#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
+#include <linux/slab.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ;
static int rt_chain_length_max __read_mostly = 20;
-static struct delayed_work expires_work;
-static unsigned long expires_ljiffies;
-
/*
* Interface to generic destination cache.
*/
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
+static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
+static unsigned int ipv4_default_mtu(const struct dst_entry *dst);
static void ipv4_dst_destroy(struct dst_entry *dst);
-static void ipv4_dst_ifdown(struct dst_entry *dst,
- struct net_device *dev, int how);
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(struct dst_ops *ops);
-static void rt_emergency_hash_rebuild(struct net *net);
+static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
+ int how)
+{
+}
+
+static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+ struct rtable *rt = (struct rtable *) dst;
+ struct inet_peer *peer;
+ u32 *p = NULL;
+
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+
+ peer = rt->peer;
+ if (peer) {
+ u32 *old_p = __DST_METRICS_PTR(old);
+ unsigned long prev, new;
+
+ p = peer->metrics;
+ if (inet_metrics_new(peer))
+ memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+
+ new = (unsigned long) p;
+ prev = cmpxchg(&dst->_metrics, old, new);
+
+ if (prev != old) {
+ p = __DST_METRICS_PTR(prev);
+ if (prev & DST_METRICS_READ_ONLY)
+ p = NULL;
+ } else {
+ if (rt->fi) {
+ fib_info_put(rt->fi);
+ rt->fi = NULL;
+ }
+ }
+ }
+ return p;
+}
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
+ .default_advmss = ipv4_default_advmss,
+ .default_mtu = ipv4_default_mtu,
+ .cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
.local_out = __ip_local_out,
- .entries = ATOMIC_INIT(0),
};
#define ECN_OR_COST(class) TC_PRIO_##class
*/
struct rt_hash_bucket {
- struct rtable *chain;
+ struct rtable __rcu *chain;
};
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
static unsigned int rt_hash_log __read_mostly;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
-#define RT_CACHE_STAT_INC(field) \
- (__raw_get_cpu_var(rt_cache_stat).field++)
+#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
+ int genid)
{
- return jhash_3words((__force u32)(__be32)(daddr),
- (__force u32)(__be32)(saddr),
+ return jhash_3words((__force u32)daddr, (__force u32)saddr,
idx, genid)
& rt_hash_mask;
}
struct rtable *r = NULL;
for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
- if (!rt_hash_table[st->bucket].chain)
+ if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain))
continue;
rcu_read_lock_bh();
- r = rcu_dereference(rt_hash_table[st->bucket].chain);
+ r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
while (r) {
- if (dev_net(r->u.dst.dev) == seq_file_net(seq) &&
+ if (dev_net(r->dst.dev) == seq_file_net(seq) &&
r->rt_genid == st->genid)
return r;
- r = rcu_dereference(r->u.dst.rt_next);
+ r = rcu_dereference_bh(r->dst.rt_next);
}
rcu_read_unlock_bh();
}
{
struct rt_cache_iter_state *st = seq->private;
- r = r->u.dst.rt_next;
+ r = rcu_dereference_bh(r->dst.rt_next);
while (!r) {
rcu_read_unlock_bh();
do {
if (--st->bucket < 0)
return NULL;
- } while (!rt_hash_table[st->bucket].chain);
+ } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain));
rcu_read_lock_bh();
- r = rt_hash_table[st->bucket].chain;
+ r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
}
- return rcu_dereference(r);
+ return r;
}
static struct rtable *rt_cache_get_next(struct seq_file *seq,
{
struct rt_cache_iter_state *st = seq->private;
while ((r = __rt_cache_get_next(seq, r)) != NULL) {
- if (dev_net(r->u.dst.dev) != seq_file_net(seq))
+ if (dev_net(r->dst.dev) != seq_file_net(seq))
continue;
if (r->rt_genid == st->genid)
break;
struct rtable *r = v;
int len;
- seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
- "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
- r->u.dst.dev ? r->u.dst.dev->name : "*",
- (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
- r->rt_flags, atomic_read(&r->u.dst.__refcnt),
- r->u.dst.__use, 0, (unsigned long)r->rt_src,
- (dst_metric(&r->u.dst, RTAX_ADVMSS) ?
- (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
- dst_metric(&r->u.dst, RTAX_WINDOW),
- (int)((dst_metric(&r->u.dst, RTAX_RTT) >> 3) +
- dst_metric(&r->u.dst, RTAX_RTTVAR)),
+ seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
+ "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
+ r->dst.dev ? r->dst.dev->name : "*",
+ (__force u32)r->rt_dst,
+ (__force u32)r->rt_gateway,
+ r->rt_flags, atomic_read(&r->dst.__refcnt),
+ r->dst.__use, 0, (__force u32)r->rt_src,
+ dst_metric_advmss(&r->dst) + 40,
+ dst_metric(&r->dst, RTAX_WINDOW),
+ (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
+ dst_metric(&r->dst, RTAX_RTTVAR)),
r->fl.fl4_tos,
- r->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1,
- r->u.dst.hh ? (r->u.dst.hh->hh_output ==
+ r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
+ r->dst.hh ? (r->dst.hh->hh_output ==
dev_queue_xmit) : 0,
r->rt_spec_dst, &len);
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),
+ dst_entries_get_slow(&ipv4_dst_ops),
st->in_hit,
st->in_slow_tot,
st->in_slow_mc,
.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)
+#ifdef CONFIG_IP_ROUTE_CLASSID
+static int rt_acct_proc_show(struct seq_file *m, void *v)
{
- unsigned int i;
-
- if ((offset & 3) || (length & 3))
- return -EIO;
+ struct ip_rt_acct *dst, *src;
+ unsigned int i, j;
- if (offset >= sizeof(struct ip_rt_acct) * 256) {
- *eof = 1;
- return 0;
- }
+ dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL);
+ if (!dst)
+ return -ENOMEM;
- if (offset + length >= sizeof(struct ip_rt_acct) * 256) {
- length = sizeof(struct ip_rt_acct) * 256 - offset;
- *eof = 1;
+ for_each_possible_cpu(i) {
+ src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i);
+ for (j = 0; j < 256; j++) {
+ dst[j].o_bytes += src[j].o_bytes;
+ dst[j].o_packets += src[j].o_packets;
+ dst[j].i_bytes += src[j].i_bytes;
+ dst[j].i_packets += src[j].i_packets;
+ }
}
- 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;
+ seq_write(m, dst, 256 * sizeof(struct ip_rt_acct));
+ kfree(dst);
+ return 0;
+}
- src = ((u32 *) per_cpu_ptr(ip_rt_acct, i)) + offset;
- for (j = 0; j < length/4; j++)
- dst[j] += src[j];
- }
- }
- return length;
+static int rt_acct_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, rt_acct_proc_show, NULL);
}
+
+static const struct file_operations rt_acct_proc_fops = {
+ .owner = THIS_MODULE,
+ .open = rt_acct_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
#endif
static int __net_init ip_rt_do_proc_init(struct net *net)
if (!pde)
goto err2;
-#ifdef CONFIG_NET_CLS_ROUTE
- pde = create_proc_read_entry("rt_acct", 0, net->proc_net,
- ip_rt_acct_read, NULL);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
if (!pde)
goto err3;
#endif
return 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
err3:
remove_proc_entry("rt_cache", net->proc_net_stat);
#endif
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
+#ifdef CONFIG_IP_ROUTE_CLASSID
remove_proc_entry("rt_acct", net->proc_net);
+#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
static inline void rt_free(struct rtable *rt)
{
- call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
+ call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static inline void rt_drop(struct rtable *rt)
{
ip_rt_put(rt);
- call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
+ call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static inline int rt_fast_clean(struct rtable *rth)
/* 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.dst.rt_next;
+ rt_is_input_route(rth) && rth->dst.rt_next;
}
static inline int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- rth->u.dst.expires;
+ (rth->peer && rth->peer->pmtu_expires);
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
unsigned long age;
int ret = 0;
- if (atomic_read(&rth->u.dst.__refcnt))
- goto out;
-
- ret = 1;
- if (rth->u.dst.expires &&
- time_after_eq(jiffies, rth->u.dst.expires))
+ if (atomic_read(&rth->dst.__refcnt))
goto out;
- age = jiffies - rth->u.dst.lastuse;
- ret = 0;
+ age = jiffies - rth->dst.lastuse;
if ((age <= tmo1 && !rt_fast_clean(rth)) ||
(age <= tmo2 && rt_valuable(rth)))
goto out;
*/
static inline u32 rt_score(struct rtable *rt)
{
- u32 score = jiffies - rt->u.dst.lastuse;
+ u32 score = jiffies - rt->dst.lastuse;
score = ~score & ~(3<<30);
if (rt_valuable(rt))
score |= (1<<31);
- if (!rt->fl.iif ||
+ if (rt_is_output_route(rt) ||
!(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
score |= (1<<30);
static inline bool compare_hash_inputs(const struct flowi *fl1,
const struct flowi *fl2)
{
- 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) |
+ return ((((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
+ ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
(fl1->iif ^ fl2->iif)) == 0);
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- 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)) |
+ return (((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) |
+ ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
(fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->nl_u.ip4_u.tos ^
- *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (*(u16 *)&fl1->fl4_tos ^ *(u16 *)&fl2->fl4_tos) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
{
- return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev);
+ return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));
}
static inline int rt_is_expired(struct rtable *rth)
{
- return rth->rt_genid != rt_genid(dev_net(rth->u.dst.dev));
+ return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
/*
* 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)
