| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20110209.223939.246547003.davem@davemloft.net>
Date: Wed, 09 Feb 2011 22:39:39 -0800 (PST)
From: David Miller <davem@...emloft.net>
To: netdev@...r.kernel.org
Subject: [RFC !!BONUS!! PATCH 6/5] ipv4: Delete routing cache.
Signed-off-by: David S. Miller <davem@...emloft.net>
---
I couldn't resist, I've been waiting years to be able to even
think about trying this.
If you want to live on the edge, and I really mean "the edge",
you want to try this patch out for sure. :-)
It builds, and that's all that I promise.
include/net/route.h | 1 -
net/ipv4/fib_frontend.c | 5 -
net/ipv4/route.c | 891 ++---------------------------------------------
3 files changed, 23 insertions(+), 874 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index bf790c1..fcf1b11 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -117,7 +117,6 @@ extern int ip_rt_init(void);
extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
__be32 src, struct net_device *dev);
extern void rt_cache_flush(struct net *net, int how);
-extern void rt_cache_flush_batch(struct net *net);
extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp);
extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp);
extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2a49c06..694145c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -978,11 +978,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
rt_cache_flush(dev_net(dev), 0);
break;
case NETDEV_UNREGISTER_BATCH:
- /* The batch unregister is only called on the first
- * device in the list of devices being unregistered.
- * Therefore we should not pass dev_net(dev) in here.
- */
- rt_cache_flush_batch(NULL);
break;
}
return NOTIFY_DONE;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 756f544..7078b8b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8;
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 rt_chain_length_max __read_mostly = 20;
/*
* Interface to generic destination cache.
@@ -222,184 +221,30 @@ const __u8 ip_tos2prio[16] = {
};
-/*
- * Route cache.
- */
-
-/* The locking scheme is rather straight forward:
- *
- * 1) Read-Copy Update protects the buckets of the central route hash.
- * 2) Only writers remove entries, and they hold the lock
- * as they look at rtable reference counts.
- * 3) Only readers acquire references to rtable entries,
- * they do so with atomic increments and with the
- * lock held.
- */
-
-struct rt_hash_bucket {
- struct rtable __rcu *chain;
-};
-
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
- defined(CONFIG_PROVE_LOCKING)
-/*
- * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
- * The size of this table is a power of two and depends on the number of CPUS.
- * (on lockdep we have a quite big spinlock_t, so keep the size down there)
- */
-#ifdef CONFIG_LOCKDEP
-# define RT_HASH_LOCK_SZ 256
-#else
-# if NR_CPUS >= 32
-# define RT_HASH_LOCK_SZ 4096
-# elif NR_CPUS >= 16
-# define RT_HASH_LOCK_SZ 2048
-# elif NR_CPUS >= 8
-# define RT_HASH_LOCK_SZ 1024
-# elif NR_CPUS >= 4
-# define RT_HASH_LOCK_SZ 512
-# else
-# define RT_HASH_LOCK_SZ 256
-# endif
-#endif
-
-static spinlock_t *rt_hash_locks;
-# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
-
-static __init void rt_hash_lock_init(void)
-{
- int i;
-
- rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ,
- GFP_KERNEL);
- if (!rt_hash_locks)
- panic("IP: failed to allocate rt_hash_locks\n");
-
- for (i = 0; i < RT_HASH_LOCK_SZ; i++)
- spin_lock_init(&rt_hash_locks[i]);
-}
-#else
-# define rt_hash_lock_addr(slot) NULL
-
-static inline void rt_hash_lock_init(void)
-{
-}
-#endif
-
-static struct rt_hash_bucket *rt_hash_table __read_mostly;
-static unsigned rt_hash_mask __read_mostly;
-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) __this_cpu_inc(rt_cache_stat.field)
-static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
-{
- return jhash_3words((__force u32)daddr, (__force u32)saddr,
- idx, genid)
- & rt_hash_mask;
-}
-
static inline int rt_genid(struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
#ifdef CONFIG_PROC_FS
-struct rt_cache_iter_state {
- struct seq_net_private p;
- int bucket;
- int genid;
-};
-
-static struct rtable *rt_cache_get_first(struct seq_file *seq)
-{
- struct rt_cache_iter_state *st = seq->private;
- struct rtable *r = NULL;
-
- for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
- if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain))
- continue;
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- while (r) {
- if (dev_net(r->dst.dev) == seq_file_net(seq) &&
- r->rt_genid == st->genid)
