#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 void rt_worker_func(struct work_struct *work);
-static DECLARE_DELAYED_WORK(expires_work, rt_worker_func);
+static struct delayed_work expires_work;
+static unsigned long expires_ljiffies;
/*
* Interface to generic destination cache.
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 struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
- .protocol = __constant_htons(ETH_P_IP),
+ .protocol = cpu_to_be16(ETH_P_IP),
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
.destroy = ipv4_dst_destroy,
(__raw_get_cpu_var(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;
}
if (!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) &&
r->rt_genid == st->genid)
return r;
- r = rcu_dereference(r->u.dst.rt_next);
+ r = rcu_dereference_bh(r->u.dst.rt_next);
}
rcu_read_unlock_bh();
}
rcu_read_lock_bh();
r = rt_hash_table[st->bucket].chain;
}
- return rcu_dereference(r);
+ return rcu_dereference_bh(r);
}
static struct rtable *rt_cache_get_next(struct seq_file *seq,
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",
+ 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->u.dst.dev ? r->u.dst.dev->name : "*",
- (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
+ (__force u32)r->rt_dst,
+ (__force u32)r->rt_gateway,
r->rt_flags, atomic_read(&r->u.dst.__refcnt),
- r->u.dst.__use, 0, (unsigned long)r->rt_src,
+ r->u.dst.__use, 0, (__force u32)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),
};
#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;
+static int rt_acct_proc_show(struct seq_file *m, void *v)
+{
+ struct ip_rt_acct *dst, *src;
+ unsigned int i, j;
+
+ dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL);
+ if (!dst)
+ return -ENOMEM;
+
+ 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)
goto err2;
#ifdef CONFIG_NET_CLS_ROUTE
- pde = create_proc_read_entry("rt_acct", 0, net->proc_net,
- ip_rt_acct_read, NULL);
+ pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
if (!pde)
goto err3;
#endif
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
+#ifdef CONFIG_NET_CLS_ROUTE
remove_proc_entry("rt_acct", net->proc_net);
+#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
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->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(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->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->nl_u.ip4_u.tos ^
- *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.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->u.dst.dev), dev_net(rt2->u.dst.dev));
}
static inline int rt_is_expired(struct rtable *rth)
#define FRACT_BITS 3
#define ONE (1UL << FRACT_BITS)
+/*
+ * 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 int has_noalias(const struct rtable *head, const struct rtable *rth)
+{
+ const struct rtable *aux = head;
+
+ while (aux != rth) {
+ if (compare_hash_inputs(&aux->fl, &rth->fl))
+ return 0;
+ aux = aux->u.dst.rt_next;
+ }
+ return ONE;
+}
+
static void rt_check_expire(void)
{
static unsigned int rover;
unsigned int i = rover, goal;
struct rtable *rth, **rthp;
- unsigned long length = 0, samples = 0;
+ unsigned long samples = 0;
unsigned long sum = 0, sum2 = 0;
+ unsigned long delta;
u64 mult;
- mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
+ 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;
- length = 0;
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 (*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);
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;
/*
- * Only bump our length if the hash
- * inputs on entries n and n+1 are not
- * the same, we only count entries on
+ * 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
*/
- if ((*rthp == NULL) ||
- !compare_hash_inputs(&(*rthp)->fl,
- &rth->fl))
- length += ONE;
+ length += has_noalias(rt_hash_table[i].chain, rth);
continue;
}
- } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
- tmo >>= 1;
- rthp = &rth->u.dst.rt_next;
- if ((*rthp == NULL) ||
- !compare_hash_inputs(&(*rthp)->fl,
- &rth->fl))
- length += ONE;
- 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_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);
-}
-
-static void rt_secret_rebuild_oneshot(struct net *net)
+/* Flush previous cache invalidated entries from the cache */
+void rt_cache_flush_batch(void)
{
- 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(!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);
}
/*
out: return 0;
}
-static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
+/*
+ * 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 = rth->u.dst.rt_next;
+ }
+ return length >> FRACT_BITS;
+}
+
+static int rt_intern_hash(unsigned hash, struct rtable *rt,
+ struct rtable **rp, struct sk_buff *skb, int ifindex)
{
struct rtable *rth, **rthp;
- struct rtable *rthi;
unsigned long now;
struct rtable *cand, **candp;
u32 min_score;
now = jiffies;
if (!rt_caching(dev_net(rt->u.dst.dev))) {
- rt_drop(rt);
- return 0;
+ /*
+ * If we're not caching, just tell the caller we
+ * were successful and don't touch the route. The
+ * caller hold the sole reference to the cache entry, and
+ * it will be released when the caller is done with it.