+static void rt_do_flush(struct net *net, int process_context)
{
unsigned int i;
struct rtable *rth, *next;
- struct rtable * tail;
for (i = 0; i <= rt_hash_mask; i++) {
+ struct rtable __rcu **pprev;
+ struct rtable *list;
+
if (process_context && need_resched())
cond_resched();
- rth = rt_hash_table[i].chain;
+ rth = rcu_dereference_raw(rt_hash_table[i].chain);
if (!rth)
continue;
spin_lock_bh(rt_hash_lock_addr(i));
-#ifdef CONFIG_NET_NS
- {
- struct rtable ** prev, * p;
- rth = rt_hash_table[i].chain;
+ list = NULL;
+ pprev = &rt_hash_table[i].chain;
+ rth = rcu_dereference_protected(*pprev,
+ lockdep_is_held(rt_hash_lock_addr(i)));
- /* defer releasing the head of the list after spin_unlock */
- for (tail = rth; tail; tail = tail->u.dst.rt_next)
- if (!rt_is_expired(tail))
- break;
- if (rth != tail)
- rt_hash_table[i].chain = tail;
-
- /* call rt_free on entries after the tail requiring flush */
- prev = &rt_hash_table[i].chain;
- for (p = *prev; p; p = next) {
- next = p->u.dst.rt_next;
- if (!rt_is_expired(p)) {
- prev = &p->u.dst.rt_next;
+ while (rth) {
+ next = rcu_dereference_protected(rth->dst.rt_next,
+ lockdep_is_held(rt_hash_lock_addr(i)));
+
+ if (!net ||
+ net_eq(dev_net(rth->dst.dev), net)) {
+ rcu_assign_pointer(*pprev, next);
+ rcu_assign_pointer(rth->dst.rt_next, list);
+ list = rth;
} else {
- *prev = next;
- rt_free(p);
+ pprev = &rth->dst.rt_next;
}
+ rth = next;
}
- }
-#else
- rth = rt_hash_table[i].chain;
- rt_hash_table[i].chain = NULL;
- tail = NULL;
-#endif
+
spin_unlock_bh(rt_hash_lock_addr(i));
- for (; rth != tail; rth = next) {
- next = rth->u.dst.rt_next;
- rt_free(rth);
+ for (; list; list = next) {
+ next = rcu_dereference_protected(list->dst.rt_next, 1);
+ rt_free(list);
}
}
}
#define FRACT_BITS 3
#define ONE (1UL << FRACT_BITS)
-static void rt_check_expire(void)
-{
- static unsigned int rover;
- unsigned int i = rover, goal;
- struct rtable *rth, *aux, **rthp;
- unsigned long samples = 0;
- unsigned long sum = 0, sum2 = 0;
- unsigned long delta;
- u64 mult;
-
- delta = jiffies - expires_ljiffies;
- expires_ljiffies = jiffies;
- mult = ((u64)delta) << 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;
- for (; goal > 0; goal--) {
- unsigned long tmo = ip_rt_gc_timeout;
- unsigned long length;
-
- i = (i + 1) & rt_hash_mask;
- rthp = &rt_hash_table[i].chain;
-
- if (need_resched())
- cond_resched();
-
- samples++;
-
- if (*rthp == NULL)
- continue;
- length = 0;
- spin_lock_bh(rt_hash_lock_addr(i));
- while ((rth = *rthp) != NULL) {
- prefetch(rth->u.dst.rt_next);
- if (rt_is_expired(rth)) {
- *rthp = rth->u.dst.rt_next;
- rt_free(rth);
- continue;
- }
- if (rth->u.dst.expires) {
- /* Entry is expired even if it is in use */
- if (time_before_eq(jiffies, rth->u.dst.expires)) {
-nofree:
- tmo >>= 1;
- rthp = &rth->u.dst.rt_next;
- /*
- * We only count entries on
- * a chain with equal hash inputs once
- * so that entries for different QOS
- * levels, and other non-hash input
- * attributes don't unfairly skew
- * the length computation
- */
- for (aux = rt_hash_table[i].chain;;) {
- if (aux == rth) {
- length += ONE;
- break;
- }
- if (compare_hash_inputs(&aux->fl, &rth->fl))
- break;
- aux = aux->u.dst.rt_next;
- }
- continue;
- }
- } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
- goto nofree;
-
- /* Cleanup aged off entries. */
- *rthp = rth->u.dst.rt_next;
- rt_free(rth);
- }
- spin_unlock_bh(rt_hash_lock_addr(i));
- sum += length;
- sum2 += length*length;
- }
- if (samples) {
- unsigned long avg = sum / samples;
- unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
- rt_chain_length_max = max_t(unsigned long,
- ip_rt_gc_elasticity,
- (avg + 4*sd) >> FRACT_BITS);
- }
- rover = i;
-}
-
/*
- * rt_worker_func() is run in process context.
- * we call rt_check_expire() to scan part of the hash table
+ * Given a hash chain and an item in this hash chain,
+ * find if a previous entry has the same hash_inputs
+ * (but differs on tos, mark or oif)
+ * Returns 0 if an alias is found.
+ * Returns ONE if rth has no alias before itself.
*/
-static void rt_worker_func(struct work_struct *work)
+static int has_noalias(const struct rtable *head, const struct rtable *rth)
{
- rt_check_expire();
- schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+ const struct rtable *aux = head;
+
+ while (aux != rth) {
+ if (compare_hash_inputs(&aux->fl, &rth->fl))
+ return 0;
+ aux = rcu_dereference_protected(aux->dst.rt_next, 1);
+ }
+ return ONE;
}
/*
{
rt_cache_invalidate(net);
if (delay >= 0)
- rt_do_flush(!in_softirq());
-}
-
-/*
- * We change rt_genid and let gc do the cleanup
- */
-static void rt_secret_rebuild(unsigned long __net)
-{
- struct net *net = (struct net *)__net;
- rt_cache_invalidate(net);
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
+ rt_do_flush(net, !in_softirq());
}
-static void rt_secret_rebuild_oneshot(struct net *net)
+/* Flush previous cache invalidated entries from the cache */
+void rt_cache_flush_batch(struct net *net)
{
- del_timer_sync(&net->ipv4.rt_secret_timer);
- rt_cache_invalidate(net);
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ rt_do_flush(net, !in_softirq());
}
static void rt_emergency_hash_rebuild(struct net *net)
{
- if (net_ratelimit()) {
+ if (net_ratelimit())
printk(KERN_WARNING "Route hash chain too long!\n");
- printk(KERN_WARNING "Adjust your secret_interval!\n");
- }
-
- rt_secret_rebuild_oneshot(net);
+ rt_cache_invalidate(net);
}
/*
static unsigned long last_gc;
static int rover;
static int equilibrium;
- struct rtable *rth, **rthp;
+ struct rtable *rth;
+ struct rtable __rcu **rthp;
unsigned long now = jiffies;
int goal;
+ int entries = dst_entries_get_fast(&ipv4_dst_ops);
/*
* Garbage collection is pretty expensive,
RT_CACHE_STAT_INC(gc_total);
if (now - last_gc < ip_rt_gc_min_interval &&
- atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) {
+ entries < ip_rt_max_size) {
RT_CACHE_STAT_INC(gc_ignored);
goto out;
}
+ entries = dst_entries_get_slow(&ipv4_dst_ops);
/* Calculate number of entries, which we want to expire now. */
- goal = atomic_read(&ipv4_dst_ops.entries) -
- (ip_rt_gc_elasticity << rt_hash_log);
+ goal = entries - (ip_rt_gc_elasticity << rt_hash_log);
if (goal <= 0) {
if (equilibrium < ipv4_dst_ops.gc_thresh)
equilibrium = ipv4_dst_ops.gc_thresh;
- goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
+ goal = entries - equilibrium;
if (goal > 0) {
equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
+ goal = entries - equilibrium;
}
} else {
/* We are in dangerous area. Try to reduce cache really
* aggressively.
*/
goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
+ equilibrium = entries - goal;
}
if (now - last_gc >= ip_rt_gc_min_interval)
k = (k + 1) & rt_hash_mask;
rthp = &rt_hash_table[k].chain;
spin_lock_bh(rt_hash_lock_addr(k));
- while ((rth = *rthp) != NULL) {
+ while ((rth = rcu_dereference_protected(*rthp,
+ lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) {
if (!rt_is_expired(rth) &&
!rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
- rthp = &rth->u.dst.rt_next;
+ rthp = &rth->dst.rt_next;
continue;
}
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
rt_free(rth);
goal--;
}
expire >>= 1;
#if RT_CACHE_DEBUG >= 2
printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
- atomic_read(&ipv4_dst_ops.entries), goal, i);
+ dst_entries_get_fast(&ipv4_dst_ops), goal, i);
#endif
- if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
+ if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
} while (!in_softirq() && time_before_eq(jiffies, now));
- if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
+ if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
+ goto out;
+ if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
if (net_ratelimit())
printk(KERN_WARNING "dst cache overflow\n");
work_done:
expire += ip_rt_gc_min_interval;
if (expire > ip_rt_gc_timeout ||
- atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh)
+ dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh ||
+ dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh)
expire = ip_rt_gc_timeout;
#if RT_CACHE_DEBUG >= 2
printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire,
- atomic_read(&ipv4_dst_ops.entries), goal, rover);
+ dst_entries_get_fast(&ipv4_dst_ops), goal, rover);
#endif
out: return 0;
}
-static int rt_intern_hash(unsigned hash, struct rtable *rt,
- struct rtable **rp, struct sk_buff *skb)
+/*
+ * Returns number of entries in a hash chain that have different hash_inputs
+ */
+static int slow_chain_length(const struct rtable *head)
+{
+ int length = 0;
+ const struct rtable *rth = head;
+
+ while (rth) {
+ length += has_noalias(head, rth);
+ rth = rcu_dereference_protected(rth->dst.rt_next, 1);
+ }
+ return length >> FRACT_BITS;
+}
+
+static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt,
+ struct sk_buff *skb, int ifindex)
{
- struct rtable *rth, **rthp;
+ struct rtable *rth, *cand;
+ struct rtable __rcu **rthp, **candp;
unsigned long now;
- struct rtable *cand, **candp;
u32 min_score;
int chain_length;
int attempts = !in_softirq();
candp = NULL;
now = jiffies;
- if (!rt_caching(dev_net(rt->u.dst.dev))) {
+ if (!rt_caching(dev_net(rt->dst.dev))) {
/*
* If we're not caching, just tell the caller we
* were successful and don't touch the route. The
* Note that we do rt_free on this new route entry, so that
* once its refcount hits zero, we are still able to reap it
* (Thanks Alexey)
- * Note also the rt_free uses call_rcu. We don't actually
- * need rcu protection here, this is just our path to get
- * on the route gc list.
+ * Note: To avoid expensive rcu stuff for this uncached dst,
+ * we set DST_NOCACHE so that dst_release() can free dst without
+ * waiting a grace period.
*/
- if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
- int err = arp_bind_neighbour(&rt->u.dst);
+ rt->dst.flags |= DST_NOCACHE;
+ if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
+ int err = arp_bind_neighbour(&rt->dst);
if (err) {
if (net_ratelimit())
printk(KERN_WARNING
"Neighbour table failure & not caching routes.\n");
- rt_drop(rt);
- return err;
+ ip_rt_put(rt);
+ return ERR_PTR(err);
}
}
- rt_free(rt);
goto skip_hashing;
}
rthp = &rt_hash_table[hash].chain;
spin_lock_bh(rt_hash_lock_addr(hash));
- while ((rth = *rthp) != NULL) {
+ while ((rth = rcu_dereference_protected(*rthp,
+ lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
if (rt_is_expired(rth)) {
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->dst.rt_next;
rt_free(rth);
continue;
}
if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) {
/* Put it first */
- *rthp = rth->u.dst.rt_next;
+ *rthp = rth->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.dst.rt_next,
+ rcu_assign_pointer(rth->dst.rt_next,
rt_hash_table[hash].chain);
/*
* Since lookup is lockfree, the update writes
*/
rcu_assign_pointer(rt_hash_table[hash].chain, rth);
- dst_use(&rth->u.dst, now);
+ dst_use(&rth->dst, now);
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
- if (rp)
- *rp = rth;
- else
- skb_dst_set(skb, &rth->u.dst);
- return 0;
+ if (skb)
+ skb_dst_set(skb, &rth->dst);
+ return rth;
}
- if (!atomic_read(&rth->u.dst.__refcnt)) {
+ if (!atomic_read(&rth->dst.__refcnt)) {
u32 score = rt_score(rth);
if (score <= min_score) {
chain_length++;
- rthp = &rth->u.dst.rt_next;
+ rthp = &rth->dst.rt_next;
}
if (cand) {
* only 2 entries per bucket. We will see.
*/
if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->u.dst.rt_next;
+ *candp = cand->dst.rt_next;
rt_free(cand);
}
} else {
- if (chain_length > rt_chain_length_max) {
- struct net *net = dev_net(rt->u.dst.dev);
+ if (chain_length > rt_chain_length_max &&
+ slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
+ struct net *net = dev_net(rt->dst.dev);
int num = ++net->ipv4.current_rt_cache_rebuild_count;
- if (!rt_caching(dev_net(rt->u.dst.dev))) {
+ if (!rt_caching(net)) {
printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
- rt->u.dst.dev->name, num);
+ rt->dst.dev->name, num);
}
- rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev));
+ rt_emergency_hash_rebuild(net);
+ spin_unlock_bh(rt_hash_lock_addr(hash));
+
+ hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
+ ifindex, rt_genid(net));
+ goto restart;
}
}
/* Try to bind route to arp only if it is output
route or unicast forwarding path.
*/
- if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
- int err = arp_bind_neighbour(&rt->u.dst);
+ if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
+ int err = arp_bind_neighbour(&rt->dst);
if (err) {
spin_unlock_bh(rt_hash_lock_addr(hash));
if (err != -ENOBUFS) {
rt_drop(rt);
- return err;
+ return ERR_PTR(err);
}
/* Neighbour tables are full and nothing
}
if (net_ratelimit())
- printk(KERN_WARNING "Neighbour table overflow.\n");
+ printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
rt_drop(rt);
- return -ENOBUFS;
+ return ERR_PTR(-ENOBUFS);
}
}
- rt->u.dst.rt_next = rt_hash_table[hash].chain;
+ rt->dst.rt_next = rt_hash_table[hash].chain;
#if RT_CACHE_DEBUG >= 2
- if (rt->u.dst.rt_next) {
+ if (rt->dst.rt_next) {
struct rtable *trt;
printk(KERN_DEBUG "rt_cache @%02x: %pI4",
hash, &rt->rt_dst);
- for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
+ for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)
printk(" . %pI4", &trt->rt_dst);
printk("\n");
}
spin_unlock_bh(rt_hash_lock_addr(hash));
skip_hashing:
- if (rp)
- *rp = rt;
- else
- skb_dst_set(skb, &rt->u.dst);
- return 0;
+ if (skb)
+ skb_dst_set(skb, &rt->dst);
+ return rt;
+}
+
+static atomic_t __rt_peer_genid = ATOMIC_INIT(0);
+
+static u32 rt_peer_genid(void)
+{
+ return atomic_read(&__rt_peer_genid);
}
void rt_bind_peer(struct rtable *rt, int create)
{
- static DEFINE_SPINLOCK(rt_peer_lock);
struct inet_peer *peer;
- peer = inet_getpeer(rt->rt_dst, create);
+ peer = inet_getpeer_v4(rt->rt_dst, create);
- spin_lock_bh(&rt_peer_lock);
- if (rt->peer == NULL) {
- rt->peer = peer;
- peer = NULL;
- }
- spin_unlock_bh(&rt_peer_lock);
- if (peer)
+ if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
inet_putpeer(peer);
+ else
+ rt->rt_peer_genid = rt_peer_genid();
}
/*
ip_select_fb_ident(iph);
}
+EXPORT_SYMBOL(__ip_select_ident);
static void rt_del(unsigned hash, struct rtable *rt)
{
- struct rtable **rthp, *aux;
+ struct rtable __rcu **rthp;
+ struct rtable *aux;
rthp = &rt_hash_table[hash].chain;
spin_lock_bh(rt_hash_lock_addr(hash));
ip_rt_put(rt);
- while ((aux = *rthp) != NULL) {
+ while ((aux = rcu_dereference_protected(*rthp,
+ lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
if (aux == rt || rt_is_expired(aux)) {
- *rthp = aux->u.dst.rt_next;
+ *rthp = aux->dst.rt_next;
rt_free(aux);
continue;
}
- rthp = &aux->u.dst.rt_next;
+ rthp = &aux->dst.rt_next;
}
spin_unlock_bh(rt_hash_lock_addr(hash));
}
+/* called in rcu_read_lock() section */
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;
- __be32 skeys[2] = { saddr, 0 };
- int ikeys[2] = { dev->ifindex, 0 };
- struct netevent_redirect netevent;
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+ struct inet_peer *peer;
struct net *net;
if (!in_dev)
ipv4_is_zeronet(new_gw))
goto reject_redirect;
- if (!rt_caching(net))
- goto reject_redirect;
-
if (!IN_DEV_SHARED_MEDIA(in_dev)) {
if (!inet_addr_onlink(in_dev, new_gw, old_gw))
goto reject_redirect;
goto reject_redirect;
}
- for (i = 0; i < 2; i++) {
- for (k = 0; k < 2; k++) {
- unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
- rt_genid(net));
-
- rthp=&rt_hash_table[hash].chain;
-
- rcu_read_lock();
- while ((rth = rcu_dereference(*rthp)) != NULL) {
- struct rtable *rt;
-
- if (rth->fl.fl4_dst != daddr ||
- rth->fl.fl4_src != skeys[i] ||
- rth->fl.oif != ikeys[k] ||
- rth->fl.iif != 0 ||
- rt_is_expired(rth) ||
- !net_eq(dev_net(rth->u.dst.dev), net)) {
- rthp = &rth->u.dst.rt_next;
- continue;
- }
-
- if (rth->rt_dst != daddr ||
- rth->rt_src != saddr ||
- rth->u.dst.error ||
- rth->rt_gateway != old_gw ||
- rth->u.dst.dev != dev)
- break;
-
- dst_hold(&rth->u.dst);
- rcu_read_unlock();
-
- rt = dst_alloc(&ipv4_dst_ops);
- if (rt == NULL) {
- ip_rt_put(rth);
- in_dev_put(in_dev);
- return;
- }
-
- /* Copy all the information. */
- *rt = *rth;
- rt->u.dst.__use = 1;
- atomic_set(&rt->u.dst.__refcnt, 1);
- rt->u.dst.child = NULL;
- if (rt->u.dst.dev)
- dev_hold(rt->u.dst.dev);
- if (rt->idev)
- in_dev_hold(rt->idev);
- rt->u.dst.obsolete = 0;
- rt->u.dst.lastuse = jiffies;
- rt->u.dst.path = &rt->u.dst;
- rt->u.dst.neighbour = NULL;
- rt->u.dst.hh = NULL;
-#ifdef CONFIG_XFRM
- rt->u.dst.xfrm = NULL;
-#endif
- rt->rt_genid = rt_genid(net);
- rt->rt_flags |= RTCF_REDIRECTED;
-
- /* Gateway is different ... */
- rt->rt_gateway = new_gw;
-
- /* Redirect received -> path was valid */
- dst_confirm(&rth->u.dst);
-
- if (rt->peer)
- atomic_inc(&rt->peer->refcnt);
-
- if (arp_bind_neighbour(&rt->u.dst) ||
- !(rt->u.dst.neighbour->nud_state &
- NUD_VALID)) {
- if (rt->u.dst.neighbour)
- neigh_event_send(rt->u.dst.neighbour, NULL);
- ip_rt_put(rth);
- rt_drop(rt);
- goto do_next;
- }
+ peer = inet_getpeer_v4(daddr, 1);
+ if (peer) {
+ peer->redirect_learned.a4 = new_gw;
- netevent.old = &rth->u.dst;
- netevent.new = &rt->u.dst;
- call_netevent_notifiers(NETEVENT_REDIRECT,
- &netevent);
+ inet_putpeer(peer);
- rt_del(hash, rth);
- if (!rt_intern_hash(hash, rt, &rt, NULL))
- ip_rt_put(rt);
- goto do_next;
- }
- rcu_read_unlock();
- do_next:
- ;
- }
+ atomic_inc(&__rt_peer_genid);
}
- in_dev_put(in_dev);
return;
reject_redirect:
&old_gw, dev->name, &new_gw,
&saddr, &daddr);
#endif
- in_dev_put(in_dev);
+ ;
}
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
struct dst_entry *ret = dst;
if (rt) {
- if (dst->obsolete) {
+ if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
- } else if ((rt->rt_flags & RTCF_REDIRECTED) ||
- rt->u.dst.expires) {
+ } else if (rt->rt_flags & RTCF_REDIRECTED) {
unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
rt->fl.oif,
rt_genid(dev_net(dst->dev)));
#endif
rt_del(hash, rt);
ret = NULL;
+ } else if (rt->peer &&
+ rt->peer->pmtu_expires &&
+ time_after_eq(jiffies, rt->peer->pmtu_expires)) {
+ unsigned long orig = rt->peer->pmtu_expires;
+
+ if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
+ dst_metric_set(dst, RTAX_MTU,
+ rt->peer->pmtu_orig);
}
}
return ret;
{
struct rtable *rt = skb_rtable(skb);
struct in_device *in_dev;
+ struct inet_peer *peer;
int log_martians;
rcu_read_lock();
- in_dev = __in_dev_get_rcu(rt->u.dst.dev);
+ in_dev = __in_dev_get_rcu(rt->dst.dev);
if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
rcu_read_unlock();
return;
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
rcu_read_unlock();
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+ peer = rt->peer;
+ if (!peer) {
+ icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+ return;
+ }
+
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
- if (time_after(jiffies, rt->u.dst.rate_last + ip_rt_redirect_silence))
- rt->u.dst.rate_tokens = 0;
+ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+ peer->rate_tokens = 0;
/* Too many ignored redirects; do not send anything
- * set u.dst.rate_last to the last seen redirected packet.
+ * set dst.rate_last to the last seen redirected packet.
*/
- if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) {
- rt->u.dst.rate_last = jiffies;
+ if (peer->rate_tokens >= ip_rt_redirect_number) {
+ peer->rate_last = jiffies;
return;
}
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
- if (rt->u.dst.rate_tokens == 0 ||
+ if (peer->rate_tokens == 0 ||
time_after(jiffies,
- (rt->u.dst.rate_last +
- (ip_rt_redirect_load << rt->u.dst.rate_tokens)))) {
+ (peer->rate_last +
+ (ip_rt_redirect_load << peer->rate_tokens)))) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
- rt->u.dst.rate_last = jiffies;
- ++rt->u.dst.rate_tokens;
+ peer->rate_last = jiffies;
+ ++peer->rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
- rt->u.dst.rate_tokens == ip_rt_redirect_number &&
+ peer->rate_tokens == ip_rt_redirect_number &&
net_ratelimit())
printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
&rt->rt_src, rt->rt_iif,
static int ip_error(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
+ struct inet_peer *peer;
unsigned long now;
+ bool send;
int code;
- switch (rt->u.dst.error) {
+ switch (rt->dst.error) {
case EINVAL:
default:
goto out;
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
- IP_INC_STATS_BH(dev_net(rt->u.dst.dev),
+ IP_INC_STATS_BH(dev_net(rt->dst.dev),
IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
break;
}
- now = jiffies;
- rt->u.dst.rate_tokens += now - rt->u.dst.rate_last;
- if (rt->u.dst.rate_tokens > ip_rt_error_burst)
- rt->u.dst.rate_tokens = ip_rt_error_burst;
- rt->u.dst.rate_last = now;
- if (rt->u.dst.rate_tokens >= ip_rt_error_cost) {
- rt->u.dst.rate_tokens -= ip_rt_error_cost;
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+ peer = rt->peer;
+
+ send = true;
+ if (peer) {
+ now = jiffies;
+ peer->rate_tokens += now - peer->rate_last;
+ if (peer->rate_tokens > ip_rt_error_burst)
+ peer->rate_tokens = ip_rt_error_burst;
+ peer->rate_last = now;
+ if (peer->rate_tokens >= ip_rt_error_cost)
+ peer->rate_tokens -= ip_rt_error_cost;
+ else
+ send = false;
+ }
+ if (send)
icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
- }
out: kfree_skb(skb);
return 0;
unsigned short new_mtu,
struct net_device *dev)
{
- int i, k;
unsigned short old_mtu = ntohs(iph->tot_len);
- struct rtable *rth;
- int ikeys[2] = { dev->ifindex, 0 };
- __be32 skeys[2] = { iph->saddr, 0, };
- __be32 daddr = iph->daddr;
unsigned short est_mtu = 0;
+ struct inet_peer *peer;
- for (k = 0; k < 2; k++) {
- for (i = 0; i < 2; i++) {
- unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
- rt_genid(net));
-
- rcu_read_lock();
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.dst.rt_next)) {
- unsigned short mtu = new_mtu;
-
- if (rth->fl.fl4_dst != daddr ||
- rth->fl.fl4_src != skeys[i] ||
- rth->rt_dst != daddr ||
- rth->rt_src != iph->saddr ||
- rth->fl.oif != ikeys[k] ||
- rth->fl.iif != 0 ||
- dst_metric_locked(&rth->u.dst, RTAX_MTU) ||
- !net_eq(dev_net(rth->u.dst.dev), net) ||
- rt_is_expired(rth))
- continue;
-
- if (new_mtu < 68 || new_mtu >= old_mtu) {
+ peer = inet_getpeer_v4(iph->daddr, 1);
+ if (peer) {
+ unsigned short mtu = new_mtu;
- /* BSD 4.2 compatibility hack :-( */
- if (mtu == 0 &&
- old_mtu >= dst_mtu(&rth->u.dst) &&
- old_mtu >= 68 + (iph->ihl << 2))
- old_mtu -= iph->ihl << 2;
+ if (new_mtu < 68 || new_mtu >= old_mtu) {
+ /* BSD 4.2 derived systems incorrectly adjust
+ * tot_len by the IP header length, and report
+ * a zero MTU in the ICMP message.
+ */
+ if (mtu == 0 &&
+ old_mtu >= 68 + (iph->ihl << 2))
+ old_mtu -= iph->ihl << 2;
+ mtu = guess_mtu(old_mtu);
+ }
- mtu = guess_mtu(old_mtu);
- }
- if (mtu <= dst_mtu(&rth->u.dst)) {
- if (mtu < dst_mtu(&rth->u.dst)) {
- dst_confirm(&rth->u.dst);
- if (mtu < ip_rt_min_pmtu) {
- mtu = ip_rt_min_pmtu;
- rth->u.dst.metrics[RTAX_LOCK-1] |=
- (1 << RTAX_MTU);
- }
- rth->u.dst.metrics[RTAX_MTU-1] = mtu;
- dst_set_expires(&rth->u.dst,
- ip_rt_mtu_expires);
- }
- est_mtu = mtu;
- }
- }
- rcu_read_unlock();
+ if (mtu < ip_rt_min_pmtu)
+ mtu = ip_rt_min_pmtu;
+ if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+ est_mtu = mtu;
+ peer->pmtu_learned = mtu;
+ peer->pmtu_expires = jiffies + ip_rt_mtu_expires;
}
+
+ inet_putpeer(peer);
+
+ atomic_inc(&__rt_peer_genid);
}
return est_mtu ? : new_mtu;
}
+static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
+{
+ unsigned long expires = peer->pmtu_expires;
+
+ if (time_before(expires, jiffies)) {
+ u32 orig_dst_mtu = dst_mtu(dst);
+ if (peer->pmtu_learned < orig_dst_mtu) {
+ if (!peer->pmtu_orig)
+ peer->pmtu_orig = dst_metric_raw(dst, RTAX_MTU);
+ dst_metric_set(dst, RTAX_MTU, peer->pmtu_learned);
+ }
+ } else if (cmpxchg(&peer->pmtu_expires, expires, 0) == expires)
+ dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig);
+}
+
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
- if (dst_mtu(dst) > mtu && mtu >= 68 &&
- !(dst_metric_locked(dst, RTAX_MTU))) {
- if (mtu < ip_rt_min_pmtu) {
+ struct rtable *rt = (struct rtable *) dst;
+ struct inet_peer *peer;
+
+ dst_confirm(dst);
+
+ if (!rt->peer)
+ rt_bind_peer(rt, 1);
+ peer = rt->peer;
+ if (peer) {
+ if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
- dst->metrics[RTAX_LOCK-1] |= (1 << RTAX_MTU);
+ if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+ peer->pmtu_learned = mtu;
+ peer->pmtu_expires = jiffies + ip_rt_mtu_expires;
+
+ atomic_inc(&__rt_peer_genid);
+ rt->rt_peer_genid = rt_peer_genid();
+
+ check_peer_pmtu(dst, peer);
}
- dst->metrics[RTAX_MTU-1] = mtu;
- dst_set_expires(dst, ip_rt_mtu_expires);
- call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
+ inet_putpeer(peer);
+ }
+}
+
+static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+ struct rtable *rt = (struct rtable *) dst;
+ __be32 orig_gw = rt->rt_gateway;
+
+ dst_confirm(&rt->dst);
+
+ neigh_release(rt->dst.neighbour);
+ rt->dst.neighbour = NULL;
+
+ rt->rt_gateway = peer->redirect_learned.a4;
+ if (arp_bind_neighbour(&rt->dst) ||
+ !(rt->dst.neighbour->nud_state & NUD_VALID)) {
+ if (rt->dst.neighbour)
+ neigh_event_send(rt->dst.neighbour, NULL);
+ rt->rt_gateway = orig_gw;
+ return -EAGAIN;
+ } else {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE,
+ rt->dst.neighbour);
}
+ return 0;
}
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
- return NULL;
+ struct rtable *rt = (struct rtable *) dst;
+
+ if (rt_is_expired(rt))
+ return NULL;
+ if (rt->rt_peer_genid != rt_peer_genid()) {
+ struct inet_peer *peer;
+
+ if (!rt->peer)
+ rt_bind_peer(rt, 0);
+
+ peer = rt->peer;
+ if (peer && peer->pmtu_expires)
+ check_peer_pmtu(dst, peer);
+
+ if (peer && peer->redirect_learned.a4 &&
+ peer->redirect_learned.a4 != rt->rt_gateway) {
+ if (check_peer_redir(dst, peer))
+ return NULL;
+ }
+
+ rt->rt_peer_genid = rt_peer_genid();
+ }
+ return dst;
}
static void ipv4_dst_destroy(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *) dst;
struct inet_peer *peer = rt->peer;
- struct in_device *idev = rt->idev;
+ if (rt->fi) {
+ fib_info_put(rt->fi);
+ rt->fi = NULL;
+ }
if (peer) {
rt->peer = NULL;
inet_putpeer(peer);
}
-
- if (idev) {
- rt->idev = NULL;
- in_dev_put(idev);
- }
}
-static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
- int how)
-{
- struct rtable *rt = (struct rtable *) dst;
- struct in_device *idev = rt->idev;
- if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) {
- struct in_device *loopback_idev =
- in_dev_get(dev_net(dev)->loopback_dev);
- if (loopback_idev) {
- rt->idev = loopback_idev;
- in_dev_put(idev);
- }
- }
-}
static void ipv4_link_failure(struct sk_buff *skb)
{
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
rt = skb_rtable(skb);
- if (rt)
- dst_set_expires(&rt->u.dst, 0);
+ if (rt &&
+ rt->peer &&
+ rt->peer->pmtu_expires) {
+ unsigned long orig = rt->peer->pmtu_expires;
+
+ if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig)
+ dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
+ }
}
static int ip_rt_bug(struct sk_buff *skb)
__be32 src;
struct fib_result res;
- if (rt->fl.iif == 0)
+ if (rt_is_output_route(rt))
src = rt->rt_src;
- else if (fib_lookup(dev_net(rt->u.dst.dev), &rt->fl, &res) == 0) {
- src = FIB_RES_PREFSRC(res);
- fib_res_put(&res);
- } else
- src = inet_select_addr(rt->u.dst.dev, rt->rt_gateway,
+ else {
+ rcu_read_lock();
+ if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0)
+ src = FIB_RES_PREFSRC(res);
+ else
+ src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
RT_SCOPE_UNIVERSE);
+ rcu_read_unlock();
+ }
memcpy(addr, &src, 4);
}
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
static void set_class_tag(struct rtable *rt, u32 tag)
{
- if (!(rt->u.dst.tclassid & 0xFFFF))
- rt->u.dst.tclassid |= tag & 0xFFFF;
- if (!(rt->u.dst.tclassid & 0xFFFF0000))
- rt->u.dst.tclassid |= tag & 0xFFFF0000;
+ if (!(rt->dst.tclassid & 0xFFFF))
+ rt->dst.tclassid |= tag & 0xFFFF;
+ if (!(rt->dst.tclassid & 0xFFFF0000))
+ rt->dst.tclassid |= tag & 0xFFFF0000;
}
#endif
-static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
+static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
{
- struct fib_info *fi = res->fi;
+ unsigned int advmss = dst_metric_raw(dst, RTAX_ADVMSS);
+
+ if (advmss == 0) {
+ advmss = max_t(unsigned int, dst->dev->mtu - 40,
+ ip_rt_min_advmss);
+ if (advmss > 65535 - 40)
+ advmss = 65535 - 40;
+ }
+ return advmss;
+}
+
+static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+{
+ unsigned int mtu = dst->dev->mtu;
+
+ if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
+ const struct rtable *rt = (const struct rtable *) dst;
+
+ if (rt->rt_gateway != rt->rt_dst && mtu > 576)
+ mtu = 576;
+ }
+
+ if (mtu > IP_MAX_MTU)
+ mtu = IP_MAX_MTU;
+
+ return mtu;
+}
+
+static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
+{
+ struct inet_peer *peer;
+ int create = 0;
+
+ /* If a peer entry exists for this destination, we must hook
+ * it up in order to get at cached metrics.
+ */
+ if (rt->fl.flags & FLOWI_FLAG_PRECOW_METRICS)
+ create = 1;
+
+ rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
+ if (peer) {
+ rt->rt_peer_genid = rt_peer_genid();
+ if (inet_metrics_new(peer))
+ memcpy(peer->metrics, fi->fib_metrics,
+ sizeof(u32) * RTAX_MAX);
+ dst_init_metrics(&rt->dst, peer->metrics, false);
+
+ if (peer->pmtu_expires)
+ check_peer_pmtu(&rt->dst, peer);
+ if (peer->redirect_learned.a4 &&
+ peer->redirect_learned.a4 != rt->rt_gateway) {
+ rt->rt_gateway = peer->redirect_learned.a4;
+ rt->rt_flags |= RTCF_REDIRECTED;
+ }
+ } else {
+ if (fi->fib_metrics != (u32 *) dst_default_metrics) {
+ rt->fi = fi;
+ atomic_inc(&fi->fib_clntref);
+ }
+ dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+ }
+}
+
+static void rt_set_nexthop(struct rtable *rt, const struct fib_result *res,
+ struct fib_info *fi, u16 type, u32 itag)
+{
+ struct dst_entry *dst = &rt->dst;
if (fi) {
if (FIB_RES_GW(*res) &&
FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = FIB_RES_GW(*res);
- memcpy(rt->u.dst.metrics, fi->fib_metrics,
- sizeof(rt->u.dst.metrics));
- if (fi->fib_mtu == 0) {
- rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu;
- if (dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
- rt->rt_gateway != rt->rt_dst &&
- rt->u.dst.dev->mtu > 576)
- rt->u.dst.metrics[RTAX_MTU-1] = 576;
- }
-#ifdef CONFIG_NET_CLS_ROUTE
- rt->u.dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
+ rt_init_metrics(rt, fi);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
- } else
- rt->u.dst.metrics[RTAX_MTU-1]= rt->u.dst.dev->mtu;
-
- if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0)
- rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
- if (dst_mtu(&rt->u.dst) > IP_MAX_MTU)
- rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
- if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0)
- rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40,
- ip_rt_min_advmss);
- if (dst_metric(&rt->u.dst, RTAX_ADVMSS) > 65535 - 40)
- rt->u.dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;
-
-#ifdef CONFIG_NET_CLS_ROUTE
+ }
+
+ if (dst_mtu(dst) > IP_MAX_MTU)
+ dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU);
+ if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40)
+ dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40);
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
set_class_tag(rt, fib_rules_tclass(res));
#endif
set_class_tag(rt, itag);
#endif
- rt->rt_type = res->type;
+ rt->rt_type = type;
+}
+
+static struct rtable *rt_dst_alloc(bool nopolicy, bool noxfrm)
+{
+ struct rtable *rt = dst_alloc(&ipv4_dst_ops, 1);
+ if (rt) {
+ rt->dst.obsolete = -1;
+
+ rt->dst.flags = DST_HOST |
+ (nopolicy ? DST_NOPOLICY : 0) |
+ (noxfrm ? DST_NOXFRM : 0);
+ }
+ return rt;
}
+/* called in rcu_read_lock() section */
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
- unsigned hash;
+ unsigned int hash;
struct rtable *rth;
__be32 spec_dst;
- struct in_device *in_dev = in_dev_get(dev);
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
u32 itag = 0;
+ int err;
/* Primary sanity checks. */
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,
- dev, &spec_dst, &itag, 0) < 0)
- goto e_inval;
-
- rth = dst_alloc(&ipv4_dst_ops);
+ } else {
+ err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
+ &itag, 0);
+ if (err < 0)
+ goto e_err;
+ }
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
- rth->u.dst.output= ip_rt_bug;
+ rth->dst.output = ip_rt_bug;
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
- 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;
rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
- rth->u.dst.tclassid = itag;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ rth->dst.tclassid = itag;
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = init_net.loopback_dev;
- dev_hold(rth->u.dst.dev);
- rth->idev = in_dev_get(rth->u.dst.dev);
+ rth->dst.dev = init_net.loopback_dev;
+ dev_hold(rth->dst.dev);
rth->fl.oif = 0;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
if (our) {
- rth->u.dst.input= ip_local_deliver;
+ rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
}
#ifdef CONFIG_IP_MROUTE
if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
- rth->u.dst.input = ip_mr_input;
+ rth->dst.input = ip_mr_input;
#endif
RT_CACHE_STAT_INC(in_slow_mc);
- in_dev_put(in_dev);
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- return rt_intern_hash(hash, rth, NULL, skb);
+ rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
+ err = 0;
+ if (IS_ERR(rth))
+ err = PTR_ERR(rth);
e_nobufs:
- in_dev_put(in_dev);
return -ENOBUFS;
-
e_inval:
- in_dev_put(in_dev);
return -EINVAL;
+e_err:
+ return err;
}
#endif
}
+/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
- struct fib_result *res,
+ const 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;
+ unsigned int flags = 0;
__be32 spec_dst;
u32 itag;
/* get a working reference to the output device */
- out_dev = in_dev_get(FIB_RES_DEV(*res));
+ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
if (out_dev == NULL) {
if (net_ratelimit())
printk(KERN_CRIT "Bug in ip_route_input" \
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
- err = -EINVAL;
goto cleanup;
}
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
* invalid for proxy arp. DNAT routes are always valid.
+ *
+ * Proxy arp feature have been extended to allow, ARP
+ * replies back to the same interface, to support
+ * Private VLAN switch technologies. See arp.c.
*/
- if (out_dev == in_dev) {
+ if (out_dev == in_dev &&
+ IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
err = -EINVAL;
goto cleanup;
}
}
-
- rth = dst_alloc(&ipv4_dst_ops);
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ IN_DEV_CONF_GET(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
}
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
- if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->u.dst.flags |= DST_NOPOLICY;
- 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;
rth->rt_gateway = daddr;
rth->rt_iif =
rth->fl.iif = in_dev->dev->ifindex;
- rth->u.dst.dev = (out_dev)->dev;
- dev_hold(rth->u.dst.dev);
- rth->idev = in_dev_get(rth->u.dst.dev);
+ rth->dst.dev = (out_dev)->dev;
+ dev_hold(rth->dst.dev);
rth->fl.oif = 0;
rth->rt_spec_dst= spec_dst;
- rth->u.dst.input = ip_forward;
- rth->u.dst.output = ip_output;
- rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
+ rth->dst.input = ip_forward;
+ rth->dst.output = ip_output;
+ rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
- rt_set_nexthop(rth, res, itag);
+ rt_set_nexthop(rth, res, res->fi, res->type, itag);
rth->rt_flags = flags;
*result = rth;
err = 0;
cleanup:
- /* release the working reference to the output device */
- in_dev_put(out_dev);
return err;
}
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif,
- rt_genid(dev_net(rth->u.dst.dev)));
- return rt_intern_hash(hash, rth, NULL, skb);
+ rt_genid(dev_net(rth->dst.dev)));
+ rth = rt_intern_hash(hash, rth, skb, fl->iif);
+ if (IS_ERR(rth))
+ return PTR_ERR(rth);
+ return 0;
}
/*
* Such approach solves two big problems:
* 1. Not simplex devices are handled properly.
* 2. IP spoofing attempts are filtered with 100% of guarantee.
+ * called with rcu_read_lock()
*/
static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct fib_result res;
- struct in_device *in_dev = in_dev_get(dev);
- struct flowi fl = { .nl_u = { .ip4_u =
- { .daddr = daddr,
- .saddr = saddr,
- .tos = tos,
- .scope = RT_SCOPE_UNIVERSE,
- } },
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+ struct flowi fl = { .fl4_dst = daddr,
+ .fl4_src = saddr,
+ .fl4_tos = tos,
+ .fl4_scope = RT_SCOPE_UNIVERSE,
.mark = skb->mark,
.iif = dev->ifindex };
unsigned flags = 0;
unsigned hash;
__be32 spec_dst;
int err = -EINVAL;
- int free_res = 0;
struct net * net = dev_net(dev);
/* IP on this device is disabled. */
ipv4_is_loopback(saddr))
goto martian_source;
- if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0))
+ if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
goto brd_input;
/* Accept zero addresses only to limited broadcast;
if (ipv4_is_zeronet(saddr))
goto martian_source;
- if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) ||
- ipv4_is_loopback(daddr))
+ if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr))
goto martian_destination;
/*
* Now we are ready to route packet.
*/
- if ((err = fib_lookup(net, &fl, &res)) != 0) {
+ err = fib_lookup(net, &fl, &res);
+ if (err != 0) {
if (!IN_DEV_FORWARD(in_dev))
goto e_hostunreach;
goto no_route;
}
- free_res = 1;
RT_CACHE_STAT_INC(in_slow_tot);
goto brd_input;
if (res.type == RTN_LOCAL) {
- int result;
- result = fib_validate_source(saddr, daddr, tos,
- net->loopback_dev->ifindex,
- dev, &spec_dst, &itag, skb->mark);
- if (result < 0)
- goto martian_source;
- if (result)
+ err = fib_validate_source(saddr, daddr, tos,
+ net->loopback_dev->ifindex,
+ dev, &spec_dst, &itag, skb->mark);
+ if (err < 0)
+ goto martian_source_keep_err;
+ if (err)
flags |= RTCF_DIRECTSRC;
spec_dst = daddr;
goto local_input;
goto martian_destination;
err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos);
-done:
- in_dev_put(in_dev);
- if (free_res)
- fib_res_put(&res);
out: return err;
brd_input:
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
&itag, skb->mark);
if (err < 0)
- goto martian_source;
+ goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
}
RT_CACHE_STAT_INC(in_brd);
local_input:
- rth = dst_alloc(&ipv4_dst_ops);
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
- rth->u.dst.output= ip_rt_bug;
+ rth->dst.output= ip_rt_bug;
rth->rt_genid = rt_genid(net);
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
- 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;
rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
-#ifdef CONFIG_NET_CLS_ROUTE
- rth->u.dst.tclassid = itag;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ rth->dst.tclassid = itag;
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
- rth->u.dst.dev = net->loopback_dev;
- dev_hold(rth->u.dst.dev);
- rth->idev = in_dev_get(rth->u.dst.dev);
+ rth->dst.dev = net->loopback_dev;
+ dev_hold(rth->dst.dev);
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->u.dst.input= ip_local_deliver;
+ rth->dst.input= ip_local_deliver;
rth->rt_flags = flags|RTCF_LOCAL;
if (res.type == RTN_UNREACHABLE) {
- rth->u.dst.input= ip_error;
- rth->u.dst.error= -err;
+ rth->dst.input= ip_error;
+ rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
- err = rt_intern_hash(hash, rth, NULL, skb);
- goto done;
+ rth = rt_intern_hash(hash, rth, skb, fl.iif);
+ err = 0;
+ if (IS_ERR(rth))
+ err = PTR_ERR(rth);
+ goto out;
no_route:
RT_CACHE_STAT_INC(in_no_route);
e_hostunreach:
err = -EHOSTUNREACH;
- goto done;
+ goto out;
e_inval:
err = -EINVAL;
- goto done;
+ goto out;
e_nobufs:
err = -ENOBUFS;
- goto done;
+ goto out;
martian_source:
+ err = -EINVAL;
+martian_source_keep_err:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
- goto e_inval;
+ goto out;
}
-int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev)
+int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev, bool noref)
{
struct rtable * rth;
unsigned hash;
int iif = dev->ifindex;
struct net *net;
+ int res;
net = dev_net(dev);
+ rcu_read_lock();
+
if (!rt_caching(net))
goto skip_cache;
tos &= IPTOS_RT_MASK;
hash = rt_hash(daddr, saddr, iif, rt_genid(net));
- rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.dst.rt_next)) {
- if (((rth->fl.fl4_dst ^ daddr) |
- (rth->fl.fl4_src ^ saddr) |
+ rth = rcu_dereference(rth->dst.rt_next)) {
+ if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
+ ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
(rth->fl.iif ^ iif) |
rth->fl.oif |
(rth->fl.fl4_tos ^ tos)) == 0 &&
rth->fl.mark == skb->mark &&
- net_eq(dev_net(rth->u.dst.dev), net) &&
+ net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
- dst_use(&rth->u.dst, jiffies);
+ if (noref) {
+ dst_use_noref(&rth->dst, jiffies);
+ skb_dst_set_noref(skb, &rth->dst);
+ } else {
+ dst_use(&rth->dst, jiffies);
+ skb_dst_set(skb, &rth->dst);
+ }
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
- skb_dst_set(skb, &rth->u.dst);
return 0;
}
RT_CACHE_STAT_INC(in_hlist_search);
}
- rcu_read_unlock();
skip_cache:
/* Multicast recognition logic is moved from route cache to here.
route cache entry is created eventually.
*/
if (ipv4_is_multicast(daddr)) {
- struct in_device *in_dev;
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
- rcu_read_lock();
- if ((in_dev = __in_dev_get_rcu(dev)) != NULL) {
+ if (in_dev) {
int our = ip_check_mc(in_dev, daddr, saddr,
- ip_hdr(skb)->protocol);
+ ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
||
IN_DEV_MFORWARD(in_dev))
#endif
) {
+ int res = ip_route_input_mc(skb, daddr, saddr,
+ tos, dev, our);
rcu_read_unlock();
- return ip_route_input_mc(skb, daddr, saddr,
- tos, dev, our);
+ return res;
}
}
rcu_read_unlock();
return -EINVAL;
}
- return ip_route_input_slow(skb, daddr, saddr, tos, dev);
+ res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
+ rcu_read_unlock();
+ return res;
}
+EXPORT_SYMBOL(ip_route_input_common);
-static int __mkroute_output(struct rtable **result,
- struct fib_result *res,
- const struct flowi *fl,
- const struct flowi *oldflp,
- struct net_device *dev_out,
- unsigned flags)
+/* called with rcu_read_lock() */
+static struct rtable *__mkroute_output(const struct fib_result *res,
+ const struct flowi *fl,
+ const struct flowi *oldflp,
+ struct net_device *dev_out,
+ unsigned int flags)
{
- struct rtable *rth;
- struct in_device *in_dev;
+ struct fib_info *fi = res->fi;
u32 tos = RT_FL_TOS(oldflp);
- int err = 0;
+ struct in_device *in_dev;
+ u16 type = res->type;
+ struct rtable *rth;
- if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
- return -EINVAL;
+ if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags & IFF_LOOPBACK))
+ return ERR_PTR(-EINVAL);
- if (fl->fl4_dst == htonl(0xFFFFFFFF))
- res->type = RTN_BROADCAST;
+ if (ipv4_is_lbcast(fl->fl4_dst))
+ type = RTN_BROADCAST;
else if (ipv4_is_multicast(fl->fl4_dst))
- res->type = RTN_MULTICAST;
- else if (ipv4_is_lbcast(fl->fl4_dst) || ipv4_is_zeronet(fl->fl4_dst))
- return -EINVAL;
+ type = RTN_MULTICAST;
+ else if (ipv4_is_zeronet(fl->fl4_dst))
+ return ERR_PTR(-EINVAL);
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
- /* get work reference to inet device */
- in_dev = in_dev_get(dev_out);
+ in_dev = __in_dev_get_rcu(dev_out);
if (!in_dev)
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
- if (res->type == RTN_BROADCAST) {
+ if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
- if (res->fi) {
- fib_info_put(res->fi);
- res->fi = NULL;
- }
- } else if (res->type == RTN_MULTICAST) {
- flags |= RTCF_MULTICAST|RTCF_LOCAL;
+ fi = NULL;
+ } else if (type == RTN_MULTICAST) {
+ flags |= RTCF_MULTICAST | RTCF_LOCAL;
if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
oldflp->proto))
flags &= ~RTCF_LOCAL;
/* If multicast route do not exist use
- default one, but do not gateway in this case.
- Yes, it is hack.
+ * default one, but do not gateway in this case.
+ * Yes, it is hack.
*/
- if (res->fi && res->prefixlen < 4) {
- fib_info_put(res->fi);
- res->fi = NULL;
- }
- }
-
-
- rth = dst_alloc(&ipv4_dst_ops);
- if (!rth) {
- err = -ENOBUFS;
- goto cleanup;
+ if (fi && res->prefixlen < 4)
+ fi = NULL;
}
- atomic_set(&rth->u.dst.__refcnt, 1);
- rth->u.dst.flags= DST_HOST;
- if (IN_DEV_CONF_GET(in_dev, NOXFRM))
- rth->u.dst.flags |= DST_NOXFRM;
- if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
- rth->u.dst.flags |= DST_NOPOLICY;
+ rth = rt_dst_alloc(IN_DEV_CONF_GET(in_dev, NOPOLICY),
+ IN_DEV_CONF_GET(in_dev, NOXFRM));
+ if (!rth)
+ return ERR_PTR(-ENOBUFS);
rth->fl.fl4_dst = oldflp->fl4_dst;
rth->fl.fl4_tos = tos;
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;
+ rth->rt_iif = 0;
/* get references to the devices that are to be hold by the routing
cache entry */
- rth->u.dst.dev = dev_out;
+ rth->dst.dev = dev_out;
dev_hold(dev_out);
- rth->idev = in_dev_get(dev_out);
rth->rt_gateway = fl->fl4_dst;
rth->rt_spec_dst= fl->fl4_src;
- rth->u.dst.output=ip_output;
+ rth->dst.output=ip_output;
rth->rt_genid = rt_genid(dev_net(dev_out));
RT_CACHE_STAT_INC(out_slow_tot);
if (flags & RTCF_LOCAL) {
- rth->u.dst.input = ip_local_deliver;
+ rth->dst.input = ip_local_deliver;
rth->rt_spec_dst = fl->fl4_dst;
}
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
rth->rt_spec_dst = fl->fl4_src;
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
- rth->u.dst.output = ip_mc_output;
+ rth->dst.output = ip_mc_output;
RT_CACHE_STAT_INC(out_slow_mc);
}
#ifdef CONFIG_IP_MROUTE
- if (res->type == RTN_MULTICAST) {
+ if (type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
!ipv4_is_local_multicast(oldflp->fl4_dst)) {
- rth->u.dst.input = ip_mr_input;
- rth->u.dst.output = ip_mc_output;
+ rth->dst.input = ip_mr_input;
+ rth->dst.output = ip_mc_output;
}
}
#endif
}
- rt_set_nexthop(rth, res, 0);
+ rt_set_nexthop(rth, res, fi, type, 0);
rth->rt_flags = flags;
-
- *result = rth;
- cleanup:
- /* release work reference to inet device */
- in_dev_put(in_dev);
-
- return err;
-}
-
-static 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)
-{
- struct rtable *rth = NULL;
- 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,
- rt_genid(dev_net(dev_out)));
- err = rt_intern_hash(hash, rth, rp, NULL);
- }
-
- return err;
+ return rth;
}
/*
* Major route resolver routine.
+ * called with rcu_read_lock();
*/
-static int ip_route_output_slow(struct net *net, struct rtable **rp,
- const struct flowi *oldflp)
+static struct rtable *ip_route_output_slow(struct net *net,
+ const struct flowi *oldflp)
{
u32 tos = RT_FL_TOS(oldflp);
- struct flowi fl = { .nl_u = { .ip4_u =
- { .daddr = oldflp->fl4_dst,
- .saddr = oldflp->fl4_src,
- .tos = tos & IPTOS_RT_MASK,
- .scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK :
- RT_SCOPE_UNIVERSE),
- } },
- .mark = oldflp->mark,
- .iif = net->loopback_dev->ifindex,
- .oif = oldflp->oif };
+ struct flowi fl;
struct fib_result res;
- unsigned flags = 0;
+ unsigned int flags = 0;
struct net_device *dev_out = NULL;
- int free_res = 0;
- int err;
-
+ struct rtable *rth;
res.fi = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
+ fl.oif = oldflp->oif;
+ fl.iif = net->loopback_dev->ifindex;
+ fl.mark = oldflp->mark;
+ fl.fl4_dst = oldflp->fl4_dst;
+ fl.fl4_src = oldflp->fl4_src;
+ fl.fl4_tos = tos & IPTOS_RT_MASK;
+ fl.fl4_scope = ((tos & RTO_ONLINK) ?
+ RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+
+ rcu_read_lock();
if (oldflp->fl4_src) {
- err = -EINVAL;
+ rth = ERR_PTR(-EINVAL);
if (ipv4_is_multicast(oldflp->fl4_src) ||
ipv4_is_lbcast(oldflp->fl4_src) ||
ipv4_is_zeronet(oldflp->fl4_src))
if (oldflp->oif == 0 &&
(ipv4_is_multicast(oldflp->fl4_dst) ||
- oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+ ipv4_is_lbcast(oldflp->fl4_dst))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = ip_dev_find(net, oldflp->fl4_src);
+ dev_out = __ip_dev_find(net, oldflp->fl4_src, false);
if (dev_out == NULL)
goto out;
if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
- dev_out = ip_dev_find(net, oldflp->fl4_src);
- if (dev_out == NULL)
+ if (!__ip_dev_find(net, oldflp->fl4_src, false))
goto out;
- dev_put(dev_out);
- dev_out = NULL;
}
}
if (oldflp->oif) {
- dev_out = dev_get_by_index(net, oldflp->oif);
- err = -ENODEV;
+ dev_out = dev_get_by_index_rcu(net, oldflp->oif);
+ rth = ERR_PTR(-ENODEV);
if (dev_out == NULL)
goto out;
/* RACE: Check return value of inet_select_addr instead. */
- if (__in_dev_get_rtnl(dev_out) == NULL) {
- dev_put(dev_out);
- goto out; /* Wrong error code */
+ if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
+ rth = ERR_PTR(-ENETUNREACH);
+ goto out;
}
-
if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
- oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
+ ipv4_is_lbcast(oldflp->fl4_dst)) {
if (!fl.fl4_src)
fl.fl4_src = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
fl.fl4_dst = fl.fl4_src;
if (!fl.fl4_dst)
fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK);
- if (dev_out)
- dev_put(dev_out);
dev_out = net->loopback_dev;
- dev_hold(dev_out);
fl.oif = net->loopback_dev->ifindex;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
res.type = RTN_UNICAST;
goto make_route;
}
- if (dev_out)
- dev_put(dev_out);
- err = -ENETUNREACH;
+ rth = ERR_PTR(-ENETUNREACH);
goto out;
}
- free_res = 1;
if (res.type == RTN_LOCAL) {
- if (!fl.fl4_src)
- fl.fl4_src = fl.fl4_dst;
- if (dev_out)
- dev_put(dev_out);
+ if (!fl.fl4_src) {
+ if (res.fi->fib_prefsrc)
+ fl.fl4_src = res.fi->fib_prefsrc;
+ else
+ fl.fl4_src = fl.fl4_dst;
+ }
dev_out = net->loopback_dev;
- dev_hold(dev_out);
fl.oif = dev_out->ifindex;
- if (res.fi)
- fib_info_put(res.fi);
res.fi = NULL;
flags |= RTCF_LOCAL;
goto make_route;
else
#endif
if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
- fib_select_default(net, &fl, &res);
+ fib_select_default(&res);
if (!fl.fl4_src)
fl.fl4_src = FIB_RES_PREFSRC(res);
- if (dev_out)
- dev_put(dev_out);
dev_out = FIB_RES_DEV(res);
- dev_hold(dev_out);
fl.oif = dev_out->ifindex;
make_route:
- err = ip_mkroute_output(rp, &res, &fl, oldflp, dev_out, flags);
+ rth = __mkroute_output(&res, &fl, oldflp, dev_out, flags);
+ if (!IS_ERR(rth)) {
+ unsigned int hash;
+ hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
+ rt_genid(dev_net(dev_out)));
+ rth = rt_intern_hash(hash, rth, NULL, oldflp->oif);
+ }
- if (free_res)
- fib_res_put(&res);
- if (dev_out)
- dev_put(dev_out);
-out: return err;
+out:
+ rcu_read_unlock();
+ return rth;
}
-int __ip_route_output_key(struct net *net, struct rtable **rp,
- const struct flowi *flp)
+struct rtable *__ip_route_output_key(struct net *net, const struct flowi *flp)
{
- unsigned hash;
struct rtable *rth;
+ unsigned int hash;
if (!rt_caching(net))
goto slow_output;
hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
rcu_read_lock_bh();
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->u.dst.rt_next)) {
+ for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
+ rth = rcu_dereference_bh(rth->dst.rt_next)) {
if (rth->fl.fl4_dst == flp->fl4_dst &&
rth->fl.fl4_src == flp->fl4_src &&
- rth->fl.iif == 0 &&
+ rt_is_output_route(rth) &&
rth->fl.oif == flp->oif &&
rth->fl.mark == flp->mark &&
!((rth->fl.fl4_tos ^ flp->fl4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK)) &&
- net_eq(dev_net(rth->u.dst.dev), net) &&
+ net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
- dst_use(&rth->u.dst, jiffies);
+ dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
- *rp = rth;
- return 0;
+ return rth;
}
RT_CACHE_STAT_INC(out_hlist_search);
}
rcu_read_unlock_bh();
slow_output:
- return ip_route_output_slow(net, rp, flp);
+ return ip_route_output_slow(net, flp);
}
-
EXPORT_SYMBOL_GPL(__ip_route_output_key);
+static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
+{
+ return NULL;
+}
+
+static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+{
+ return 0;
+}
+
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
- .check = ipv4_dst_check,
+ .check = ipv4_blackhole_dst_check,
+ .default_mtu = ipv4_blackhole_default_mtu,
+ .default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
- .entries = ATOMIC_INIT(0),
};
-
-static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi *flp)
+struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rtable *ort = *rp;
- struct rtable *rt = (struct rtable *)
- dst_alloc(&ipv4_dst_blackhole_ops);
+ struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, 1);
+ struct rtable *ort = (struct rtable *) dst_orig;
if (rt) {
- struct dst_entry *new = &rt->u.dst;
+ struct dst_entry *new = &rt->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));
+ dst_copy_metrics(new, &ort->dst);
- new->dev = ort->u.dst.dev;
+ new->dev = ort->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_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->peer = ort->peer;
if (rt->peer)
atomic_inc(&rt->peer->refcnt);
+ rt->fi = ort->fi;
+ if (rt->fi)
+ atomic_inc(&rt->fi->fib_clntref);
dst_free(new);
}
- dst_release(&(*rp)->u.dst);
- *rp = rt;
- return (rt ? 0 : -ENOMEM);
+ dst_release(dst_orig);
+
+ return rt ? &rt->dst : ERR_PTR(-ENOMEM);
}
-int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
- struct sock *sk, int flags)
+struct rtable *ip_route_output_flow(struct net *net, struct flowi *flp,
+ struct sock *sk)
{
- int err;
+ struct rtable *rt = __ip_route_output_key(net, flp);
- if ((err = __ip_route_output_key(net, rp, flp)) != 0)
- return err;
+ if (IS_ERR(rt))
+ return rt;
if (flp->proto) {
if (!flp->fl4_src)
- flp->fl4_src = (*rp)->rt_src;
+ flp->fl4_src = rt->rt_src;
if (!flp->fl4_dst)
- flp->fl4_dst = (*rp)->rt_dst;
- err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk,
- flags ? XFRM_LOOKUP_WAIT : 0);
- if (err == -EREMOTE)
- err = ipv4_dst_blackhole(net, rp, flp);
-
- return err;
+ flp->fl4_dst = rt->rt_dst;
+ rt = (struct rtable *) xfrm_lookup(net, &rt->dst, flp, sk, 0);
}
- return 0;
+ return rt;
}
-
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-int ip_route_output_key(struct net *net, struct rtable **rp, struct flowi *flp)
-{
- return ip_route_output_flow(net, rp, flp, NULL, 0);
-}
-
static int rt_fill_info(struct net *net,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
r->rtm_src_len = 32;
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);
-#ifdef CONFIG_NET_CLS_ROUTE
- if (rt->u.dst.tclassid)
- NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid);
+ if (rt->dst.dev)
+ NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ if (rt->dst.tclassid)
+ NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
#endif
- if (rt->fl.iif)
+ if (rt_is_input_route(rt))
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
else if (rt->rt_src != rt->fl.fl4_src)
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
if (rt->rt_dst != rt->rt_gateway)
NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway);
- if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
+ if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
- error = rt->u.dst.error;
- expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
+ if (rt->fl.mark)
+ NLA_PUT_BE32(skb, RTA_MARK, rt->fl.mark);
+
+ error = rt->dst.error;
+ expires = (rt->peer && rt->peer->pmtu_expires) ?
+ rt->peer->pmtu_expires - jiffies : 0;
if (rt->peer) {
+ inet_peer_refcheck(rt->peer);
id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
if (rt->peer->tcp_ts_stamp) {
ts = rt->peer->tcp_ts;
}
}
- if (rt->fl.iif) {
+ if (rt_is_input_route(rt)) {
#ifdef CONFIG_IP_MROUTE
__be32 dst = rt->rt_dst;
NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif);
}
- if (rtnl_put_cacheinfo(skb, &rt->u.dst, id, ts, tsage,
+ if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
expires, error) < 0)
goto nla_put_failure;
__be32 src = 0;
u32 iif;
int err;
+ int mark;
struct sk_buff *skb;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
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;
+ mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
if (iif) {
struct net_device *dev;
skb->protocol = htons(ETH_P_IP);
skb->dev = dev;
+ skb->mark = mark;
local_bh_disable();
err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
local_bh_enable();
rt = skb_rtable(skb);
- if (err == 0 && rt->u.dst.error)
- err = -rt->u.dst.error;
+ if (err == 0 && rt->dst.error)
+ err = -rt->dst.error;
} else {
struct flowi fl = {
- .nl_u = {
- .ip4_u = {
- .daddr = dst,
- .saddr = src,
- .tos = rtm->rtm_tos,
- },
- },
+ .fl4_dst = dst,
+ .fl4_src = src,
+ .fl4_tos = rtm->rtm_tos,
.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
+ .mark = mark,
};
- err = ip_route_output_key(net, &rt, &fl);
+ rt = ip_route_output_key(net, &fl);
+
+ err = 0;
+ if (IS_ERR(rt))
+ err = PTR_ERR(rt);
}
if (err)
goto errout_free;
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
if (!rt_hash_table[h].chain)
continue;
rcu_read_lock_bh();
- for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
- if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
+ for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
+ rt = rcu_dereference_bh(rt->dst.rt_next), idx++) {
+ if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx)
continue;
if (rt_is_expired(rt))
continue;
- skb_dst_set(skb, dst_clone(&rt->u.dst));
+ skb_dst_set_noref(skb, &rt->dst);
if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
return -EINVAL;
}
-static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table,
- void __user *oldval,
- size_t __user *oldlenp,
- void __user *newval,
- size_t newlen)
-{
- int delay;
- struct net *net;
- if (newlen != sizeof(int))
- return -EINVAL;
- if (get_user(delay, (int __user *)newval))
- return -EFAULT;
- net = (struct net *)table->extra1;
- rt_cache_flush(net, delay);
- return 0;
-}
-
-static void rt_secret_reschedule(int old)
-{
- struct net *net;
- int new = ip_rt_secret_interval;
- int diff = new - old;
-
- if (!diff)
- return;
-
- rtnl_lock();
- for_each_net(net) {
- int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
-
- if (!new)
- continue;
-
- if (deleted) {
- long time = net->ipv4.rt_secret_timer.expires - jiffies;
-
- if (time <= 0 || (time += diff) <= 0)
- time = 0;
-
- net->ipv4.rt_secret_timer.expires = time;
- } else
- net->ipv4.rt_secret_timer.expires = new;
-
- net->ipv4.rt_secret_timer.expires += jiffies;
- add_timer(&net->ipv4.rt_secret_timer);
- }
- rtnl_unlock();
-}
-
-static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int old = ip_rt_secret_interval;
- int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
-
- rt_secret_reschedule(old);
-
- return ret;
-}
-
-static int ipv4_sysctl_rt_secret_interval_strategy(ctl_table *table,
- void __user *oldval,
- size_t __user *oldlenp,
- void __user *newval,
- size_t newlen)
-{
- int old = ip_rt_secret_interval;
- int ret = sysctl_jiffies(table, oldval, oldlenp, newval, newlen);
-
- rt_secret_reschedule(old);
-
- return ret;
-}
-
static ctl_table ipv4_route_table[] = {
{
- .ctl_name = NET_IPV4_ROUTE_GC_THRESH,
.procname = "gc_thresh",
.data = &ipv4_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_MAX_SIZE,
.procname = "max_size",
.data = &ip_rt_max_size,
.maxlen = sizeof(int),
{
/* Deprecated. Use gc_min_interval_ms */
- .ctl_name = NET_IPV4_ROUTE_GC_MIN_INTERVAL,
.procname = "gc_min_interval",
.data = &ip_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS,
.procname = "gc_min_interval_ms",
.data = &ip_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
- .strategy = sysctl_ms_jiffies,
},
{
- .ctl_name = NET_IPV4_ROUTE_GC_TIMEOUT,
.procname = "gc_timeout",
.data = &ip_rt_gc_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV4_ROUTE_GC_INTERVAL,
.procname = "gc_interval",
.data = &ip_rt_gc_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV4_ROUTE_REDIRECT_LOAD,
.procname = "redirect_load",
.data = &ip_rt_redirect_load,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_REDIRECT_NUMBER,
.procname = "redirect_number",
.data = &ip_rt_redirect_number,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_REDIRECT_SILENCE,
.procname = "redirect_silence",
.data = &ip_rt_redirect_silence,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_ERROR_COST,
.procname = "error_cost",
.data = &ip_rt_error_cost,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_ERROR_BURST,
.procname = "error_burst",
.data = &ip_rt_error_burst,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_GC_ELASTICITY,
.procname = "gc_elasticity",
.data = &ip_rt_gc_elasticity,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_MTU_EXPIRES,
.procname = "mtu_expires",
.data = &ip_rt_mtu_expires,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_IPV4_ROUTE_MIN_PMTU,
.procname = "min_pmtu",
.data = &ip_rt_min_pmtu,
.maxlen = sizeof(int),
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_IPV4_ROUTE_MIN_ADVMSS,
.procname = "min_adv_mss",
.data = &ip_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .ctl_name = NET_IPV4_ROUTE_SECRET_INTERVAL,
- .procname = "secret_interval",
- .data = &ip_rt_secret_interval,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = ipv4_sysctl_rt_secret_interval,
- .strategy = ipv4_sysctl_rt_secret_interval_strategy,
- },
- { .ctl_name = 0 }
+ { }
};
static struct ctl_table empty[1];
static struct ctl_table ipv4_skeleton[] =
{
- { .procname = "route", .ctl_name = NET_IPV4_ROUTE,
+ { .procname = "route",
.mode = 0555, .child = ipv4_route_table},
- { .procname = "neigh", .ctl_name = NET_IPV4_NEIGH,
+ { .procname = "neigh",
.mode = 0555, .child = empty},
{ }
};
static __net_initdata struct ctl_path ipv4_path[] = {
- { .procname = "net", .ctl_name = CTL_NET, },
- { .procname = "ipv4", .ctl_name = NET_IPV4, },
+ { .procname = "net", },
+ { .procname = "ipv4", },
{ },
};
static struct ctl_table ipv4_route_flush_table[] = {
{
- .ctl_name = NET_IPV4_ROUTE_FLUSH,
.procname = "flush",
.maxlen = sizeof(int),
.mode = 0200,
.proc_handler = ipv4_sysctl_rtcache_flush,
- .strategy = ipv4_sysctl_rtcache_flush_strategy,
},
- { .ctl_name = 0 },
+ { },
};
static __net_initdata struct ctl_path ipv4_route_path[] = {
- { .procname = "net", .ctl_name = CTL_NET, },
- { .procname = "ipv4", .ctl_name = NET_IPV4, },
- { .procname = "route", .ctl_name = NET_IPV4_ROUTE, },
+ { .procname = "net", },
+ { .procname = "ipv4", },
+ { .procname = "route", },
{ },
};
struct ctl_table *tbl;
tbl = ipv4_route_flush_table;
- if (net != &init_net) {
+ if (!net_eq(net, &init_net)) {
tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
if (tbl == NULL)
goto err_dup;
};
#endif
-
-static __net_init int rt_secret_timer_init(struct net *net)
+static __net_init int rt_genid_init(struct net *net)
{
- atomic_set(&net->ipv4.rt_genid,
- (int) ((num_physpages ^ (num_physpages>>8)) ^
- (jiffies ^ (jiffies >> 7))));
-
- net->ipv4.rt_secret_timer.function = rt_secret_rebuild;
- net->ipv4.rt_secret_timer.data = (unsigned long)net;
- init_timer_deferrable(&net->ipv4.rt_secret_timer);
-
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires =
- jiffies + net_random() % ip_rt_secret_interval +
- ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ get_random_bytes(&net->ipv4.rt_genid,
+ sizeof(net->ipv4.rt_genid));
return 0;
}
-static __net_exit void rt_secret_timer_exit(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
-}
-
-static __net_initdata struct pernet_operations rt_secret_timer_ops = {
- .init = rt_secret_timer_init,
- .exit = rt_secret_timer_exit,
+static __net_initdata struct pernet_operations rt_genid_ops = {
+ .init = rt_genid_init,
};
-#ifdef CONFIG_NET_CLS_ROUTE
-struct ip_rt_acct *ip_rt_acct __read_mostly;
-#endif /* CONFIG_NET_CLS_ROUTE */
+#ifdef CONFIG_IP_ROUTE_CLASSID
+struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
+#endif /* CONFIG_IP_ROUTE_CLASSID */
static __initdata unsigned long rhash_entries;
static int __init set_rhash_entries(char *str)
{
int rc = 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
if (!ip_rt_acct)
panic("IP: failed to allocate ip_rt_acct\n");
ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep;
+ if (dst_entries_init(&ipv4_dst_ops) < 0)
+ panic("IP: failed to allocate ipv4_dst_ops counter\n");
+
+ if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0)
+ panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n");
+
rt_hash_table = (struct rt_hash_bucket *)
alloc_large_system_hash("IP route cache",
sizeof(struct rt_hash_bucket),
devinet_init();
ip_fib_init();
- /* All the timers, started at system startup tend
- to synchronize. Perturb it a bit.
- */
- INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
- expires_ljiffies = jiffies;
- schedule_delayed_work(&expires_work,
- net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
-
- if (register_pernet_subsys(&rt_secret_timer_ops))
- printk(KERN_ERR "Unable to setup rt_secret_timer\n");
-
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
+ register_pernet_subsys(&rt_genid_ops);
return rc;
}
register_sysctl_paths(ipv4_path, ipv4_skeleton);
}
#endif
-
-EXPORT_SYMBOL(__ip_select_ident);
-EXPORT_SYMBOL(ip_route_input);
-EXPORT_SYMBOL(ip_route_output_key);