath_set_nhinfo(rth,
- FIB_RES_NETWORK(*res),
- FIB_RES_NETMASK(*res),
- res->prefixlen,
- &FIB_RES_NH(*res));
- cleanup:
- /* release work reference to output device */
- dev_put(dev2nexthop);
-
- if (err != 0)
- return err;
- }
- return err;
- } else {
- return ip_mkroute_output_def(rp, res, fl, oldflp, dev_out,
- flags);
+ int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
+ unsigned hash;
+ if (err == 0) {
+ hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif);
+ err = rt_intern_hash(hash, rth, rp);
}
-#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
- return ip_mkroute_output_def(rp, res, fl, oldflp, dev_out, flags);
-#endif
+
+ return err;
}
/*
.scope = ((tos & RTO_ONLINK) ?
RT_SCOPE_LINK :
RT_SCOPE_UNIVERSE),
-#ifdef CONFIG_IP_ROUTE_FWMARK
- .fwmark = oldflp->fl4_fwmark
-#endif
} },
- .iif = loopback_dev.ifindex,
+ .mark = oldflp->mark,
+ .iif = init_net.loopback_dev->ifindex,
.oif = oldflp->oif };
struct fib_result res;
unsigned flags = 0;
if (oldflp->fl4_src) {
err = -EINVAL;
- if (MULTICAST(oldflp->fl4_src) ||
- BADCLASS(oldflp->fl4_src) ||
- ZERONET(oldflp->fl4_src))
+ if (ipv4_is_multicast(oldflp->fl4_src) ||
+ ipv4_is_lbcast(oldflp->fl4_src) ||
+ ipv4_is_zeronet(oldflp->fl4_src))
goto out;
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = ip_dev_find(oldflp->fl4_src);
+ dev_out = ip_dev_find(&init_net, oldflp->fl4_src);
if (dev_out == NULL)
goto out;
/* I removed check for oif == dev_out->oif here.
It was wrong for two reasons:
- 1. ip_dev_find(saddr) can return wrong iface, if saddr is
- assigned to multiple interfaces.
+ 1. ip_dev_find(net, saddr) can return wrong iface, if saddr
+ is assigned to multiple interfaces.
2. Moreover, we are allowed to send packets with saddr
of another iface. --ANK
*/
if (oldflp->oif == 0
- && (MULTICAST(oldflp->fl4_dst) || oldflp->fl4_dst == 0xFFFFFFFF)) {
+ && (ipv4_is_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
/* Special hack: user can direct multicasts
and limited broadcast via necessary interface
without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
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;
goto out; /* Wrong error code */
}
- if (LOCAL_MCAST(oldflp->fl4_dst) || oldflp->fl4_dst == 0xFFFFFFFF) {
+ if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
if (!fl.fl4_src)
fl.fl4_src = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
goto make_route;
}
if (!fl.fl4_src) {
- if (MULTICAST(oldflp->fl4_dst))
+ if (ipv4_is_multicast(oldflp->fl4_dst))
fl.fl4_src = inet_select_addr(dev_out, 0,
fl.fl4_scope);
else if (!oldflp->fl4_dst)
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;
}
- if (fib_lookup(&fl, &res)) {
+ if (fib_lookup(&init_net, &fl, &res)) {
res.fi = NULL;
if (oldflp->oif) {
/* Apparently, routing tables are wrong. Assume,
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)
else
#endif
if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
- fib_select_default(&fl, &res);
+ fib_select_default(&init_net, &fl, &res);
if (!fl.fl4_src)
fl.fl4_src = FIB_RES_PREFSRC(res);
unsigned hash;
struct rtable *rth;
