aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2012-07-22 17:04:15 -0700
committerDavid S. Miller <davem@davemloft.net>2012-07-22 17:04:15 -0700
commit5e9965c15ba88319500284e590733f4a4629a288 (patch)
treeab76263b9f43fb75048a50141d199f445f5fdd2d /net
parent3ba97381343b271296487bf073eb670d5465a8b8 (diff)
parent2860583fe840d972573363dfa190b2149a604534 (diff)
Merge branch 'kill_rtcache'
The ipv4 routing cache is non-deterministic, performance wise, and is subject to reasonably easy to launch denial of service attacks. The routing cache works great for well behaved traffic, and the world was a much friendlier place when the tradeoffs that led to the routing cache's design were considered. What it boils down to is that the performance of the routing cache is a product of the traffic patterns seen by a system rather than being a product of the contents of the routing tables. The former of which is controllable by external entitites. Even for "well behaved" legitimate traffic, high volume sites can see hit rates in the routing cache of only ~%10. The general flow of this patch series is that first the routing cache is removed. We build a completely new rtable entry every lookup request. Next we make some simplifications due to the fact that removing the routing cache causes several members of struct rtable to become no longer necessary. Then we need to make some amends such that we can legally cache pre-constructed routes in the FIB nexthops. Firstly, we need to invalidate routes which are hit with nexthop exceptions. Secondly we have to change the semantics of rt->rt_gateway such that zero means that the destination is on-link and non-zero otherwise. Now that the preparations are ready, we start caching precomputed routes in the FIB nexthops. Output and input routes need different kinds of care when determining if we can legally do such caching or not. The details are in the commit log messages for those changes. The patch series then winds down with some more struct rtable simplifications and other tidy ups that remove unnecessary overhead. On a SPARC-T3 output route lookups are ~876 cycles. Input route lookups are ~1169 cycles with rpfilter disabled, and about ~1468 cycles with rpfilter enabled. These measurements were taken with the kbench_mod test module in the net_test_tools GIT tree: git://git.kernel.org/pub/scm/linux/kernel/git/davem/net_test_tools.git That GIT tree also includes a udpflood tester tool and stresses route lookups on packet output. For example, on the same SPARC-T3 system we can run: time ./udpflood -l 10000000 10.2.2.11 with routing cache: real 1m21.955s user 0m6.530s sys 1m15.390s without routing cache: real 1m31.678s user 0m6.520s sys 1m25.140s Performance undoubtedly can easily be improved further. For example fib_table_lookup() performs a lot of excessive computations with all the masking and shifting, some of it conditionalized to deal with edge cases. Also, Eric's no-ref optimization for input route lookups can be re-instated for the FIB nexthop caching code path. I would be really pleased if someone would work on that. In fact anyone suitable motivated can just fire up perf on the loading of the test net_test_tools benchmark kernel module. I spend much of my time going: bash# perf record insmod ./kbench_mod.ko dst=172.30.42.22 src=74.128.0.1 iif=2 bash# perf report Thanks to helpful feedback from Joe Perches, Eric Dumazet, Ben Hutchings, and others. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/core/dst.c4
-rw-r--r--net/dccp/ipv4.c2
-rw-r--r--net/decnet/dn_route.c4
-rw-r--r--net/ipv4/arp.c5
-rw-r--r--net/ipv4/fib_frontend.c5
-rw-r--r--net/ipv4/fib_semantics.c4
-rw-r--r--net/ipv4/inet_connection_sock.c9
-rw-r--r--net/ipv4/ip_fragment.c4
-rw-r--r--net/ipv4/ip_gre.c2
-rw-r--r--net/ipv4/ip_input.c4
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/ipmr.c9
-rw-r--r--net/ipv4/netfilter/ipt_MASQUERADE.c5
-rw-r--r--net/ipv4/route.c1329
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/xfrm4_input.c4
-rw-r--r--net/ipv4/xfrm4_policy.c9
-rw-r--r--net/ipv6/route.c4
-rw-r--r--net/sctp/transport.c2
-rw-r--r--net/xfrm/xfrm_policy.c23
21 files changed, 262 insertions, 1174 deletions
diff --git a/net/core/dst.c b/net/core/dst.c
index 07bacff84aa..069d51d2941 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -94,7 +94,7 @@ loop:
* But we do not have state "obsoleted, but
* referenced by parent", so it is right.
*/
- if (dst->obsolete > 1)
+ if (dst->obsolete > 0)
continue;
___dst_free(dst);
@@ -202,7 +202,7 @@ static void ___dst_free(struct dst_entry *dst)
*/
if (dst->dev == NULL || !(dst->dev->flags&IFF_UP))
dst->input = dst->output = dst_discard;
- dst->obsolete = 2;
+ dst->obsolete = DST_OBSOLETE_DEAD;
}
void __dst_free(struct dst_entry *dst)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ab4f44c9bb2..25428d0c50c 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -508,7 +508,7 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
struct dst_entry *dst;
struct flowi4 fl4;
- dst = inet_csk_route_req(sk, &fl4, req, false);
+ dst = inet_csk_route_req(sk, &fl4, req);
if (dst == NULL)
goto out;
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 47de90d8fe9..23cc11dd4e4 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1176,7 +1176,7 @@ make_route:
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
- rt = dst_alloc(&dn_dst_ops, dev_out, 1, 0, DST_HOST);
+ rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST);
if (rt == NULL)
goto e_nobufs;
@@ -1444,7 +1444,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
}
make_route:
- rt = dst_alloc(&dn_dst_ops, out_dev, 0, 0, DST_HOST);
+ rt = dst_alloc(&dn_dst_ops, out_dev, 0, DST_OBSOLETE_NONE, DST_HOST);
if (rt == NULL)
goto e_nobufs;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 2e560f0c757..a0124eb7dbe 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -475,8 +475,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb)
return 1;
}
- paddr = skb_rtable(skb)->rt_gateway;
-
+ paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr);
if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr,
paddr, dev))
return 0;
@@ -828,7 +827,7 @@ static int arp_process(struct sk_buff *skb)
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
- ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
+ ip_route_input(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b83203658ee..f277cf0e632 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1072,11 +1072,6 @@ 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/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2b57d768240..e55171f184f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -171,6 +171,10 @@ static void free_fib_info_rcu(struct rcu_head *head)
dev_put(nexthop_nh->nh_dev);
if (nexthop_nh->nh_exceptions)
free_nh_exceptions(nexthop_nh);
+ if (nexthop_nh->nh_rth_output)
+ dst_release(&nexthop_nh->nh_rth_output->dst);
+ if (nexthop_nh->nh_rth_input)
+ dst_release(&nexthop_nh->nh_rth_input->dst);
} endfor_nexthops(fi);
release_net(fi->fib_net);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c7a4de05ca0..db0cf17c00f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -368,8 +368,7 @@ EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
struct dst_entry *inet_csk_route_req(struct sock *sk,
struct flowi4 *fl4,
- const struct request_sock *req,
- bool nocache)
+ const struct request_sock *req)
{
struct rtable *rt;
const struct inet_request_sock *ireq = inet_rsk(req);
@@ -377,8 +376,6 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
struct net *net = sock_net(sk);
int flags = inet_sk_flowi_flags(sk);
- if (nocache)
- flags |= FLOWI_FLAG_RT_NOCACHE;
flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol,
@@ -389,7 +386,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_gateway)
goto route_err;
return &rt->dst;
@@ -422,7 +419,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_gateway)
goto route_err;
return &rt->dst;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8d07c973409..7ad88e5e711 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -258,8 +258,8 @@ static void ip_expire(unsigned long arg)
/* skb dst is stale, drop it, and perform route lookup again */
skb_dst_drop(head);
iph = ip_hdr(head);
- err = ip_route_input_noref(head, iph->daddr, iph->saddr,
- iph->tos, head->dev);
+ err = ip_route_input(head, iph->daddr, iph->saddr,
+ iph->tos, head->dev);
if (err)
goto out_rcu_unlock;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 42c44b1403c..b062a98574f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -766,7 +766,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
- dst = rt->rt_gateway;
+ dst = rt_nexthop(rt, old_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b27d4440f52..4ebc6feee25 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -336,8 +336,8 @@ static int ip_rcv_finish(struct sk_buff *skb)
* how the packet travels inside Linux networking.
*/
if (!skb_dst(skb)) {
- int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
+ int err = ip_route_input(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EXDEV)
NET_INC_STATS_BH(dev_net(skb->dev),
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 665abbb7122..ba39a52d18c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
- if (inet_opt && inet_opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+ if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2c2c35bace7..99af1f0cc65 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -487,7 +487,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
dev->stats.tx_fifo_errors++;
goto tx_error;
}
- dst = rt->rt_gateway;
+ dst = rt_nexthop(rt, old_iph->daddr);
}
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5716c6b808d..8eec8f4a053 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1795,9 +1795,12 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
- .flowi4_oif = rt->rt_oif,
- .flowi4_iif = rt->rt_iif,
- .flowi4_mark = rt->rt_mark,
+ .flowi4_oif = (rt_is_output_route(rt) ?
+ skb->dev->ifindex : 0),
+ .flowi4_iif = (rt_is_output_route(rt) ?
+ net->loopback_dev->ifindex :
+ skb->dev->ifindex),
+ .flowi4_mark = skb->mark,
};
struct mr_table *mrt;
int err;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 2f210c79dc8..cbb6a1a6f6f 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -52,7 +52,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
struct nf_nat_ipv4_range newrange;
const struct nf_nat_ipv4_multi_range_compat *mr;
const struct rtable *rt;
- __be32 newsrc;
+ __be32 newsrc, nh;
NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
@@ -70,7 +70,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
mr = par->targinfo;
rt = skb_rtable(skb);
- newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE);
+ nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
+ newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
if (!newsrc) {
pr_info("%s ate my IP address\n", par->out->name);
return NF_DROP;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d547f6fae20..9add08869c7 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.
@@ -145,14 +141,12 @@ 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, 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 int rt_garbage_collect(struct dst_ops *ops);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
@@ -172,12 +166,10 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
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,
.cow_metrics = ipv4_cow_metrics,
- .destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
@@ -209,184 +201,30 @@ 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)
@@ -396,24 +234,6 @@ 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), 0,
- r->rt_key_tos,
- -1, 0, 0, &len);
-
- seq_printf(seq, "%*s\n", 127 - len, "");
- }
return 0;
}
@@ -426,8 +246,7 @@ 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 = {
@@ -435,7 +254,7 @@ 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,
};
@@ -625,263 +444,12 @@ 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->dst.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)
{
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) ||
- rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- continue;
- }
-
- /* 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
- */
- tmo >>= 1;
- rthp = &rth->dst.rt_next;
- length += has_noalias(rt_hash_table[i].chain, 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.
@@ -902,167 +470,6 @@ 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 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);
-