diff options
Diffstat (limited to 'net/ipv4/route.c')
| -rw-r--r-- | net/ipv4/route.c | 2229 |
1 files changed, 683 insertions, 1546 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98b30d08efe..c035251beb0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -133,10 +133,6 @@ 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; - -static struct delayed_work expires_work; -static unsigned long expires_ljiffies; /* * Interface to generic destination cache. @@ -145,11 +141,13 @@ static unsigned long expires_ljiffies; 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_mtu(const struct dst_entry *dst); -static void ipv4_dst_destroy(struct dst_entry *dst); 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 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +static void ipv4_dst_destroy(struct dst_entry *dst); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) @@ -158,45 +156,17 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, 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, rt->rt_dst, 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; + WARN_ON(1); + return NULL; } -static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr); +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); 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, .mtu = ipv4_mtu, @@ -206,6 +176,7 @@ static struct dst_ops ipv4_dst_ops = { .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, + .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, }; @@ -232,184 +203,30 @@ const __u8 ip_tos2prio[16] = { }; EXPORT_SYMBOL(ip_tos2prio); -/* - * 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 int 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_access_pointer(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_access_pointer(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) @@ -419,34 +236,6 @@ 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; - struct neighbour *n; - int len, HHUptod; - - rcu_read_lock(); - n = dst_get_neighbour_noref(&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", - 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->rt_key_tos, - -1, - HHUptod, - r->rt_spec_dst, &len); - - seq_printf(seq, "%*s\n", 127 - len, ""); - } return 0; } @@ -459,8 +248,7 @@ 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(file, &rt_cache_seq_ops); } static const struct file_operations rt_cache_seq_fops = { @@ -468,7 +256,7 @@ static const struct file_operations rt_cache_seq_fops = { .open = rt_cache_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_net, + .release = seq_release, }; @@ -658,275 +446,12 @@ 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 rtable *rt1, - const struct rtable *rt2) -{ - return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | - ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0); -} - -static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) -{ - return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | - ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_mark ^ rt2->rt_mark) | - (rt1->rt_key_tos ^ rt2->rt_key_tos) | - (rt1->rt_route_iif ^ rt2->rt_route_iif) | - (rt1->rt_oif ^ rt2->rt_oif)) == 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) +static inline bool rt_is_expired(const 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_access_pointer(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, rth)) - return 0; - aux = rcu_dereference_protected(aux->dst.rt_next, 1); - } - 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() * many times (2^24) without giving recent rt_genid. @@ -938,7 +463,6 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); - inetpeer_invalidate_tree(AF_INET); } /* @@ -948,183 +472,22 @@ 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) -{ - net_warn_ratelimited("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 struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { - 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 (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; - net_warn_ratelimited("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; -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; -} - -static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) -{ - static const __be32 inaddr_any = 0; struct net_device *dev = dst->dev; const __be32 *pkey = daddr; const struct rtable *rt; struct neighbour *n; rt = (const struct rtable *) dst; - - if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) - pkey = &inaddr_any; - else if (rt->rt_gateway) + if (rt->rt_gateway) pkey = (const __be32 *) &rt->rt_gateway; + else if (skb) + pkey = &ip_hdr(skb)->daddr; n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey); if (n) @@ -1132,311 +495,221 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const vo return neigh_create(&arp_tbl, pkey, dev); } -static int rt_bind_neighbour(struct rtable *rt) +/* + * Peer allocation may fail only in serious out-of-memory conditions. However + * we still can generate some output. + * Random ID selection looks a bit dangerous because we have no chances to + * select ID being unique in a reasonable period of time. + * But broken packet identifier may be better than no packet at all. + */ +static void ip_select_fb_ident(struct iphdr *iph) { - struct neighbour *n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - dst_set_neighbour(&rt->dst, n); + static DEFINE_SPINLOCK(ip_fb_id_lock); + static u32 ip_fallback_id; + u32 salt; - return 0; + spin_lock_bh(&ip_fb_id_lock); + salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); + iph->id = htons(salt & 0xFFFF); + ip_fallback_id = salt; + spin_unlock_bh(&ip_fb_id_lock); } -static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt, - struct sk_buff *skb, int ifindex) +void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) { - 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 = rt_bind_neighbour(rt); - if (err) { - net_warn_ratelimited("Neighbour table failure & not caching routes\n"); - ip_rt_put(rt); - return ERR_PTR(err); - } - } + struct net *net = dev_net(dst->dev); + struct inet_peer *peer; - goto skip_hashing; + peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); + if (peer) { + iph->id = htons(inet_getid(peer, more)); + inet_putpeer(peer); + return; } - 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, rt) && 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 (skb) - skb_dst_set(skb, &rth->dst); - return rth; - } - - 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; - } + ip_select_fb_ident(iph); +} +EXPORT_SYMBOL(__ip_select_ident); - 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)) { - pr_warn("%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)); +static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk, + const struct iphdr *iph, + int oif, u8 tos, + u8 prot, u32 mark, int flow_flags) +{ + if (sk) { + const struct inet_sock *inet = inet_sk(sk); - hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, - ifindex, rt_genid(net)); - goto restart; - } + oif = sk->sk_bound_dev_if; + mark = sk->sk_mark; + tos = RT_CONN_FLAGS(sk); + prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; } + flowi4_init_output(fl4, oif, mark, tos, + RT_SCOPE_UNIVERSE, prot, + flow_flags, + iph->daddr, iph->saddr, 0, 0); +} - /* Try to bind route to arp only if it is output - route or unicast forwarding path. - */ - if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = rt_bind_neighbour(rt); - if (err) { - spin_unlock_bh(rt_hash_lock_addr(hash)); - - if (err != -ENOBUFS) { - rt_drop(rt); - return ERR_PTR(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; - } - - net_warn_ratelimited("Neighbour table overflow\n"); - rt_drop(rt); - return ERR_PTR(-ENOBUFS); - } - } +static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, + const struct sock *sk) +{ + const struct iphdr *iph = ip_hdr(skb); + int oif = skb->dev->ifindex; + u8 tos = RT_TOS(iph->tos); + u8 prot = iph->protocol; + u32 mark = skb->mark; - rt->dst.rt_next = rt_hash_table[hash].chain; + __build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0); +} - /* - * Since lookup is lockfree, we must make sure - * previous writes to rt are committed to memory - * before making rt visible to other CPUS. - */ - rcu_assign_pointer(rt_hash_table[hash].chain, rt); +static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; - spin_unlock_bh(rt_hash_lock_addr(hash)); + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, + inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + inet_sk_flowi_flags(sk), + daddr, inet->inet_saddr, 0, 0); + rcu_read_unlock(); +} -skip_hashing: +static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, + const struct sk_buff *skb) +{ if (skb) - skb_dst_set(skb, &rt->dst); - return rt; + build_skb_flow_key(fl4, skb, sk); + else + build_sk_flow_key(fl4, sk); } -static atomic_t __rt_peer_genid = ATOMIC_INIT(0); - -static u32 rt_peer_genid(void) +static inline void rt_free(struct rtable *rt) { - return atomic_read(&__rt_peer_genid); + call_rcu(&rt->dst.rcu_head, dst_rcu_free); } -void rt_bind_peer(struct rtable *rt, __be32 daddr, int create) -{ - struct inet_peer *peer; +static DEFINE_SPINLOCK(fnhe_lock); - peer = inet_getpeer_v4(daddr, create); +static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) +{ + struct fib_nh_exception *fnhe, *oldest; + struct rtable *orig; - if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) - inet_putpeer(peer); - else - rt->rt_peer_genid = rt_peer_genid(); + oldest = rcu_dereference(hash->chain); + for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) + oldest = fnhe; + } + orig = rcu_dereference(oldest->fnhe_rth); + if (orig) { + RCU_INIT_POINTER(oldest->fnhe_rth, NULL); + rt_free(orig); + } + return oldest; } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. - */ -static void ip_select_fb_ident(struct iphdr *iph) +static inline u32 fnhe_hashfun(__be32 daddr) { - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; + u32 hval; - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); + hval = (__force u32) daddr; + hval ^= (hval >> 11) ^ (hval >> 22); + + return hval & (FNHE_HASH_SIZE - 1); } -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, + u32 pmtu, unsigned long expires) { - struct rtable *rt = (struct rtable *) dst; + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe; + int depth; + u32 hval = fnhe_hashfun(daddr); - if (rt && !(rt->dst.flags & DST_NOPEER)) { - if (rt->peer == NULL) - rt_bind_peer(rt, rt->rt_dst, 1); + spin_lock_bh(&fnhe_lock); - /* If peer is attached to destination, it is never detached, - so that we need not to grab a lock to dereference it. - */ - if (rt->peer) { - iph->id = htons(inet_getid(rt->peer, more)); - return; - } - } else if (!rt) - pr_debug("rt_bind_peer(0) @%p\n", __builtin_return_address(0)); + hash = nh->nh_exceptions; + if (!hash) { + hash = kzalloc(FNHE_HASH_SIZE * sizeof(*hash), GFP_ATOMIC); + if (!hash) + goto out_unlock; + nh->nh_exceptions = hash; + } - ip_select_fb_ident(iph); -} -EXPORT_SYMBOL(__ip_select_ident); + hash += hval; -static void rt_del(unsigned int hash, struct rtable *rt) -{ - struct rtable __rcu **rthp; - struct rtable *aux; + depth = 0; + for (fnhe = rcu_dereference(hash->chain); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + if (fnhe->fnhe_daddr == daddr) + break; + depth++; + } - 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; + if (fnhe) { + if (gw) + fnhe->fnhe_gw = gw; + if (pmtu) { + fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_expires = expires; + } + } else { + if (depth > FNHE_RECLAIM_DEPTH) + fnhe = fnhe_oldest(hash); + else { + fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); + if (!fnhe) + goto out_unlock; + + fnhe->fnhe_next = hash->chain; + rcu_assign_pointer(hash->chain, fnhe); } - rthp = &aux->dst.rt_next; + fnhe->fnhe_daddr = daddr; + fnhe->fnhe_gw = gw; + fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_expires = expires; } - spin_unlock_bh(rt_hash_lock_addr(hash)); + + fnhe->fnhe_stamp = jiffies; + +out_unlock: + spin_unlock_bh(&fnhe_lock); + return; } -static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, + bool kill_route) { - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); + __be32 new_gw = icmp_hdr(skb)->un.gateway; + __be32 old_gw = ip_hdr(skb)->saddr; + struct net_device *dev = skb->dev; + struct in_device *in_dev; + struct fib_result res; + struct neighbour *n; + struct net *net; - rt->rt_gateway = peer->redirect_learned.a4; + switch (icmp_hdr(skb)->code & 7) { + case ICMP_REDIR_NET: + case ICMP_REDIR_NETTOS: + case ICMP_REDIR_HOST: + case ICMP_REDIR_HOSTTOS: + break; - n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) { - rt->rt_gateway = orig_gw; + default: return; } - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!(n->nud_state & NUD_VALID)) { - neigh_event_send(n, NULL); - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } -} -/* 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; + if (rt->rt_gateway != old_gw) + return; + in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; @@ -1456,72 +729,50 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - for (s = 0; s < 2; s++) { - for (i = 0; i < 2; i++) { - unsigned int hash; - struct rtable __rcu **rthp; - struct rtable *rt; - - hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); - - 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); - } + n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); + if (n) { + if (!(n->nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + } else { + if (fib_lookup(net, fl4, &res) == 0) { + struct fib_nh *nh = &FIB_RES_NH(res); + + update_or_create_fnhe(nh, fl4->daddr, new_gw, + 0, 0); } + if (kill_route) + rt->dst.obsolete = DST_OBSOLETE_KILL; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } + neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE - if (IN_DEV_LOG_MARTIANS(in_dev)) + if (IN_DEV_LOG_MARTIANS(in_dev)) { + const struct iphdr *iph = (const struct iphdr *) skb->data; + __be32 daddr = iph->daddr; + __be32 saddr = iph->saddr; + net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); + } #endif ; } -static bool peer_pmtu_expired(struct inet_peer *peer) +static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { - unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); + struct rtable *rt; + struct flowi4 fl4; - return orig && - time_after_eq(jiffies, orig) && - cmpxchg(&peer->pmtu_expires, orig, 0) == orig; -} + rt = (struct rtable *) dst; -static bool peer_pmtu_cleaned(struct inet_peer *peer) -{ - unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); - - return orig && - cmpxchg(&peer->pmtu_expires, orig, 0) == orig; + ip_rt_build_flow_key(&fl4, sk, skb); + __ip_do_redirect(rt, skb, &fl4, true); } static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) @@ -1533,14 +784,10 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; - } else if (rt->rt_flags & RTCF_REDIRECTED) { - unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src, - rt->rt_oif, - rt_genid(dev_net(dst->dev))); - rt_del(hash, rt); + } else if ((rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) { + ip_rt_put(rt); ret = NULL; - } else if (rt->peer && peer_pmtu_expired(rt->peer)) { - dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig); } } return ret; @@ -1567,6 +814,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; + struct net *net; int log_martians; rcu_read_lock(); @@ -1578,9 +826,8 @@ void ip_rt_send_redirect(struct sk_buff *skb) log_martians = IN_DEV_LOG_MARTIANS(in_dev); rcu_read_unlock(); - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); return; @@ -1597,7 +844,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) */ if (peer->rate_tokens >= ip_rt_redirect_number) { peer->rate_last = jiffies; - return; + goto out_put_peer; } /* Check for load limit; set rate_last to the latest sent @@ -1614,20 +861,38 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (log_martians && peer->rate_tokens == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", - &ip_hdr(skb)->saddr, rt->rt_iif, - &rt->rt_dst, &rt->rt_gateway); + &ip_hdr(skb)->saddr, inet_iif(skb), + &ip_hdr(skb)->daddr, &rt->rt_gateway); #endif } +out_put_peer: + inet_putpeer(peer); } static int ip_error(struct sk_buff *skb) { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); struct rtable *rt = skb_rtable(skb); struct inet_peer *peer; unsigned long now; + struct net *net; bool send; int code; + net = dev_net(rt->dst.dev); + if (!IN_DEV_FORWARD(in_dev)) { + switch (rt->dst.error) { + case EHOSTUNREACH: + IP_INC_STATS_BH(net, IPSTATS_MIB_INADDRERRORS); + break; + + case ENETUNREACH: + IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES); + break; + } + goto out; + } + switch (rt->dst.error) { case EINVAL: default: @@ -1637,17 +902,14 @@ static int ip_error(struct sk_buff *skb) break; case ENETUNREACH: code = ICMP_NET_UNREACH; - IP_INC_STATS_BH(dev_net(rt->dst.dev), - IPSTATS_MIB_INNOROUTES); + IP_INC_STATS_BH(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); send = true; if (peer) { @@ -1660,6 +922,7 @@ static int ip_error(struct sk_buff *skb) peer->rate_tokens -= ip_rt_error_cost; else send = false; + inet_putpeer(peer); } if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); @@ -1668,163 +931,120 @@ out: kfree_skb(skb); return 0; } -/* - * The last two values are not from the RFC but - * are needed for AMPRnet AX.25 paths. - */ +static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) +{ + struct fib_result res; -static const unsigned short mtu_plateau[] = -{32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 }; + if (mtu < ip_rt_min_pmtu) + mtu = ip_rt_min_pmtu; -static inline unsigned short guess_mtu(unsigned short old_mtu) -{ - int i; + if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) { + struct fib_nh *nh = &FIB_RES_NH(res); - for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++) - if (old_mtu > mtu_plateau[i]) - return mtu_plateau[i]; - return 68; + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + jiffies + ip_rt_mtu_expires); + } + return mtu; } -unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, - unsigned short new_mtu, - struct net_device *dev) +static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { - unsigned short old_mtu = ntohs(iph->tot_len); - unsigned short est_mtu = 0; - struct inet_peer *peer; - - peer = inet_getpeer_v4(iph->daddr, 1); - if (peer) { - unsigned short mtu = new_mtu; - - 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); - } - - if (mtu < ip_rt_min_pmtu) - mtu = ip_rt_min_pmtu; - if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { - unsigned long pmtu_expires; - - pmtu_expires = jiffies + ip_rt_mtu_expires; - if (!pmtu_expires) - pmtu_expires = 1UL; + struct rtable *rt = (struct rtable *) dst; + struct flowi4 fl4; - est_mtu = mtu; - peer->pmtu_learned = mtu; - peer->pmtu_expires = pmtu_expires; - atomic_inc(&__rt_peer_genid); - } + ip_rt_build_flow_key(&fl4, sk, skb); + mtu = __ip_rt_update_pmtu(rt, &fl4, mtu); - inet_putpeer(peer); + if (!rt->rt_pmtu) { + dst->obsolete = DST_OBSOLETE_KILL; + } else { + rt->rt_pmtu = mtu; + dst_set_expires(&rt->dst, ip_rt_mtu_expires); } - return est_mtu ? : new_mtu; } -static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) +void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, + int oif, u32 mark, u8 protocol, int flow_flags) { - unsigned long expires = ACCESS_ONCE(peer->pmtu_expires); + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - if (!expires) - return; - if (time_before(jiffies, expires)) { - 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); + __build_flow_key(&fl4, NULL, iph, oif, + RT_TOS(iph->tos), protocol, mark, flow_flags); + rt = __ip_route_output_key(net, &fl4); + if (!IS_ERR(rt)) { + __ip_rt_update_pmtu(rt, &fl4, mtu); + ip_rt_put(rt); + } } +EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - struct rtable *rt = (struct rtable *) dst; - struct inet_peer *peer; - - dst_confirm(dst); - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; - if (peer) { - unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires); - - if (mtu < ip_rt_min_pmtu) - mtu = ip_rt_min_pmtu; - if (!pmtu_expires || mtu < peer->pmtu_learned) { - - pmtu_expires = jiffies + ip_rt_mtu_expires; - if (!pmtu_expires) - pmtu_expires = 1UL; - - peer->pmtu_learned = mtu; - peer->pmtu_expires = pmtu_expires; + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - atomic_inc(&__rt_peer_genid); - rt->rt_peer_genid = rt_peer_genid(); - } - check_peer_pmtu(dst, peer); + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + rt = __ip_route_output_key(sock_net(sk), &fl4); + if (!IS_ERR(rt)) { + __ip_rt_update_pmtu(rt, &fl4, mtu); + ip_rt_put(rt); } } +EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); - -static void ipv4_validate_peer(struct rtable *rt) +void ipv4_redirect(struct sk_buff *skb, struct net *net, + int oif, u32 mark, u8 protocol, int flow_flags) { - if (rt->rt_peer_genid != rt_peer_genid()) { - struct inet_peer *peer; - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 0); + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - peer = rt->peer; - if (peer) { - check_peer_pmtu(&rt->dst, peer); + __build_flow_key(&fl4, NULL, iph, oif, + RT_TOS(iph->tos), protocol, mark, flow_flags); + rt = __ip_route_output_key(net, &fl4); + if (!IS_ERR(rt)) { + __ip_do_redirect(rt, skb, &fl4, false); + ip_rt_put(rt); + } +} +EXPORT_SYMBOL_GPL(ipv4_redirect); - if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) - check_peer_redir(&rt->dst, peer); - } +void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; - rt->rt_peer_genid = rt_peer_genid(); + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + rt = __ip_route_output_key(sock_net(sk), &fl4); + if (!IS_ERR(rt)) { + __ip_do_redirect(rt, skb, &fl4, false); + ip_rt_put(rt); } } +EXPORT_SYMBOL_GPL(ipv4_sk_redirect); static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = (struct rtable *) dst; - if (rt_is_expired(rt)) + /* All IPV4 dsts are created with ->obsolete set to the value + * DST_OBSOLETE_FORCE_CHK which forces validation calls down + * into this function always. + * + * When a PMTU/redirect information update invalidates a + * route, this is indicated by setting obsolete to + * DST_OBSOLETE_KILL. + */ + if (dst->obsolete == DST_OBSOLETE_KILL || rt_is_expired(rt)) return NULL; - ipv4_validate_peer(rt); return dst; } -static void ipv4_dst_destroy(struct dst_entry *dst) -{ - struct rtable *rt = (struct rtable *) dst; - struct inet_peer *peer = rt->peer; - - if (rt->fi) { - fib_info_put(rt->fi); - rt->fi = NULL; - } - if (peer) { - rt->peer = NULL; - inet_putpeer(peer); - } -} - - static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; @@ -1832,8 +1052,8 @@ 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 && rt->peer && peer_pmtu_cleaned(rt->peer)) - dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); + if (rt) + dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct sk_buff *skb) @@ -1880,8 +1100,9 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0) src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res); else - src = inet_select_addr(rt->dst.dev, rt->rt_gateway, - RT_SCOPE_UNIVERSE); + src = inet_select_addr(rt->dst.dev, + rt_nexthop(rt, iph->daddr), + RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); @@ -1913,7 +1134,13 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) static unsigned int ipv4_mtu(const struct dst_entry *dst) { const struct rtable *rt = (const struct rtable *) dst; - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + unsigned int mtu = rt->rt_pmtu; + + if (mtu && time_after_eq(jiffies, rt->dst.expires)) + mtu = 0; + + if (!mtu) + mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu && rt_is_output_route(rt)) return mtu; @@ -1921,8 +1148,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - - if (rt->rt_gateway != rt->rt_dst && mtu > 576) + if (rt->rt_gateway && mtu > 576) mtu = 576; } @@ -1932,76 +1158,184 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu; } -static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, - struct fib_info *fi) +static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { - struct inet_peer *peer; - int create = 0; + struct fnhe_hash_bucket *hash = nh->nh_exceptions; + struct fib_nh_exception *fnhe; + u32 hval; - /* If a peer entry exists for this destination, we must hook - * it up in order to get at cached metrics. - */ - if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS)) - create = 1; + if (!hash) + return NULL; - 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); + hval = fnhe_hashfun(daddr); - check_peer_pmtu(&rt->dst, peer); + for (fnhe = rcu_dereference(hash[hval].chain); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + if (fnhe->fnhe_daddr == daddr) + return fnhe; + } + return NULL; +} + +static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, + __be32 daddr) +{ + bool ret = false; + + spin_lock_bh(&fnhe_lock); - if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - rt->rt_gateway = peer->redirect_learned.a4; + if (daddr == fnhe->fnhe_daddr) { + struct rtable *orig; + + if (fnhe->fnhe_pmtu) { + unsigned long expires = fnhe->fnhe_expires; + unsigned long diff = expires - jiffies; + + if (time_before(jiffies, expires)) { + rt->rt_pmtu = fnhe->fnhe_pmtu; + dst_set_expires(&rt->dst, diff); + } + } + if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_gateway = fnhe->fnhe_gw; } + + orig = rcu_dereference(fnhe->fnhe_rth); + rcu_assign_pointer(fnhe->fnhe_rth, rt); + if (orig) + rt_free(orig); + + fnhe->fnhe_stamp = jiffies; + ret = true; + } else { + /* Routes we intend to cache in nexthop exception have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ + rt->dst.flags |= DST_NOCACHE; + } + spin_unlock_bh(&fnhe_lock); + + return ret; +} + +static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) +{ + struct rtable *orig, *prev, **p; + bool ret = true; + + if (rt_is_input_route(rt)) { + p = (struct rtable **)&nh->nh_rth_input; + } else { + if (!nh->nh_pcpu_rth_output) + goto nocache; + p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output); + } + orig = *p; + + prev = cmpxchg(p, orig, rt); + if (prev == orig) { + if (orig) + rt_free(orig); } else { - if (fi->fib_metrics != (u32 *) dst_default_metrics) { - rt->fi = fi; - atomic_inc(&fi->fib_clntref); + /* Routes we intend to cache in the FIB nexthop have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ +nocache: + rt->dst.flags |= DST_NOCACHE; + ret = false; + } + + return ret; +} + +static DEFINE_SPINLOCK(rt_uncached_lock); +static LIST_HEAD(rt_uncached_list); + +static void rt_add_uncached_list(struct rtable *rt) +{ + spin_lock_bh(&rt_uncached_lock); + list_add_tail(&rt->rt_uncached, &rt_uncached_list); + spin_unlock_bh(&rt_uncached_lock); +} + +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct rtable *rt = (struct rtable *) dst; + + if (dst->flags & DST_NOCACHE) { + spin_lock_bh(&rt_uncached_lock); + list_del(&rt->rt_uncached); + spin_unlock_bh(&rt_uncached_lock); + } +} + +void rt_flush_dev(struct net_device *dev) +{ + if (!list_empty(&rt_uncached_list)) { + struct net *net = dev_net(dev); + struct rtable *rt; + + spin_lock_bh(&rt_uncached_lock); + list_for_each_entry(rt, &rt_uncached_list, rt_uncached) { + if (rt->dst.dev != dev) + continue; + rt->dst.dev = net->loopback_dev; + dev_hold(rt->dst.dev); + dev_put(dev); } - dst_init_metrics(&rt->dst, fi->fib_metrics, true); + spin_unlock_bh(&rt_uncached_lock); } } -static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4, +static bool rt_cache_valid(const struct rtable *rt) +{ + return rt && + rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && + !rt_is_expired(rt); +} + +static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, + struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag) { - struct dst_entry *dst = &rt->dst; + bool cached = false; if (fi) { - if (FIB_RES_GW(*res) && - FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - rt->rt_gateway = FIB_RES_GW(*res); - rt_init_metrics(rt, fl4, fi); + struct fib_nh *nh = &FIB_RES_NH(*res); + + if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) + rt->rt_gateway = nh->nh_gw; + dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID - dst->tclassid = FIB_RES_NH(*res).nh_tclassid; + rt->dst.tclassid = nh->nh_tclassid; #endif + if (unlikely(fnhe)) + cached = rt_bind_exception(rt, fnhe, daddr); + else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_cache_route(nh, rt); } - - 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); + if (unlikely(!cached)) + rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES - set_class_tag(rt, fib_rules_tclass(res)); + set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } static struct rtable *rt_dst_alloc(struct net_device *dev, - bool nopolicy, bool noxfrm) + bool nopolicy, bool noxfrm, bool will_cache) { - return dst_alloc(&ipv4_dst_ops, dev, 1, -1, - DST_HOST | + return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); } @@ -2010,9 +1344,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev, 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); u32 itag = 0; int err; @@ -2023,21 +1355,24 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP)) + skb->protocol != htons(ETH_P_IP)) goto e_inval; + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) + if (ipv4_is_loopback(saddr)) + goto e_inval; + if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) goto e_inval; - spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); } else { - err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst, - &itag); + err = fib_validate_source(skb, saddr, 0, tos, 0, dev, + in_dev, &itag); if (err < 0) goto e_err; } rth = rt_dst_alloc(dev_net(dev)->loopback_dev, - IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) goto e_nobufs; @@ -2046,23 +1381,14 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif rth->dst.output = ip_rt_bug; - rth->rt_key_dst = daddr; - rth->rt_key_src = saddr; rth->rt_genid = rt_genid(dev_net(dev)); rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; - rth->rt_key_tos = tos; - rth->rt_dst = daddr; - rth->rt_src = saddr; - rth->rt_route_iif = dev->ifindex; - rth->rt_iif = dev->ifindex; - rth->rt_oif = 0; - rth->rt_mark = skb->mark; - rth->rt_gateway = daddr; - rth->rt_spec_dst= spec_dst; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input= 1; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -2074,9 +1400,8 @@ 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))); - rth = rt_intern_hash(hash, rth, skb, dev->ifindex); - return IS_ERR(rth) ? PTR_ERR(rth) : 0; + skb_dst_set(skb, &rth->dst); + return 0; e_nobufs: return -ENOBUFS; @@ -2116,14 +1441,13 @@ static void ip_handle_martian_source(struct net_device *dev, static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos, - struct rtable **result) + __be32 daddr, __be32 saddr, u32 tos) { struct rtable *rth; int err; struct in_device *out_dev; unsigned int flags = 0; - __be32 spec_dst; + bool do_cache; u32 itag; /* get a working reference to the output device */ @@ -2135,7 +1459,7 @@ static int __mkroute_input(struct sk_buff *skb, err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), - in_dev->dev, &spec_dst, &itag); + in_dev->dev, in_dev, &itag); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); @@ -2143,9 +1467,6 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - if (err) - flags |= RTCF_DIRECTSRC; - if (out_dev == in_dev && err && (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) @@ -2166,38 +1487,41 @@ static int __mkroute_input(struct sk_buff *skb, } } + do_cache = false; + if (res->fi) { + if (!itag) { + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rt_cache_valid(rth)) { + skb_dst_set_noref(skb, &rth->dst); + goto out; + } + do_cache = true; + } + } + rth = rt_dst_alloc(out_dev->dev, IN_DEV_CONF_GET(in_dev, NOPOLICY), - IN_DEV_CONF_GET(out_dev, NOXFRM)); + IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache); if (!rth) { err = -ENOBUFS; goto cleanup; } - rth->rt_key_dst = daddr; - rth->rt_key_src = saddr; rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); rth->rt_flags = flags; rth->rt_type = res->type; - rth->rt_key_tos = tos; - rth->rt_dst = daddr; - rth->rt_src = saddr; - rth->rt_route_iif = in_dev->dev->ifindex; - rth->rt_iif = in_dev->dev->ifindex; - rth->rt_oif = 0; - rth->rt_mark = skb->mark; - rth->rt_gateway = daddr; - rth->rt_spec_dst= spec_dst; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input = 1; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); rth->dst.input = ip_forward; rth->dst.output = ip_output; - rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag); - - *result = rth; + rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag); + skb_dst_set(skb, &rth->dst); +out: err = 0; cleanup: return err; @@ -2209,27 +1533,13 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable *rth = NULL; - int err; - unsigned int hash; - #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) fib_select_multipath(res); #endif /* create a routing cache entry */ - err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth); - if (err) - return err; - - /* put it into the cache */ - hash = rt_hash(daddr, saddr, fl4->flowi4_iif, - rt_genid(dev_net(rth->dst.dev))); - rth = rt_intern_hash(hash, rth, skb, fl4->flowi4_iif); - if (IS_ERR(rth)) - return PTR_ERR(rth); - return 0; + return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* @@ -2252,10 +1562,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, unsigned int flags = 0; u32 itag = 0; struct rtable *rth; - unsigned int hash; - __be32 spec_dst; int err = -EINVAL; struct net *net = dev_net(dev); + bool do_cache; /* IP on this device is disabled. */ @@ -2266,10 +1575,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ - if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - ipv4_is_loopback(saddr)) + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; + res.fi = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -2279,9 +1588,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(saddr)) goto martian_source; - if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr)) + if (ipv4_is_zeronet(daddr)) goto martian_destination; + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) { + if (ipv4_is_loopback(daddr)) + goto martian_destination; + + if (ipv4_is_loopback(saddr)) + goto martian_source; + } + /* * Now we are ready to route packet. */ @@ -2293,11 +1610,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) { - if (!IN_DEV_FORWARD(in_dev)) - goto e_hostunreach; + if (err != 0) goto no_route; - } RT_CACHE_STAT_INC(in_slow_tot); @@ -2307,17 +1621,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, net->loopback_dev->ifindex, - dev, &spec_dst, &itag); + dev, in_dev, &itag); if (err < 0) goto martian_source_keep_err; - if (err) - flags |= RTCF_DIRECTSRC; - spec_dst = daddr; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) - goto e_hostunreach; + goto no_route; if (res.type != RTN_UNICAST) goto martian_destination; @@ -2328,23 +1639,32 @@ brd_input: if (skb->protocol != htons(ETH_P_IP)) goto e_inval; - if (ipv4_is_zeronet(saddr)) - spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); - else { - err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst, - &itag); + if (!ipv4_is_zeronet(saddr)) { + err = fib_validate_source(skb, saddr, 0, tos, 0, dev, + in_dev, &itag); if (err < 0) goto martian_source_keep_err; - if (err) - flags |= RTCF_DIRECTSRC; } flags |= RTCF_BROADCAST; res.type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: + do_cache = false; + if (res.fi) { + if (!itag) { + rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); + if (rt_cache_valid(rth)) { + skb_dst_set_noref(skb, &rth->dst); + err = 0; + goto out; + } + do_cache = true; + } + } + rth = rt_dst_alloc(net->loopback_dev, - IN_DEV_CONF_GET(in_dev, NOPOLICY), false); + IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; @@ -2354,41 +1674,27 @@ local_input: rth->dst.tclassid = itag; #endif - rth->rt_key_dst = daddr; - rth->rt_key_src = saddr; rth->rt_genid = rt_genid(net); rth->rt_flags = flags|RTCF_LOCAL; rth->rt_type = res.type; - rth->rt_key_tos = tos; - rth->rt_dst = daddr; - rth->rt_src = saddr; -#ifdef CONFIG_IP_ROUTE_CLASSID - rth->dst.tclassid = itag; -#endif - rth->rt_route_iif = dev->ifindex; - rth->rt_iif = dev->ifindex; - rth->rt_oif = 0; - rth->rt_mark = skb->mark; - rth->rt_gateway = daddr; - rth->rt_spec_dst= spec_dst; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input = 1; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } - hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net)); - rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif); + if (do_cache) + rt_cache_route(&FIB_RES_NH(res), rth); + skb_dst_set(skb, &rth->dst); err = 0; - if (IS_ERR(rth)) - err = PTR_ERR(rth); goto out; no_route: RT_CACHE_STAT_INC(in_no_route); - spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); res.type = RTN_UNREACHABLE; if (err == -ESRCH) err = -ENETUNREACH; @@ -2405,10 +1711,6 @@ martian_destination: &daddr, &saddr, dev->name); #endif -e_hostunreach: - err = -EHOSTUNREACH; - goto out; - e_inval: err = -EINVAL; goto out; @@ -2424,50 +1726,13 @@ martian_source_keep_err: goto out; } -int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, bool noref) +int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev) { - struct rtable *rth; - unsigned int 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->rt_key_dst ^ (__force u32)daddr) | - ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | - (rth->rt_route_iif ^ iif) | - (rth->rt_key_tos ^ tos)) == 0 && - rth->rt_mark == skb->mark && - net_eq(dev_net(rth->dst.dev), net) && - !rt_is_expired(rth)) { - ipv4_validate_peer(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 @@ -2505,24 +1770,28 @@ skip_cache: rcu_read_unlock(); return res; } -EXPORT_SYMBOL(ip_route_input_common); +EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, - const struct flowi4 *fl4, - __be32 orig_daddr, __be32 orig_saddr, - int orig_oif, __u8 orig_rtos, + const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; + struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; - if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + in_dev = __in_dev_get_rcu(dev_out); + if (!in_dev) return ERR_PTR(-EINVAL); + if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) + if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK)) + return ERR_PTR(-EINVAL); + if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) @@ -2533,10 +1802,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - in_dev = __in_dev_get_rcu(dev_out); - if (!in_dev) - return ERR_PTR(-EINVAL); - if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; @@ -2553,40 +1818,44 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fi = NULL; } + fnhe = NULL; + if (fi) { + struct rtable __rcu **prth; + + fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr); + if (fnhe) + prth = &fnhe->fnhe_rth; + else + prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output); + rth = rcu_dereference(*prth); + if (rt_cache_valid(rth)) { + dst_hold(&rth->dst); + return rth; + } + } rth = rt_dst_alloc(dev_out, IN_DEV_CONF_GET(in_dev, NOPOLICY), - IN_DEV_CONF_GET(in_dev, NOXFRM)); + IN_DEV_CONF_GET(in_dev, NOXFRM), + fi); if (!rth) return ERR_PTR(-ENOBUFS); rth->dst.output = ip_output; - rth->rt_key_dst = orig_daddr; - rth->rt_key_src = orig_saddr; rth->rt_genid = rt_genid(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; - rth->rt_key_tos = orig_rtos; - rth->rt_dst = fl4->daddr; - rth->rt_src = fl4->saddr; - rth->rt_route_iif = 0; - rth->rt_iif = orig_oif ? : dev_out->ifindex; - rth->rt_oif = orig_oif; - rth->rt_mark = fl4->flowi4_mark; - rth->rt_gateway = fl4->daddr; - rth->rt_spec_dst= fl4->saddr; - rth->rt_peer_genid = 0; - rth->peer = NULL; - rth->fi = NULL; + rth->rt_is_input = 0; + rth->rt_iif = orig_oif ? : 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); RT_CACHE_STAT_INC(out_slow_tot); - if (flags & RTCF_LOCAL) { + if (flags & RTCF_LOCAL) rth->dst.input = ip_local_deliver; - rth->rt_spec_dst = fl4->daddr; - } if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { - rth->rt_spec_dst = fl4->saddr; if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; @@ -2603,34 +1872,28 @@ static struct rtable *__mkroute_output(const struct fib_result *res, #endif } - rt_set_nexthop(rth, fl4, res, fi, type, 0); + rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); return rth; } /* * Major route resolver routine. - * called with rcu_read_lock(); */ -static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) +struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) { struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); unsigned int flags = 0; struct fib_result res; struct rtable *rth; - __be32 orig_daddr; - __be32 orig_saddr; int orig_oif; + res.tclassid = 0; res.fi = NULL; -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif + res.table = NULL; - orig_daddr = fl4->daddr; - orig_saddr = fl4->saddr; orig_oif = fl4->flowi4_oif; fl4->flowi4_iif = net->loopback_dev->ifindex; @@ -2730,6 +1993,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) if (fib_lookup(net, fl4, &res)) { res.fi = NULL; + res.table = NULL; if (fl4->flowi4_oif) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2791,60 +2055,12 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) make_route: - rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif, - tos, dev_out, flags); - if (!IS_ERR(rth)) { - unsigned int hash; - - hash = rt_hash(orig_daddr, orig_saddr, orig_oif, - rt_genid(dev_net(dev_out))); - rth = rt_intern_hash(hash, rth, NULL, orig_oif); - } + rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags); out: rcu_read_unlock(); return rth; } - -struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) -{ - struct rtable *rth; - unsigned int hash; - - if (!rt_caching(net)) - goto slow_output; - - hash = rt_hash(flp4->daddr, flp4->saddr, flp4->flowi4_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->rt_key_dst == flp4->daddr && - rth->rt_key_src == flp4->saddr && - rt_is_output_route(rth) && - rth->rt_oif == flp4->flowi4_oif && - rth->rt_mark == flp4->flowi4_mark && - !((rth->rt_key_tos ^ flp4->flowi4_tos) & - (IPTOS_RT_MASK | RTO_ONLINK)) && - net_eq(dev_net(rth->dst.dev), net) && - !rt_is_expired(rth)) { - ipv4_validate_peer(rth); - dst_use(&rth->dst, jiffies); - RT_CACHE_STAT_INC(out_hit); - rcu_read_unlock_bh(); - if (!flp4->saddr) - flp4->saddr = rth->rt_src; - if (!flp4->daddr) - flp4->daddr = rth->rt_dst; - return rth; - } - RT_CACHE_STAT_INC(out_hlist_search); - } - rcu_read_unlock_bh(); - -slow_output: - return ip_route_output_slow(net, flp4); -} EXPORT_SYMBOL_GPL(__ip_route_output_key); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) @@ -2859,7 +2075,13 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } @@ -2872,53 +2094,42 @@ static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), - .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, + .redirect = ipv4_rt_blackhole_redirect, .cow_metrics = ipv4_rt_blackhole_cow_metrics, .neigh_lookup = ipv4_neigh_lookup, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0); struct rtable *ort = (struct rtable *) dst_orig; + struct rtable *rt; + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard; - dst_copy_metrics(new, &ort->dst); new->dev = ort->dst.dev; if (new->dev) dev_hold(new->dev); - rt->rt_key_dst = ort->rt_key_dst; - rt->rt_key_src = ort->rt_key_src; - rt->rt_key_tos = ort->rt_key_tos; - rt->rt_route_iif = ort->rt_route_iif; + rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; - rt->rt_oif = ort->rt_oif; - rt->rt_mark = ort->rt_mark; + rt->rt_pmtu = ort->rt_pmtu; rt->rt_genid = rt_genid(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; - rt->rt_dst = ort->rt_dst; - rt->rt_src = ort->rt_src; rt->rt_gateway = ort->rt_gateway; - rt->rt_spec_dst = ort->rt_spec_dst; - 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); + + INIT_LIST_HEAD(&rt->rt_uncached); dst_free(new); } @@ -2945,16 +2156,16 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); -static int rt_fill_info(struct net *net, - struct sk_buff *skb, u32 pid, u32 seq, int event, - int nowait, unsigned int flags) +static int rt_fill_info(struct net *net, __be32 dst, __be32 src, + struct flowi4 *fl4, struct sk_buff *skb, u32 pid, + u32 seq, int event, int nowait, unsigned int flags) { struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; - const struct inet_peer *peer = rt->peer; - u32 id = 0, ts = 0, tsage = 0, error; + u32 error; + u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); if (nlh == NULL) @@ -2964,7 +2175,7 @@ static int rt_fill_info(struct net *net, r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = rt->rt_key_tos; + r->rtm_tos = fl4->flowi4_tos; r->rtm_table = RT_TABLE_MAIN; if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN)) goto nla_put_failure; @@ -2975,11 +2186,11 @@ static int rt_fill_info(struct net *net, if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - if (nla_put_be32(skb, RTA_DST, rt->rt_dst)) + if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; - if (rt->rt_key_src) { + if (src) { r->rtm_src_len = 32; - if (nla_put_be32(skb, RTA_SRC, rt->rt_key_src)) + if (nla_put_be32(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && @@ -2990,69 +2201,40 @@ static int rt_fill_info(struct net *net, nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif - if (rt_is_input_route(rt)) { - if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_spec_dst)) - goto nla_put_failure; - } else if (rt->rt_src != rt->rt_key_src) { - if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src)) + if (!rt_is_input_route(rt) && + fl4->saddr != src) { + if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } - if (rt->rt_dst != rt->rt_gateway && + if (rt->rt_gateway && nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway)) goto nla_put_failure; - if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) + memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); + if (rt->rt_pmtu) + metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; - if (rt->rt_mark && - nla_put_be32(skb, RTA_MARK, rt->rt_mark)) + if (fl4->flowi4_mark && + nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; error = rt->dst.error; - if (peer) { - inet_peer_refcheck(rt->peer); - id = atomic_read(&peer->ip_id_count) & 0xffff; - if (peer->tcp_ts_stamp) { - ts = peer->tcp_ts; - tsage = get_seconds() - peer->tcp_ts_stamp; - } - expires = ACCESS_ONCE(peer->pmtu_expires); - if (expires) { - if (time_before(jiffies, expires)) - expires -= jiffies; - else - expires = 0; - } + expires = rt->dst.expires; + if (expires) { + if (time_before(jiffies, expires)) + expires -= jiffies; + else + expires = 0; } if (rt_is_input_route(rt)) { -#ifdef CONFIG_IP_MROUTE - __be32 dst = rt->rt_dst; - - if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && - IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { - int err = ipmr_get_route(net, skb, - rt->rt_src, rt->rt_dst, - r, nowait); - if (err <= 0) { - if (!nowait) { - if (err == 0) - return 0; - goto nla_put_failure; - } else { - if (err == -EMSGSIZE) - goto nla_put_failure; - error = err; - } - } - } else -#endif - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) - goto nla_put_failure; + if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + goto nla_put_failure; } - if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage, - expires, error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -3068,6 +2250,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; struct rtable *rt = NULL; + struct flowi4 fl4; __be32 dst = 0; __be32 src = 0; u32 iif; @@ -3102,6 +2285,13 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = dst; + fl4.saddr = src; + fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; + fl4.flowi4_mark = mark; + if (iif) { struct net_device *dev; @@ -3122,13 +2312,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { - struct flowi4 fl4 = { - .daddr = dst, - .saddr = src, - .flowi4_tos = rtm->rtm_tos, - .flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0, - .flowi4_mark = mark, - }; rt = ip_route_output_key(net, &fl4); err = 0; @@ -3143,7 +2326,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + err = rt_fill_info(net, dst, src, &fl4, skb, + NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err <= 0) goto errout_free; @@ -3159,43 +2343,6 @@ 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; } @@ -3400,26 +2547,34 @@ static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; +static int __net_init ipv4_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); -#ifdef CONFIG_IP_ROUTE_CLASSID -struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; -#endif /* CONFIG_IP_ROUTE_CLASSID */ + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv4.peers = bp; + return 0; +} -static __initdata unsigned long rhash_entries; -static int __init set_rhash_entries(char *str) +static void __net_exit ipv4_inetpeer_exit(struct net *net) { - ssize_t ret; + struct inet_peer_base *bp = net->ipv4.peers; - if (!str) - return 0; + net->ipv4.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} - ret = kstrtoul(str, 0, &rhash_entries); - if (ret) - return 0; +static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { + .init = ipv4_inetpeer_init, + .exit = ipv4_inetpeer_exit, +}; - return 1; -} -__setup("rhash_entries=", set_rhash_entries); +#ifdef CONFIG_IP_ROUTE_CLASSID +struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; +#endif /* CONFIG_IP_ROUTE_CLASSID */ int __init ip_rt_init(void) { @@ -3443,31 +2598,12 @@ 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, - 0, - 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(); - 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()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM @@ -3480,6 +2616,7 @@ int __init ip_rt_init(void) register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&rt_genid_ops); + register_pernet_subsys(&ipv4_inetpeer_ops); return rc; } |