- hash = rt_hash_code(flp->fl4_dst, flp->fl4_src ^ (flp->oif << 5));
+ hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif);
rcu_read_lock_bh();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.rt_next)) {
+ rth = rcu_dereference(rth->u.dst.rt_next)) {
if (rth->fl.fl4_dst == flp->fl4_dst &&
rth->fl.fl4_src == flp->fl4_src &&
rth->fl.iif == 0 &&
rth->fl.oif == flp->oif &&
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark == flp->fl4_fwmark &&
-#endif
+ rth->fl.mark == flp->mark &&
!((rth->fl.fl4_tos ^ flp->fl4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK))) {
-
- /* check for multipath routes and choose one if
- * necessary
- */
- if (multipath_select_route(flp, rth, rp)) {
- dst_hold(&(*rp)->u.dst);
- RT_CACHE_STAT_INC(out_hit);
- rcu_read_unlock_bh();
- return 0;
- }
-
- 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;
EXPORT_SYMBOL_GPL(__ip_route_output_key);
+static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
+{
+}
+
+static struct dst_ops ipv4_dst_blackhole_ops = {
+ .family = AF_INET,
+ .protocol = __constant_htons(ETH_P_IP),
+ .destroy = ipv4_dst_destroy,
+ .check = ipv4_dst_check,
+ .update_pmtu = ipv4_rt_blackhole_update_pmtu,
+ .entry_size = sizeof(struct rtable),
+};
+
+
+static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock *sk)
+{
+ struct rtable *ort = *rp;
+ struct rtable *rt = (struct rtable *)
+ dst_alloc(&ipv4_dst_blackhole_ops);
+
+ if (rt) {
+ struct dst_entry *new = &rt->u.dst;
+
+ atomic_set(&new->__refcnt, 1);
+ new->__use = 1;
+ new->input = dst_discard;
+ new->output = dst_discard;
+ memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
+
+ new->dev = ort->u.dst.dev;
+ if (new->dev)
+ dev_hold(new->dev);
+
+ rt->fl = ort->fl;
+
+ rt->idev = ort->idev;
+ if (rt->idev)
+ in_dev_hold(rt->idev);
+ rt->rt_flags = ort->rt_flags;
+ rt->rt_type = ort->rt_type;
+ rt->rt_dst = ort->rt_dst;
+ rt->rt_src = ort->rt_src;
+ rt->rt_iif = ort->rt_iif;
+ rt->rt_gateway = ort->rt_gateway;
+ rt->rt_spec_dst = ort->rt_spec_dst;
+ rt->peer = ort->peer;
+ if (rt->peer)
+ atomic_inc(&rt->peer->refcnt);
+
+ dst_free(new);
+ }
+
+ dst_release(&(*rp)->u.dst);
+ *rp = rt;
+ return (rt ? 0 : -ENOMEM);
+}
+
int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk, int flags)
{
int err;
flp->fl4_src = (*rp)->rt_src;
if (!flp->fl4_dst)
flp->fl4_dst = (*rp)->rt_dst;
- return xfrm_lookup((struct dst_entry **)rp, flp, sk, flags);
+ err = __xfrm_lookup((struct dst_entry **)rp, flp, sk,
+ flags ? XFRM_LOOKUP_WAIT : 0);
+ if (err == -EREMOTE)
+ err = ipv4_dst_blackhole(rp, flp, sk);
+
+ return err;
}
return 0;
struct rtable *rt = (struct rtable*)skb->dst;
struct rtmsg *r;
struct nlmsghdr *nlh;
- struct rta_cacheinfo ci;
+ long expires;
+ u32 id = 0, ts = 0, tsage = 0, error;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
if (nlh == NULL)
- return -ENOBUFS;
+ return -EMSGSIZE;
r = nlmsg_data(nlh);
r->rtm_family = AF_INET;
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
- NLA_PUT_U32(skb, RTA_DST, rt->rt_dst);
+ NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
if (rt->fl.fl4_src) {
r->rtm_src_len = 32;
- NLA_PUT_U32(skb, RTA_SRC, rt->fl.fl4_src);
+ NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src);
}
if (rt->u.dst.dev)
NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex);
if (rt->u.dst.tclassid)
NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid);
#endif
-#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
- if (rt->rt_multipath_alg != IP_MP_ALG_NONE)
- NLA_PUT_U32(skb, RTA_MP_ALGO, rt->rt_multipath_alg);
-#endif
if (rt->fl.iif)
- NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_spec_dst);
+ NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
else if (rt->rt_src != rt->fl.fl4_src)
- NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_src);
+ NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
if (rt->rt_dst != rt->rt_gateway)
- NLA_PUT_U32(skb, RTA_GATEWAY, rt->rt_gateway);
+ NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway);
if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
goto nla_put_failure;
- ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse);
- ci.rta_used = rt->u.dst.__use;
- ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt);
- if (rt->u.dst.expires)
- ci.rta_expires = jiffies_to_clock_t(rt->u.dst.expires - jiffies);
- else
- ci.rta_expires = 0;
- ci.rta_error = rt->u.dst.error;
- ci.rta_id = ci.rta_ts = ci.rta_tsage = 0;
+ error = rt->u.dst.error;
+ expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
if (rt->peer) {
- ci.rta_id = rt->peer->ip_id_count;
+ id = rt->peer->ip_id_count;
if (rt->peer->tcp_ts_stamp) {
- ci.rta_ts = rt->peer->tcp_ts;
- ci.rta_tsage = xtime.tv_sec - rt->peer->tcp_ts_stamp;
+ ts = rt->peer->tcp_ts;
+ tsage = get_seconds() - rt->peer->tcp_ts_stamp;
}
}
if (rt->fl.iif) {
#ifdef CONFIG_IP_MROUTE
- u32 dst = rt->rt_dst;
+ __be32 dst = rt->rt_dst;
- if (MULTICAST(dst) && !LOCAL_MCAST(dst) &&
- ipv4_devconf.mc_forwarding) {
+ if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
+ IPV4_DEVCONF_ALL(&init_net, MC_FORWARDING)) {
int err = ipmr_get_route(skb, r, nowait);
if (err <= 0) {
if (!nowait) {
} else {
if (err == -EMSGSIZE)
goto nla_put_failure;
- ci.rta_error = err;
+ error = err;
}
}
} else
NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif);
}
- NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci);
+ if (rtnl_put_cacheinfo(skb, &rt->u.dst, id, ts, tsage,
+ expires, error) < 0)
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
nla_put_failure:
- return nlmsg_cancel(skb, nlh);
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
}
-int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
+static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
+ struct net *net = in_skb->sk->sk_net;
struct rtmsg *rtm;
struct nlattr *tb[RTA_MAX+1];
struct rtable *rt = NULL;
- u32 dst, src, iif;
+ __be32 dst = 0;
+ __be32 src = 0;
+ u32 iif;
int err;
struct sk_buff *skb;
+ if (net != &init_net)
+ return -EINVAL;
+
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
goto errout;
/* Reserve room for dummy headers, this skb can pass
through good chunk of routing engine.
*/
- skb->mac.raw = skb->nh.raw = skb->data;
+ skb_reset_mac_header(skb);
+ skb_reset_network_header(skb);
/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
- skb->nh.iph->protocol = IPPROTO_ICMP;
+ ip_hdr(skb)->protocol = IPPROTO_ICMP;
skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
- src = tb[RTA_SRC] ? nla_get_u32(tb[RTA_SRC]) : 0;
- dst = tb[RTA_DST] ? nla_get_u32(tb[RTA_DST]) : 0;
+ src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0;
+ dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
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;
if (err <= 0)
goto errout_free;
- err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid);
errout:
return err;
int idx, s_idx;
s_h = cb->args[0];
+ if (s_h < 0)
+ s_h = 0;
s_idx = idx = cb->args[1];
- for (h = 0; h <= rt_hash_mask; h++) {
- if (h < s_h) continue;
- if (h > s_h)
- s_idx = 0;
+ for (h = s_h; h <= rt_hash_mask; h++) {
rcu_read_lock_bh();
for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference(rt->u.rt_next), idx++) {
+ rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
if (idx < s_idx)
continue;
skb->dst = dst_clone(&rt->u.dst);
if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, RTM_NEWROUTE,
+ cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
dst_release(xchg(&skb->dst, NULL));
rcu_read_unlock_bh();
dst_release(xchg(&skb->dst, NULL));
}
rcu_read_unlock_bh();
+ s_idx = 0;
}
done:
proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
rt_cache_flush(flush_delay);
return 0;
- }
+ }
return -EINVAL;
}
void __user *oldval,
size_t __user *oldlenp,
void __user *newval,
- size_t newlen,
- void **context)
+ size_t newlen)
{
int delay;
if (newlen != sizeof(int))
return -EINVAL;
if (get_user(delay, (int __user *)newval))
- return -EFAULT;
- rt_cache_flush(delay);
+ return -EFAULT;
+ rt_cache_flush(delay);
return 0;
}
ctl_table ipv4_route_table[] = {
- {
+ {
.ctl_name = NET_IPV4_ROUTE_FLUSH,
.procname = "flush",
.data = &flush_delay,
},
{
/* Deprecated. Use gc_min_interval_ms */
-
+
.ctl_name = NET_IPV4_ROUTE_GC_MIN_INTERVAL,
.procname = "gc_min_interval",
.data = &ip_rt_gc_min_interval,
#endif
#ifdef CONFIG_NET_CLS_ROUTE
-struct ip_rt_acct *ip_rt_acct;
-
-/* This code sucks. But you should have seen it before! --RR */
-
-/* IP route accounting ptr for this logical cpu number. */
-#define IP_RT_ACCT_CPU(i) (ip_rt_acct + i * 256)
-
-#ifdef CONFIG_PROC_FS
-static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
- int length, int *eof, void *data)
-{
- unsigned int i;
-
- if ((offset & 3) || (length & 3))
- return -EIO;
-
- if (offset >= sizeof(struct ip_rt_acct) * 256) {
- *eof = 1;
- return 0;
- }
-
- if (offset + length >= sizeof(struct ip_rt_acct) * 256) {
- length = sizeof(struct ip_rt_acct) * 256 - offset;
- *eof = 1;
- }
-
- 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);
-
- /* 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;
-
- for (j = 0; j < length/4; j++)
- dst[j] += src[j];
- }
- }
- return length;
-}
-#endif /* CONFIG_PROC_FS */
+struct ip_rt_acct *ip_rt_acct __read_mostly;
#endif /* CONFIG_NET_CLS_ROUTE */
static __initdata unsigned long rhash_entries;
(jiffies ^ (jiffies >> 7)));
#ifdef CONFIG_NET_CLS_ROUTE
- {
- int order;
- for (order = 0;
- (PAGE_SIZE << order) < 256 * sizeof(struct ip_rt_acct) * NR_CPUS; order++)
- /* NOTHING */;
- ip_rt_acct = (struct ip_rt_acct *)__get_free_pages(GFP_KERNEL, order);
+ ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct));
if (!ip_rt_acct)
panic("IP: failed to allocate ip_rt_acct\n");
- memset(ip_rt_acct, 0, PAGE_SIZE << order);
- }
#endif
- ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache",
- sizeof(struct rtable),
- 0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
+ ipv4_dst_ops.kmem_cachep =
+ kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
- if (!ipv4_dst_ops.kmem_cachep)
- panic("IP: failed to allocate ip_dst_cache\n");
+ ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep;
rt_hash_table = (struct rt_hash_bucket *)
alloc_large_system_hash("IP route cache",
devinet_init();
ip_fib_init();
- 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;
+ setup_timer(&rt_flush_timer, rt_run_flush, 0);
+ setup_timer(&rt_secret_timer, rt_secret_rebuild, 0);
/* 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;
add_timer(&rt_secret_timer);
-#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) ||
- !(rtstat_pde = create_proc_entry("rt_cache", S_IRUGO,
- 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);
-#endif
-#endif
+ if (ip_rt_proc_init(&init_net))
+ printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
xfrm4_init();
#endif
+ rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
+
return rc;
}