+ * If we drop it here, the callers have no way to resolve routes
+ * when we're not caching. Instead, just point *rp at rt, so
+ * the caller gets a single use out of the route
+ * 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.
+ */
+
+ if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
+ int err = arp_bind_neighbour(&rt->u.dst);
+ if (err) {
+ if (net_ratelimit())
+ printk(KERN_WARNING
+ "Neighbour table failure & not caching routes.\n");
+ rt_drop(rt);
+ return err;
+ }
+ }
+
+ rt_free(rt);
+ goto skip_hashing;
}
rthp = &rt_hash_table[hash].chain;
- rthi = NULL;
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
- *rp = rth;
+ if (rp)
+ *rp = rth;
+ else
+ skb_dst_set(skb, &rth->u.dst);
return 0;
}
chain_length++;
rthp = &rth->u.dst.rt_next;
-
- /*
- * check to see if the next entry in the chain
- * contains the same hash input values as rt. If it does
- * This is where we will insert into the list, instead of
- * at the head. This groups entries that differ by aspects not
- * relvant to the hash function together, which we use to adjust
- * our chain length
- */
- if (*rthp && compare_hash_inputs(&(*rthp)->fl, &rt->fl))
- rthi = rth;
}
if (cand) {
rt_free(cand);
}
} else {
- if (chain_length > rt_chain_length_max) {
+ 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->u.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_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;
}
}
}
}
- if (rthi)
- rt->u.dst.rt_next = rthi->u.dst.rt_next;
- else
- rt->u.dst.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.dst.rt_next) {
struct rtable *trt;
- printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst);
+ 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)
printk(" . %pI4", &trt->rt_dst);
printk("\n");
* previous writes to rt are comitted to memory
* before making rt visible to other CPUS.
*/
- if (rthi)
- rcu_assign_pointer(rthi->u.dst.rt_next, rt);
- else
- rcu_assign_pointer(rt_hash_table[hash].chain, rt);
+ rcu_assign_pointer(rt_hash_table[hash].chain, rt);
spin_unlock_bh(rt_hash_lock_addr(hash));
- *rp = rt;
+
+skip_hashing:
+ if (rp)
+ *rp = rt;
+ else
+ skb_dst_set(skb, &rt->u.dst);
return 0;
}
return;
net = dev_net(dev);
- if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
- || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw)
- || ipv4_is_zeronet(new_gw))
+ if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) ||
+ ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) ||
+ ipv4_is_zeronet(new_gw))
goto reject_redirect;
if (!rt_caching(net))
dev_hold(rt->u.dst.dev);
if (rt->idev)
in_dev_hold(rt->idev);
- rt->u.dst.obsolete = 0;
+ rt->u.dst.obsolete = -1;
rt->u.dst.lastuse = jiffies;
rt->u.dst.path = &rt->u.dst;
rt->u.dst.neighbour = NULL;
&netevent);
rt_del(hash, rth);
- if (!rt_intern_hash(hash, rt, &rt))
+ if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif))
ip_rt_put(rt);
goto do_next;
}
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) {
+ (rt->u.dst.expires &&
+ time_after_eq(jiffies, rt->u.dst.expires))) {
unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
rt->fl.oif,
rt_genid(dev_net(dst->dev)));
void ip_rt_send_redirect(struct sk_buff *skb)
{
- struct rtable *rt = skb->rtable;
- struct in_device *in_dev = in_dev_get(rt->u.dst.dev);
+ struct rtable *rt = skb_rtable(skb);
+ struct in_device *in_dev;
+ int log_martians;
- if (!in_dev)
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(rt->u.dst.dev);
+ if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
+ rcu_read_unlock();
return;
-
- if (!IN_DEV_TX_REDIRECTS(in_dev))
- goto out;
+ }
+ log_martians = IN_DEV_LOG_MARTIANS(in_dev);
+ rcu_read_unlock();
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) {
rt->u.dst.rate_last = jiffies;
- goto out;
+ return;
}
/* Check for load limit; set rate_last to the latest sent
rt->u.dst.rate_last = jiffies;
++rt->u.dst.rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (IN_DEV_LOG_MARTIANS(in_dev) &&
+ if (log_martians &&
rt->u.dst.rate_tokens == ip_rt_redirect_number &&
net_ratelimit())
printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
&rt->rt_dst, &rt->rt_gateway);
#endif
}
-out:
- in_dev_put(in_dev);
}
static int ip_error(struct sk_buff *skb)
{
- struct rtable *rt = skb->rtable;
+ struct rtable *rt = skb_rtable(skb);
unsigned long now;
int code;
__be32 daddr = iph->daddr;
unsigned short est_mtu = 0;
- if (ipv4_config.no_pmtu_disc)
- return 0;
-
for (k = 0; k < 2; k++) {
for (i = 0; i < 2; i++) {
unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
- return NULL;
+ if (rt_is_expired((struct rtable *)dst))
+ return NULL;
+ return dst;
}
static void ipv4_dst_destroy(struct dst_entry *dst)
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
- rt = skb->rtable;
+ rt = skb_rtable(skb);
if (rt)
dst_set_expires(&rt->u.dst, 0);
}
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)
+ dev, &spec_dst, &itag, 0) < 0)
goto e_inval;
rth = dst_alloc(&ipv4_dst_ops);
if (!rth)
goto e_nobufs;
- rth->u.dst.output= ip_rt_bug;
+ rth->u.dst.output = ip_rt_bug;
+ rth->u.dst.obsolete = -1;
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
in_dev_put(in_dev);
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- return rt_intern_hash(hash, rth, &skb->rtable);
+ return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
e_nobufs:
in_dev_put(in_dev);
err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res),
- in_dev->dev, &spec_dst, &itag);
+ in_dev->dev, &spec_dst, &itag, skb->mark);
if (err < 0) {
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
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->fl.oif = 0;
rth->rt_spec_dst= spec_dst;
+ rth->u.dst.obsolete = -1;
rth->u.dst.input = ip_forward;
rth->u.dst.output = ip_output;
rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
/* 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, &skb->rtable);
+ return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
}
/*
int result;
result = fib_validate_source(saddr, daddr, tos,
net->loopback_dev->ifindex,
- dev, &spec_dst, &itag);
+ dev, &spec_dst, &itag, skb->mark);
if (result < 0)
goto martian_source;
if (result)
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
else {
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
- &itag);
+ &itag, skb->mark);
if (err < 0)
goto martian_source;
if (err)
goto e_nobufs;
rth->u.dst.output= ip_rt_bug;
+ rth->u.dst.obsolete = -1;
rth->rt_genid = rt_genid(net);
atomic_set(&rth->u.dst.__refcnt, 1);
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
- err = rt_intern_hash(hash, rth, &skb->rtable);
+ err = rt_intern_hash(hash, rth, NULL, skb, fl.iif);
goto done;
no_route:
goto e_inval;
}
-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;
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) |
+ 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) &&
!rt_is_expired(rth)) {
- dst_use(&rth->u.dst, jiffies);
+ if (noref) {
+ dst_use_noref(&rth->u.dst, jiffies);
+ skb_dst_set_noref(skb, &rth->u.dst);
+ } else {
+ dst_use(&rth->u.dst, jiffies);
+ skb_dst_set(skb, &rth->u.dst);
+ }
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
- skb->rtable = rth;
return 0;
}
RT_CACHE_STAT_INC(in_hlist_search);
ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
- || (!ipv4_is_local_multicast(daddr) &&
- IN_DEV_MFORWARD(in_dev))
+ ||
+ (!ipv4_is_local_multicast(daddr) &&
+ IN_DEV_MFORWARD(in_dev))
#endif
- ) {
+ ) {
rcu_read_unlock();
return ip_route_input_mc(skb, daddr, saddr,
tos, dev, our);
}
return ip_route_input_slow(skb, daddr, saddr, tos, dev);
}
+EXPORT_SYMBOL(ip_route_input_common);
static int __mkroute_output(struct rtable **result,
struct fib_result *res,
rth->rt_spec_dst= fl->fl4_src;
rth->u.dst.output=ip_output;
+ rth->u.dst.obsolete = -1;
rth->rt_genid = rt_genid(dev_net(dev_out));
RT_CACHE_STAT_INC(out_slow_tot);
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);
+ err = rt_intern_hash(hash, rth, rp, NULL, oldflp->oif);
}
return err;
of another iface. --ANK
*/
- if (oldflp->oif == 0
- && (ipv4_is_multicast(oldflp->fl4_dst) ||
- oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
+ if (oldflp->oif == 0 &&
+ (ipv4_is_multicast(oldflp->fl4_dst) ||
+ oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
dev_out = ip_dev_find(net, oldflp->fl4_src);
if (dev_out == NULL)
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->u.dst.rt_next)) {
if (rth->fl.fl4_dst == flp->fl4_dst &&
rth->fl.fl4_src == flp->fl4_src &&
rth->fl.iif == 0 &&
static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
- .protocol = __constant_htons(ETH_P_IP),
+ .protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
.check = ipv4_dst_check,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
- struct rtable *rt = skb->rtable;
+ struct rtable *rt = skb_rtable(skb);
struct rtmsg *r;
struct nlmsghdr *nlh;
long expires;
error = rt->u.dst.error;
expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
if (rt->peer) {
- id = rt->peer->ip_id_count;
+ id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
if (rt->peer->tcp_ts_stamp) {
ts = rt->peer->tcp_ts;
tsage = get_seconds() - rt->peer->tcp_ts_stamp;
err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
local_bh_enable();
- rt = skb->rtable;
+ rt = skb_rtable(skb);
if (err == 0 && rt->u.dst.error)
err = -rt->u.dst.error;
} else {
if (err)
goto errout_free;
- skb->rtable = rt;
+ skb_dst_set(skb, &rt->u.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++) {
+ for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
+ rt = rcu_dereference_bh(rt->u.dst.rt_next), idx++) {
if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
continue;
if (rt_is_expired(rt))
continue;
- skb->dst = dst_clone(&rt->u.dst);
+ skb_dst_set_noref(skb, &rt->u.dst);
if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
- dst_release(xchg(&skb->dst, NULL));
+ skb_dst_drop(skb);
rcu_read_unlock_bh();
goto done;
}
- dst_release(xchg(&skb->dst, NULL));
+ skb_dst_drop(skb);
}
rcu_read_unlock_bh();
}
#ifdef CONFIG_SYSCTL
static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
if (write) {
memcpy(&ctl, __ctl, sizeof(ctl));
ctl.data = &flush_delay;
- proc_dointvec(&ctl, write, filp, buffer, lenp, ppos);
+ proc_dointvec(&ctl, write, buffer, lenp, ppos);
net = (struct net *)__ctl->extra1;
rt_cache_flush(net, flush_delay);
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,
- struct file *filp,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int old = ip_rt_secret_interval;
- int ret = proc_dointvec_jiffies(ctl, write, filp, 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;
+struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
#endif /* CONFIG_NET_CLS_ROUTE */
static __initdata unsigned long rhash_entries;
int rc = 0;
#ifdef CONFIG_NET_CLS_ROUTE
- ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct));
+ 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");
#endif
alloc_large_system_hash("IP route cache",
sizeof(struct rt_hash_bucket),
rhash_entries,
- (num_physpages >= 128 * 1024) ?
+ (totalram_pages >= 128 * 1024) ?
15 : 17,
0,
&rt_hash_log,
&rt_hash_mask,
- 0);
+ rhash_entries ? 0 : 512 * 1024);
memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
rt_hash_lock_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
xfrm_init();
- xfrm4_init();
+ xfrm4_init(ip_rt_max_size);
#endif
rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
+ register_pernet_subsys(&rt_genid_ops);
return rc;
}
#endif
EXPORT_SYMBOL(__ip_select_ident);
-EXPORT_SYMBOL(ip_route_input);
EXPORT_SYMBOL(ip_route_output_key);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff