aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r--net/ipv4/route.c213
1 files changed, 180 insertions, 33 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 75ef66f..6b95f74 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -91,6 +91,7 @@
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <linux/slab.h>
+#include <linux/prefetch.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
@@ -132,6 +133,9 @@ static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
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.
*/
@@ -412,7 +416,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
"HHUptod\tSpecDst");
else {
struct rtable *r = v;
- int len;
+ struct neighbour *n;
+ int len, HHUptod;
+
+ rcu_read_lock();
+ n = dst_get_neighbour(&r->dst);
+ HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+ rcu_read_unlock();
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",
@@ -427,8 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
dst_metric(&r->dst, RTAX_RTTVAR)),
r->rt_key_tos,
r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1,
- r->dst.hh ? (r->dst.hh->hh_output ==
- dev_queue_xmit) : 0,
+ HHUptod,
r->rt_spec_dst, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
@@ -821,6 +830,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth)
return ONE;
}
+static void rt_check_expire(void)
+{
+ static unsigned int rover;
+ unsigned int i = rover, goal;
+ struct rtable *rth;
+ struct rtable __rcu **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 (rcu_dereference_raw(*rthp) == NULL)
+ continue;
+ length = 0;
+ spin_lock_bh(rt_hash_lock_addr(i));
+ while ((rth = rcu_dereference_protected(*rthp,
+ lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
+ prefetch(rth->dst.rt_next);
+ if (rt_is_expired(rth)) {
+ *rthp = rth->dst.rt_next;
+ rt_free(rth);
+ continue;
+ }
+ if (rth->dst.expires) {
+ /* Entry is expired even if it is in use */
+ if (time_before_eq(jiffies, rth->dst.expires)) {
+nofree:
+ tmo >>= 1;
+ rthp = &rth->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
+ */
+ length += has_noalias(rt_hash_table[i].chain, rth);
+ continue;
+ }
+ } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+ goto nofree;
+
+ /* Cleanup aged off entries. */
+ *rthp = rth->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
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+ rt_check_expire();
+ schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+}
+
/*
* Perturbation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
@@ -1269,11 +1369,41 @@ static void rt_del(unsigned hash, struct rtable *rt)
spin_unlock_bh(rt_hash_lock_addr(hash));
}
+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;
+ struct neighbour *n, *old_n;
+
+ dst_confirm(&rt->dst);
+
+ rt->rt_gateway = peer->redirect_learned.a4;
+ n = __arp_bind_neighbour(&rt->dst, rt->rt_gateway);
+ if (IS_ERR(n))
+ return PTR_ERR(n);
+ old_n = xchg(&rt->dst._neighbour, n);
+ if (old_n)
+ neigh_release(old_n);
+ if (!n || !(n->nud_state & NUD_VALID)) {
+ if (n)
+ neigh_event_send(n, NULL);
+ rt->rt_gateway = orig_gw;
+ return -EAGAIN;
+ } else {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+ }
+ return 0;
+}
+
/* 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 s, i;
struct in_device *in_dev = __in_dev_get_rcu(dev);
+ __be32 skeys[2] = { saddr, 0 };
+ int ikeys[2] = { dev->ifindex, 0 };
struct inet_peer *peer;
struct net *net;
@@ -1296,13 +1426,43 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
goto reject_redirect;
}
- peer = inet_getpeer_v4(daddr, 1);
- if (peer) {
- peer->redirect_learned.a4 = new_gw;
+ for (s = 0; s < 2; s++) {
+ for (i = 0; i < 2; i++) {
+ unsigned int hash;
+ struct rtable __rcu **rthp;
+ struct rtable *rt;
- inet_putpeer(peer);
+ hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
- atomic_inc(&__rt_peer_genid);
+ rthp = &rt_hash_table[hash].chain;
+
+ while ((rt = rcu_dereference(*rthp)) != NULL) {
+ rthp = &rt->dst.rt_next;
+
+ if (rt->rt_key_dst != daddr ||
+ rt->rt_key_src != skeys[s] ||
+ rt->rt_oif != ikeys[i] ||
+ rt_is_input_route(rt) ||
+ rt_is_expired(rt) ||
+ !net_eq(dev_net(rt->dst.dev), net) ||
+ rt->dst.error ||
+ rt->dst.dev != dev ||
+ rt->rt_gateway != old_gw)
+ continue;
+
+ if (!rt->peer)
+ rt_bind_peer(rt, rt->rt_dst, 1);
+
+ peer = rt->peer;
+ if (peer) {
+ if (peer->redirect_learned.a4 != new_gw) {
+ peer->redirect_learned.a4 = new_gw;
+ atomic_inc(&__rt_peer_genid);
+ }
+ check_peer_redir(&rt->dst, peer);
+ }
+ }
+ }
}
return;
@@ -1589,31 +1749,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
}
}
-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)
{
struct rtable *rt = (struct rtable *) dst;
@@ -3088,6 +3223,13 @@ static ctl_table ipv4_route_table[] = {
.proc_handler = proc_dointvec_jiffies,
},
{
+ .procname = "gc_interval",
+ .data = &ip_rt_gc_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
.procname = "redirect_load",
.data = &ip_rt_redirect_load,
.maxlen = sizeof(int),
@@ -3297,6 +3439,11 @@ int __init ip_rt_init(void)
devinet_init();
ip_fib_init();
+ 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 (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
generated by cgit v1.1 at 2025-02-05 04:30:52 +0000