- return r;
- r = rcu_dereference_bh(r->dst.rt_next);
- }
- rcu_read_unlock_bh();
- }
- return r;
-}
-
-static struct rtable *__rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
-
- r = rcu_dereference_bh(r->dst.rt_next);
- while (!r) {
- rcu_read_unlock_bh();
- do {
- if (--st->bucket < 0)
- return NULL;
- } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain));
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
- while ((r = __rt_cache_get_next(seq, r)) != NULL) {
- if (dev_net(r->dst.dev) != seq_file_net(seq))
- continue;
- if (r->rt_genid == st->genid)
- break;
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
-{
- struct rtable *r = rt_cache_get_first(seq);
-
- if (r)
- while (pos && (r = rt_cache_get_next(seq, r)))
- --pos;
- return pos ? NULL : r;
-}
-
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct rt_cache_iter_state *st = seq->private;
if (*pos)
- return rt_cache_get_idx(seq, *pos - 1);
- st->genid = rt_genid(seq_file_net(seq));
+ return NULL;
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct rtable *r;
-
- if (v == SEQ_START_TOKEN)
- r = rt_cache_get_first(seq);
- else
- r = rt_cache_get_next(seq, v);
++*pos;
- return r;
+ return NULL;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
- if (v && v != SEQ_START_TOKEN)
- rcu_read_unlock_bh();
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
@@ -409,29 +254,6 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
- else {
- struct rtable *r = v;
- int len;
-
- 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->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, "%*s\n", 127 - len, "");
- }
return 0;
}
@@ -444,8 +266,7 @@ static const struct seq_operations rt_cache_seq_ops = {
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &rt_cache_seq_ops,
- sizeof(struct rt_cache_iter_state));
+ return seq_open_net(inode, file, &rt_cache_seq_ops, 0);
}
static const struct file_operations rt_cache_seq_fops = {
@@ -643,184 +464,12 @@ static inline int ip_rt_proc_init(void)
}
#endif /* CONFIG_PROC_FS */
-static inline void rt_free(struct rtable *rt)
-{
- 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->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)) &&
- 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->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->dst.__refcnt))
- goto out;
-
- age = jiffies - rth->dst.lastuse;
- if ((age <= tmo1 && !rt_fast_clean(rth)) ||
- (age <= tmo2 && rt_valuable(rth)))
- goto out;
- ret = 1;
-out: return ret;
-}
-
-/* Bits of score are:
- * 31: very valuable
- * 30: not quite useless
- * 29..0: usage counter
- */
-static inline u32 rt_score(struct rtable *rt)
-{
- u32 score = jiffies - rt->dst.lastuse;
-
- score = ~score & ~(3<<30);
-
- if (rt_valuable(rt))
- score |= (1<<31);
-
- if (rt_is_output_route(rt) ||
- !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
- score |= (1<<30);
-
- return score;
-}
-
-static inline bool rt_caching(const struct net *net)
-{
- return net->ipv4.current_rt_cache_rebuild_count <=
- net->ipv4.sysctl_rt_cache_rebuild_count;
-}
-
-static inline bool compare_hash_inputs(const struct flowi *fl1,
- const struct flowi *fl2)
-{
- 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->fl4_dst ^ (__force u32)fl2->fl4_dst) |
- ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) |
- (fl1->mark ^ fl2->mark) |
- (*(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 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->dst.dev));
}
/*
- * Perform a full scan of hash table and free all entries.
- * Can be called by a softirq or a process.
- * In the later case, we want to be reschedule if necessary
- */
-static void rt_do_flush(struct net *net, int process_context)
-{
- unsigned int i;
- struct rtable *rth, *next;
-
- for (i = 0; i <= rt_hash_mask; i++) {
- struct rtable __rcu **pprev;
- struct rtable *list;
-
- if (process_context && need_resched())
- cond_resched();
- rth = rcu_dereference_raw(rt_hash_table[i].chain);
- if (!rth)
- continue;
-
- spin_lock_bh(rt_hash_lock_addr(i));
-
- list = NULL;
- pprev = &rt_hash_table[i].chain;
- rth = rcu_dereference_protected(*pprev,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- 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 {
- pprev = &rth->dst.rt_next;
- }
- rth = next;
- }
-
- spin_unlock_bh(rt_hash_lock_addr(i));
-
- for (; list; list = next) {
- next = rcu_dereference_protected(list->dst.rt_next, 1);
- rt_free(list);
- }
- }
-}
-
-/*
- * While freeing expired entries, we compute average chain length
- * and standard deviation, using fixed-point arithmetic.
- * This to have an estimation of rt_chain_length_max
- * rt_chain_length_max = max(elasticity, AVG + 4*SD)
- * We use 3 bits for frational part, and 29 (or 61) for magnitude.
- */
-
-#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 = rcu_dereference_protected(aux->dst.rt_next, 1);
- }
- return ONE;
-}
-
-/*
* Pertubation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
* many times (2^24) without giving recent rt_genid.
@@ -841,366 +490,32 @@ static void rt_cache_invalidate(struct net *net)
void rt_cache_flush(struct net *net, int delay)
{
rt_cache_invalidate(net);
- if (delay >= 0)
- rt_do_flush(net, !in_softirq());
-}
-
-/* Flush previous cache invalidated entries from the cache */
-void rt_cache_flush_batch(struct net *net)
-{
- rt_do_flush(net, !in_softirq());
}
-static void rt_emergency_hash_rebuild(struct net *net)
-{
- if (net_ratelimit())
- printk(KERN_WARNING "Route hash chain too long!\n");
- rt_cache_invalidate(net);
-}
-
-/*
- Short description of GC goals.
-
- We want to build algorithm, which will keep routing cache
- at some equilibrium point, when number of aged off entries
- is kept approximately equal to newly generated ones.
-
- Current expiration strength is variable "expire".
- We try to adjust it dynamically, so that if networking
- is idle expires is large enough to keep enough of warm entries,
- and when load increases it reduces to limit cache size.
- */
-
static int rt_garbage_collect(struct dst_ops *ops)
{
- static unsigned long expire = RT_GC_TIMEOUT;
- static unsigned long last_gc;
- static int rover;
- static int equilibrium;
- 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,
- * do not make it too frequently.
- */
-
RT_CACHE_STAT_INC(gc_total);
-
- if (now - last_gc < ip_rt_gc_min_interval &&
- 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 = 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 = entries - equilibrium;
- if (goal > 0) {
- equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- 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 = entries - goal;
- }
-
- if (now - last_gc >= ip_rt_gc_min_interval)
- last_gc = now;
-
- if (goal <= 0) {
- equilibrium += goal;
- goto work_done;
- }
-
- do {
- int i, k;
-
- for (i = rt_hash_mask, k = rover; i >= 0; i--) {
- unsigned long tmo = expire;
-
- k = (k + 1) & rt_hash_mask;
- rthp = &rt_hash_table[k].chain;
- spin_lock_bh(rt_hash_lock_addr(k));
- 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->dst.rt_next;
- continue;
- }
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- goal--;
- }
- spin_unlock_bh(rt_hash_lock_addr(k));
- if (goal <= 0)
- break;
- }
- rover = k;
-
- if (goal <= 0)
- goto work_done;
-
- /* Goal is not achieved. We stop process if:
-
- - if expire reduced to zero. Otherwise, expire is halfed.
- - if table is not full.
- - if we are called from interrupt.
- - jiffies check is just fallback/debug loop breaker.
- We will not spin here for long time in any case.
- */
-
- RT_CACHE_STAT_INC(gc_goal_miss);
-
- if (expire == 0)
- break;
-
- expire >>= 1;
-#if RT_CACHE_DEBUG >= 2
- printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
- dst_entries_get_fast(&ipv4_dst_ops), goal, i);
-#endif
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- } while (!in_softirq() && time_before_eq(jiffies, now));
-
- 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");
- RT_CACHE_STAT_INC(gc_dst_overflow);
- return 1;
-
-work_done:
- expire += ip_rt_gc_min_interval;
- if (expire > ip_rt_gc_timeout ||
- 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,
- dst_entries_get_fast(&ipv4_dst_ops), goal, rover);
-#endif
-out: return 0;
-}
-
-/*
- * 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;
+ return 0;
}
-static int rt_intern_hash(unsigned hash, struct rtable *rt,
- struct rtable **rp, struct sk_buff *skb, int ifindex)
+static int rt_finalize(struct rtable *rt, struct rtable **rp, struct sk_buff *skb)
{
- struct rtable *rth, *cand;
- struct rtable __rcu **rthp, **candp;
- unsigned long now;
- u32 min_score;
- int chain_length;
- int attempts = !in_softirq();
-
-restart:
- chain_length = 0;
- min_score = ~(u32)0;
- cand = NULL;
- candp = NULL;
- now = jiffies;
-
- 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
- * 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: 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.
- */
-
- 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");
- ip_rt_put(rt);
- return err;
- }
- }
-
- goto skip_hashing;
- }
-
- rthp = &rt_hash_table[hash].chain;
-
- spin_lock_bh(rt_hash_lock_addr(hash));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (rt_is_expired(rth)) {
- *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->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->dst.rt_next,
- rt_hash_table[hash].chain);
- /*
- * Since lookup is lockfree, the update writes
- * must be ordered for consistency on SMP.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rth);
-
- 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->dst);
- return 0;
- }
-
- if (!atomic_read(&rth->dst.__refcnt)) {
- u32 score = rt_score(rth);
-
- if (score <= min_score) {
- cand = rth;
- candp = rthp;
- min_score = score;
- }
- }
-
- chain_length++;
-
- rthp = &rth->dst.rt_next;
- }
-
- if (cand) {
- /* ip_rt_gc_elasticity used to be average length of chain
- * length, when exceeded gc becomes really aggressive.
- *
- * The second limit is less certain. At the moment it allows
- * only 2 entries per bucket. We will see.
- */
- if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->dst.rt_next;
- rt_free(cand);
- }
- } else {
- 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(net)) {
- printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
- rt->dst.dev->name, num);
- }
- 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.
+ /* 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.
*/
+ 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) {
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- if (err != -ENOBUFS) {
- rt_drop(rt);
- return err;
- }
-
- /* Neighbour tables are full and nothing
- can be released. Try to shrink route cache,
- it is most likely it holds some neighbour records.
- */
- if (attempts-- > 0) {
- int saved_elasticity = ip_rt_gc_elasticity;
- int saved_int = ip_rt_gc_min_interval;
- ip_rt_gc_elasticity = 1;
- ip_rt_gc_min_interval = 0;
- rt_garbage_collect(&ipv4_dst_ops);
- ip_rt_gc_min_interval = saved_int;
- ip_rt_gc_elasticity = saved_elasticity;
- goto restart;
- }
-
if (net_ratelimit())
- printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
- rt_drop(rt);
- return -ENOBUFS;
+ printk(KERN_WARNING
+ "Neighbour table failure & not caching routes.\n");
+ ip_rt_put(rt);
+ return err;
}
}
- rt->dst.rt_next = rt_hash_table[hash].chain;
-
-#if RT_CACHE_DEBUG >= 2
- if (rt->dst.rt_next) {
- struct rtable *trt;
- printk(KERN_DEBUG "rt_cache @%02x: %pI4",
- hash, &rt->rt_dst);
- for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next)
- printk(" . %pI4", &trt->rt_dst);
- printk("\n");
- }
-#endif
- /*
- * Since lookup is lockfree, we must make sure
- * previous writes to rt are comitted to memory
- * before making rt visible to other CPUS.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rt);
-
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
-skip_hashing:
if (rp)
*rp = rt;
else
@@ -1270,26 +585,6 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void rt_del(unsigned hash, struct rtable *rt)
-{
- 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 = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (aux == rt || rt_is_expired(aux)) {
- *rthp = aux->dst.rt_next;
- rt_free(aux);
- continue;
- }
- 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)
@@ -1348,14 +643,11 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
ip_rt_put(rt);
ret = NULL;
} 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)));
#if RT_CACHE_DEBUG >= 1
printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n",
- &rt->rt_dst, rt->fl.fl4_tos);
+ &rt->rt_dst, rt->fl.fl4_tos);
#endif
- rt_del(hash, rt);
+ ip_rt_put(rt);
ret = NULL;
} else if (rt->peer &&
rt->peer->pmtu_expires &&
@@ -1820,7 +1112,6 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
- unsigned int hash;
struct rtable *rth;
__be32 spec_dst;
struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -1887,8 +1178,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
RT_CACHE_STAT_INC(in_slow_mc);
- hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- return rt_intern_hash(hash, rth, NULL, skb, dev->ifindex);
+ return rt_finalize(rth, NULL, skb);
e_nobufs:
return -ENOBUFS;
@@ -2035,7 +1325,6 @@ static int ip_mkroute_input(struct sk_buff *skb,
{
struct rtable* rth = NULL;
int err;
- unsigned hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1 && fl->oif == 0)
@@ -2048,9 +1337,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
return err;
/* put it into the cache */
- hash = rt_hash(daddr, saddr, fl->iif,
- rt_genid(dev_net(rth->dst.dev)));
- return rt_intern_hash(hash, rth, NULL, skb, fl->iif);
+ return rt_finalize(rth, NULL, skb);
}
/*
@@ -2078,7 +1365,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
- unsigned hash;
__be32 spec_dst;
int err = -EINVAL;
struct net * net = dev_net(dev);
@@ -2197,8 +1483,7 @@ local_input:
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, fl.iif);
+ err = rt_finalize(rth, NULL, skb);
goto out;
no_route:
@@ -2242,47 +1527,10 @@ martian_source_keep_err:
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));
-
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- 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->dst.dev), net) &&
- !rt_is_expired(rth)) {
- 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();
- return 0;
- }
- RT_CACHE_STAT_INC(in_hlist_search);
- }
-
-skip_cache:
/* Multicast recognition logic is moved from route cache to here.
The problem was that too many Ethernet cards have broken/missing
hardware multicast filters :-( As result the host on multicasting
@@ -2439,12 +1687,9 @@ static int ip_mkroute_output(struct rtable **rp,
{
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, oldflp->oif);
- }
+
+ if (!err == 0)
+ err = rt_finalize(rth, rp, NULL);
return err;
}
@@ -2635,38 +1880,8 @@ out: return err;
int __ip_route_output_key(struct net *net, struct rtable **rp,
const struct flowi *flp)
{
- unsigned int hash;
int res;
- struct rtable *rth;
- 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_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 &&
- 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->dst.dev), net) &&
- !rt_is_expired(rth)) {
- dst_use(&rth->dst, jiffies);
- RT_CACHE_STAT_INC(out_hit);
- rcu_read_unlock_bh();
- *rp = rth;
- return 0;
- }
- RT_CACHE_STAT_INC(out_hlist_search);
- }
- rcu_read_unlock_bh();
-
-slow_output:
rcu_read_lock();
res = ip_route_output_slow(net, rp, flp);
rcu_read_unlock();
@@ -2966,43 +2181,6 @@ errout_free:
int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct rtable *rt;
- int h, s_h;
- int idx, s_idx;
- struct net *net;
-
- net = sock_net(skb->sk);
-
- s_h = cb->args[0];
- if (s_h < 0)
- s_h = 0;
- s_idx = idx = cb->args[1];
- for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) {
- if (!rt_hash_table[h].chain)
- continue;
- rcu_read_lock_bh();
- 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_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) {
- skb_dst_drop(skb);
- rcu_read_unlock_bh();
- goto done;
- }
- skb_dst_drop(skb);
- }
- rcu_read_unlock_bh();
- }
-
-done:
- cb->args[0] = h;
- cb->args[1] = idx;
return skb->len;
}
@@ -3235,16 +2413,6 @@ static __net_initdata struct pernet_operations rt_genid_ops = {
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)
-{
- if (!str)
- return 0;
- rhash_entries = simple_strtoul(str, &str, 0);
- return 1;
-}
-__setup("rhash_entries=", set_rhash_entries);
-
int __init ip_rt_init(void)
{
int rc = 0;
@@ -3267,21 +2435,8 @@ int __init ip_rt_init(void)
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),
- rhash_entries,
- (totalram_pages >= 128 * 1024) ?
- 15 : 17,
- 0,
- &rt_hash_log,
- &rt_hash_mask,
- rhash_entries ? 0 : 512 * 1024);
- memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
- rt_hash_lock_init();
-
- ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
- ip_rt_max_size = (rt_hash_mask + 1) * 16;
+ ipv4_dst_ops.gc_thresh = ~0;
+ ip_rt_max_size = INT_MAX;
devinet_init();
ip_fib_init();
--
1.7.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists