提交 c1a34035 编写于 作者: D David S. Miller

Merge branch 'ipv6_route_sharing'

Martin KaFai Lau says:

====================
ipv6: Only create RTF_CACHE route after encountering pmtu exception

v4 -> v5:
- Patch 1 is new. Clean up the ipv6_select_ident() and ip6_fragment().

- Further simplify the newly added rt6_get_pcpu_route().  If there is a
  'prev' after cmpxchg, return prev instead of the newly created percpu
  clone.

v3 -> v4:
- Patch 8 is new. It keeps track of the DST_NOCACHE routes in a list to handle
  the iface down/unregister event.

- Remove rcu from the newly added rt6i_pcpu variable.  It is not needed
  because it has already been protected by the existing reader/writer lock.

- Thanks to 'Julian Anastasov <ja@ssi.bg>' for testing the FLOWI_FLAG_KNOWN_NH
  patches.

v2 -> v3:
- Patch 5 to 7 are new.  They take care of cases where the daddr in
  skb is not the one used to do the route look-up.  There is also
  related changes to rt6_nexthop() since v2 which is in patch 2/9.
  Thanks to 'Julian Anastasov <ja@ssi.bg>' for pointing it out.

- Fix a few problems in __ip6_rt_update_pmtu(), like setting the expire
  and mtu before inserting to the tree and don't do dst_destroy() after
  tree insertion failure.  Also update the rt6i_pmtu in fib6_add_rt2node().
  Thanks to 'Steffen Klassert <steffen.klassert@secunet.com>' for pointing
  it out.

- Merge ip6_pmtu_rt_cache_alloc() into ip6_rt_cache_alloc().

v1 -> v2:
- Move the /128 route bug fixes to another series (accepted).
- Create a function for checking (rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)).
- Avoid shuffling the skb network_header.  Instead, change the function
  signature to take iph instead of skb.

- Many Thanks to 'Hannes Frederic Sowa <hannes@stressinduktion.org>' on
  reviewing v1 and v2 and giving advice.

--Martin

~~~ start: v1 compose message (with the out-dated parts removed) ~~~

This series is to avoid creating a RTF_CACHE route whenever we are consulting
the fib6 tree with a new destination.  Instead, only create RTF_CACHE route
when we see a pmtu exception.

Out of all ipv6 RTF_CACHE routes that are created, the percentage that has a
different mtu is very small. In one of our end-user facing proxy server,
only 1k out of 80k RTF_CACHE routes have a smaller MTU.  For our DC
traffic, there is no mtu exception.

A large fib6 tree has problems like, 'ip -6 r show' takes a long time.
gc may kick in too often.  Also, when a service has restarted and a lot
of new TCP conn requests come in, it creates pressure on the tree by inserting
a lot of RTF_CACHE in a short time and it currently requires a write lock
to do that.

The first few patches are prep works to remove assumption that the
returned rt is always RTF_CACHE.

The patch 'ipv6: Only create RTF_CACHE routes after encountering pmtu exception'
do the lazy RTF_CACHE route creation.

The following patches added percpu rt to compensate the performance loss after
doing the RTF_CACHE lazy creation.

Here is some numbers of the udpflood test.  The udpflood has been
slightly modified to have a time limit instead of count limit.

A /64 via gateway route is used for the test. Each udpflood uses 10000 dst
addresses.  The dst addresses of different udpflood processes do not overlap
with each other.

1                    16M                          15M
10                   61M                          61M
20                   65M                          62M
40                   88M                          83M

~~~ end: v1 compose message ~~~
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
......@@ -728,7 +728,7 @@ static struct cxgbi_sock *cxgbi_check_route6(struct sockaddr *dst_addr)
}
ndev = n->dev;
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
if (ipv6_addr_is_multicast(&daddr6->sin6_addr)) {
pr_info("multi-cast route %pI6 port %u, dev %s.\n",
daddr6->sin6_addr.s6_addr,
ntohs(daddr6->sin6_port), ndev->name);
......
......@@ -120,7 +120,11 @@ struct rt6_info {
struct rt6key rt6i_src;
struct rt6key rt6i_prefsrc;
struct list_head rt6i_uncached;
struct uncached_list *rt6i_uncached_list;
struct inet6_dev *rt6i_idev;
struct rt6_info * __percpu *rt6i_pcpu;
u32 rt6i_metric;
u32 rt6i_pmtu;
......@@ -159,6 +163,14 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
rt0->rt6i_flags |= RTF_EXPIRES;
}
static inline u32 rt6_get_cookie(const struct rt6_info *rt)
{
if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
rt = (struct rt6_info *)(rt->dst.from);
return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
}
static inline void ip6_rt_put(struct rt6_info *rt)
{
/* dst_release() accepts a NULL parameter.
......
......@@ -145,7 +145,7 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst,
#ifdef CONFIG_IPV6_SUBTREES
np->saddr_cache = saddr;
#endif
np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
np->dst_cookie = rt6_get_cookie(rt);
}
static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
......@@ -163,11 +163,14 @@ static inline bool ipv6_unicast_destination(const struct sk_buff *skb)
return rt->rt6i_flags & RTF_LOCAL;
}
static inline bool ipv6_anycast_destination(const struct sk_buff *skb)
static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
const struct in6_addr *daddr)
{
struct rt6_info *rt = (struct rt6_info *) skb_dst(skb);
struct rt6_info *rt = (struct rt6_info *)dst;
return rt->rt6i_flags & RTF_ANYCAST;
return rt->rt6i_flags & RTF_ANYCAST ||
(rt->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
}
int ip6_fragment(struct sock *sk, struct sk_buff *skb,
......@@ -194,9 +197,15 @@ static inline bool ip6_sk_ignore_df(const struct sock *sk)
inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
}
static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
struct in6_addr *daddr)
{
return &rt->rt6i_gateway;
if (rt->rt6i_flags & RTF_GATEWAY)
return &rt->rt6i_gateway;
else if (unlikely(rt->rt6i_flags & RTF_CACHE))
return &rt->rt6i_dst.addr;
else
return daddr;
}
#endif
......@@ -671,8 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
}
void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr,
struct rt6_info *rt);
u32 ipv6_select_ident(struct net *net,
const struct in6_addr *daddr,
const struct in6_addr *saddr);
void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
int ip6_dst_hoplimit(struct dst_entry *dst);
......
......@@ -34,6 +34,7 @@
#define RTF_PREF(pref) ((pref) << 27)
#define RTF_PREF_MASK 0x18000000
#define RTF_PCPU 0x40000000
#define RTF_LOCAL 0x80000000
......
......@@ -192,7 +192,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_dev *dev,
if (ipv6_addr_any(nexthop))
return NULL;
} else {
nexthop = rt6_nexthop(rt);
nexthop = rt6_nexthop(rt, daddr);
/* We need to remember the address because it is needed
* by bt_xmit() when sending the packet. In bt_xmit(), the
......
......@@ -207,7 +207,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
struct inet_peer *peer;
peer = inet_getpeer_v6(net->ipv6.peers,
&rt->rt6i_dst.addr, 1);
&fl6->daddr, 1);
res = inet_peer_xrlim_allow(peer, tmo);
if (peer)
inet_putpeer(peer);
......@@ -337,7 +337,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
* We won't send icmp if the destination is known
* anycast.
*/
if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
if (ipv6_anycast_destination(dst, &fl6->daddr)) {
net_dbg_ratelimited("icmp6_send: acast source\n");
dst_release(dst);
return ERR_PTR(-EINVAL);
......@@ -564,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
if (!ipv6_unicast_destination(skb) &&
!(net->ipv6.sysctl.anycast_src_echo_reply &&
ipv6_anycast_destination(skb)))
ipv6_anycast_destination(skb_dst(skb), saddr)))
saddr = NULL;
memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
......
......@@ -154,10 +154,32 @@ static void node_free(struct fib6_node *fn)
kmem_cache_free(fib6_node_kmem, fn);
}
static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
{
int cpu;
if (!non_pcpu_rt->rt6i_pcpu)
return;
for_each_possible_cpu(cpu) {
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
if (pcpu_rt) {
dst_free(&pcpu_rt->dst);
*ppcpu_rt = NULL;
}
}
}
static void rt6_release(struct rt6_info *rt)
{
if (atomic_dec_and_test(&rt->rt6i_ref))
if (atomic_dec_and_test(&rt->rt6i_ref)) {
rt6_free_pcpu(rt);
dst_free(&rt->dst);
}
}
static void fib6_link_table(struct net *net, struct fib6_table *tb)
......@@ -738,6 +760,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
iter->rt6i_pmtu = rt->rt6i_pmtu;
return -EEXIST;
}
/* If we have the same destination and the same metric,
......
......@@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
}
rcu_read_lock_bh();
nexthop = rt6_nexthop((struct rt6_info *)dst);
nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
......@@ -459,7 +459,7 @@ int ip6_forward(struct sk_buff *skb)
else
target = &hdr->daddr;
peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
......@@ -551,7 +551,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
int hroom, troom;
__be32 frag_id = 0;
__be32 frag_id;
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
struct net *net = dev_net(skb_dst(skb)->dev);
......@@ -584,6 +584,9 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
}
mtu -= hlen + sizeof(struct frag_hdr);
frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr);
if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
struct sk_buff *frag2;
......@@ -632,11 +635,10 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
ipv6_select_ident(net, fh, rt);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
frag_id = fh->identification;
fh->identification = frag_id;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
......@@ -778,11 +780,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
if (!frag_id) {
ipv6_select_ident(net, fh, rt);
frag_id = fh->identification;
} else
fh->identification = frag_id;
fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
......@@ -936,7 +934,8 @@ static int ip6_dst_lookup_tail(struct sock *sk,
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
n = __ipv6_neigh_lookup_noref(rt->dst.dev,
rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
......@@ -1060,11 +1059,10 @@ static inline int ip6_ufo_append_data(struct sock *sk,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
int transhdrlen, int mtu, unsigned int flags,
struct rt6_info *rt)
const struct flowi6 *fl6)
{
struct sk_buff *skb;
struct frag_hdr fhdr;
int err;
/* There is support for UDP large send offload by network
......@@ -1106,8 +1104,9 @@ static inline int ip6_ufo_append_data(struct sock *sk,
skb_shinfo(skb)->gso_size = (mtu - fragheaderlen -
sizeof(struct frag_hdr)) & ~7;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
ipv6_select_ident(sock_net(sk), &fhdr, rt);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
skb_shinfo(skb)->ip6_frag_id = ipv6_select_ident(sock_net(sk),
&fl6->daddr,
&fl6->saddr);
append:
return skb_append_datato_frags(sk, skb, getfrag, from,
......@@ -1332,7 +1331,7 @@ static int __ip6_append_data(struct sock *sk,
(sk->sk_type == SOCK_DGRAM)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen,
transhdrlen, mtu, flags, rt);
transhdrlen, mtu, flags, fl6);
if (err)
goto error;
return 0;
......
......@@ -151,7 +151,7 @@ EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *) dst;
t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
t->dst_cookie = rt6_get_cookie(rt);
dst_release(t->dst_cache);
t->dst_cache = dst;
}
......
......@@ -1506,7 +1506,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
"Redirect: destination is not a neighbour\n");
goto release;
}
peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
if (peer)
inet_putpeer(peer);
......
......@@ -10,7 +10,8 @@
#include <net/secure_seq.h>
static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
struct in6_addr *dst, struct in6_addr *src)
const struct in6_addr *dst,
const struct in6_addr *src)
{
u32 hash, id;
......@@ -60,17 +61,17 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr,
struct rt6_info *rt)
u32 ipv6_select_ident(struct net *net,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
static u32 ip6_idents_hashrnd __read_mostly;
u32 id;
net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
id = __ipv6_select_ident(net, ip6_idents_hashrnd, &rt->rt6i_dst.addr,
&rt->rt6i_src.addr);
fhdr->identification = htonl(id);
id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr);
return htonl(id);
}
EXPORT_SYMBOL(ipv6_select_ident);
......
......@@ -865,6 +865,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = np->ucast_oif;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
if (inet->hdrincl)
fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
......
......@@ -72,8 +72,7 @@ enum rt6_nud_state {
RT6_NUD_SUCCEED = 1
};
static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest);
static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ip6_default_advmss(const struct dst_entry *dst);
static unsigned int ip6_mtu(const struct dst_entry *dst);
......@@ -105,11 +104,79 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *gwaddr, int ifindex);
#endif
struct uncached_list {
spinlock_t lock;
struct list_head head;
};
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
static void rt6_uncached_list_add(struct rt6_info *rt)
{
struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
rt->dst.flags |= DST_NOCACHE;
rt->rt6i_uncached_list = ul;
spin_lock_bh(&ul->lock);
list_add_tail(&rt->rt6i_uncached, &ul->head);
spin_unlock_bh(&ul->lock);
}
static void rt6_uncached_list_del(struct rt6_info *rt)
{
if (!list_empty(&rt->rt6i_uncached)) {
struct uncached_list *ul = rt->rt6i_uncached_list;
spin_lock_bh(&ul->lock);
list_del(&rt->rt6i_uncached);
spin_unlock_bh(&ul->lock);
}
}
static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
{
struct net_device *loopback_dev = net->loopback_dev;
int cpu;
for_each_possible_cpu(cpu) {
struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
struct rt6_info *rt;
spin_lock_bh(&ul->lock);
list_for_each_entry(rt, &ul->head, rt6i_uncached) {
struct inet6_dev *rt_idev = rt->rt6i_idev;
struct net_device *rt_dev = rt->dst.dev;
if (rt_idev && (rt_idev->dev == dev || !dev) &&
rt_idev->dev != loopback_dev) {
rt->rt6i_idev = in6_dev_get(loopback_dev);
in6_dev_put(rt_idev);
}
if (rt_dev && (rt_dev == dev || !dev) &&
rt_dev != loopback_dev) {
rt->dst.dev = loopback_dev;
dev_hold(rt->dst.dev);
dev_put(rt_dev);
}
}
spin_unlock_bh(&ul->lock);
}
}
static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt)
{
return dst_metrics_write_ptr(rt->dst.from);
}
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
{
struct rt6_info *rt = (struct rt6_info *)dst;
if (rt->rt6i_flags & RTF_CACHE)
if (rt->rt6i_flags & RTF_PCPU)
return rt6_pcpu_cow_metrics(rt);
else if (rt->rt6i_flags & RTF_CACHE)
return NULL;
else
return dst_cow_metrics_generic(dst, old);
......@@ -249,10 +316,10 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
static struct rt6_info *__ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
......@@ -262,18 +329,53 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
INIT_LIST_HEAD(&rt->rt6i_siblings);
INIT_LIST_HEAD(&rt->rt6i_uncached);
}
return rt;
}
static struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
int flags,
struct fib6_table *table)
{
struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table);
if (rt) {
rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
if (rt->rt6i_pcpu) {
int cpu;
for_each_possible_cpu(cpu) {
struct rt6_info **p;
p = per_cpu_ptr(rt->rt6i_pcpu, cpu);
/* no one shares rt */
*p = NULL;
}
} else {
dst_destroy((struct dst_entry *)rt);
return NULL;
}
}
return rt;
}
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
struct dst_entry *from = dst->from;
struct inet6_dev *idev;
dst_destroy_metrics_generic(dst);
if (rt->rt6i_pcpu)
free_percpu(rt->rt6i_pcpu);
rt6_uncached_list_del(rt);
idev = rt->rt6i_idev;
if (idev) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
......@@ -655,6 +757,11 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
return match ? match : net->ipv6.ip6_null_entry;
}
static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
{
return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
}
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr)
......@@ -833,9 +940,9 @@ int ip6_ins_rt(struct rt6_info *rt)
return __ip6_ins_rt(rt, &info, &mxc);
}
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct rt6_info *rt;
......@@ -843,15 +950,26 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
* Clone the route.
*/
rt = ip6_rt_copy(ort, daddr);
if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
ort = (struct rt6_info *)ort->dst.from;
if (rt) {
rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
0, ort->rt6i_table);
if (!rt)
return NULL;
ip6_rt_copy_init(rt, ort);
rt->rt6i_flags |= RTF_CACHE;
rt->rt6i_metric = 0;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *daddr;
rt->rt6i_dst.plen = 128;
if (!rt6_is_gw_or_nonexthop(ort)) {
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
rt->rt6i_flags |= RTF_CACHE;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
rt->rt6i_src.addr = *saddr;
......@@ -863,30 +981,65 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
return rt;
}
static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
const struct in6_addr *daddr)
static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
{
struct rt6_info *rt = ip6_rt_copy(ort, daddr);
struct rt6_info *pcpu_rt;
if (rt)
rt->rt6i_flags |= RTF_CACHE;
return rt;
pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev),
rt->dst.dev, rt->dst.flags,
rt->rt6i_table);
if (!pcpu_rt)
return NULL;
ip6_rt_copy_init(pcpu_rt, rt);
pcpu_rt->rt6i_protocol = rt->rt6i_protocol;
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
}
/* It should be called with read_lock_bh(&tb6_lock) acquired */
static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
{
struct rt6_info *pcpu_rt, *prev, **p;
p = this_cpu_ptr(rt->rt6i_pcpu);
pcpu_rt = *p;
if (pcpu_rt)
goto done;
pcpu_rt = ip6_rt_pcpu_alloc(rt);
if (!pcpu_rt) {
struct net *net = dev_net(rt->dst.dev);
pcpu_rt = net->ipv6.ip6_null_entry;
goto done;
}
prev = cmpxchg(p, NULL, pcpu_rt);
if (prev) {
/* If someone did it before us, return prev instead */
dst_destroy(&pcpu_rt->dst);
pcpu_rt = prev;
}
done:
dst_hold(&pcpu_rt->dst);
rt6_dst_from_metrics_check(pcpu_rt);
return pcpu_rt;
}
static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
struct flowi6 *fl6, int flags)
{
struct fib6_node *fn, *saved_fn;
struct rt6_info *rt, *nrt;
struct rt6_info *rt;
int strict = 0;
int attempts = 3;
int err;
strict |= flags & RT6_LOOKUP_F_IFACE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
redo_fib6_lookup_lock:
read_lock_bh(&table->tb6_lock);
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
......@@ -905,52 +1058,52 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
strict &= ~RT6_LOOKUP_F_REACHABLE;
fn = saved_fn;
goto redo_rt6_select;
} else {
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
goto out2;
}
}
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
if (rt->rt6i_flags & RTF_CACHE)
goto out2;
if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) {
dst_use(&rt->dst, jiffies);
read_unlock_bh(&table->tb6_lock);
if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)))
nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
else if (!(rt->dst.flags & DST_HOST) || !(rt->rt6i_flags & RTF_LOCAL))
nrt = rt6_alloc_clone(rt, &fl6->daddr);
else
goto out2;
rt6_dst_from_metrics_check(rt);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
!(rt->rt6i_flags & RTF_GATEWAY))) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
* from the fl6->daddr used to look-up route here.
*/
ip6_rt_put(rt);
rt = nrt ? : net->ipv6.ip6_null_entry;
struct rt6_info *uncached_rt;
dst_hold(&rt->dst);
if (nrt) {
err = ip6_ins_rt(nrt);
if (!err)
goto out2;
}
dst_use(&rt->dst, jiffies);
read_unlock_bh(&table->tb6_lock);
if (--attempts <= 0)
goto out2;
uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
dst_release(&rt->dst);
/*
* Race condition! In the gap, when table->tb6_lock was
* released someone could insert this route. Relookup.
*/
ip6_rt_put(rt);
goto redo_fib6_lookup_lock;
if (uncached_rt)
rt6_uncached_list_add(uncached_rt);
else
uncached_rt = net->ipv6.ip6_null_entry;
out2:
rt6_dst_from_metrics_check(rt);
rt->dst.lastuse = jiffies;
rt->dst.__use++;
dst_hold(&uncached_rt->dst);
return uncached_rt;
return rt;
} else {
/* Get a percpu copy */
struct rt6_info *pcpu_rt;
rt->dst.lastuse = jiffies;
rt->dst.__use++;
pcpu_rt = rt6_get_pcpu_route(rt);
read_unlock_bh(&table->tb6_lock);
return pcpu_rt;
}
}
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
......@@ -1061,6 +1214,26 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt)
dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true);
}
static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
{
if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
return NULL;
if (rt6_check_expired(rt))
return NULL;
return &rt->dst;
}
static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
{
if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
rt6_check((struct rt6_info *)(rt->dst.from), cookie))
return &rt->dst;
else
return NULL;
}
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
struct rt6_info *rt;
......@@ -1071,15 +1244,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
return NULL;
if (rt6_check_expired(rt))
return NULL;
rt6_dst_from_metrics_check(rt);
return dst;
if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
return rt6_dst_from_check(rt, cookie);
else
return rt6_check(rt, cookie);
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
......@@ -1118,24 +1289,63 @@ static void ip6_link_failure(struct sk_buff *skb)
}
}
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
{
struct net *net = dev_net(rt->dst.dev);
rt->rt6i_flags |= RTF_MODIFIED;
rt->rt6i_pmtu = mtu;
rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
const struct ipv6hdr *iph, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info *)dst;
dst_confirm(dst);
if (mtu < dst_mtu(dst) && (rt6->rt6i_flags & RTF_CACHE)) {
struct net *net = dev_net(dst->dev);
if (rt6->rt6i_flags & RTF_LOCAL)
return;
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
dst_confirm(dst);
mtu = max_t(u32, mtu, IPV6_MIN_MTU);
if (mtu >= dst_mtu(dst))
return;
rt6->rt6i_pmtu = mtu;
rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
if (rt6->rt6i_flags & RTF_CACHE) {
rt6_do_update_pmtu(rt6, mtu);
} else {
const struct in6_addr *daddr, *saddr;
struct rt6_info *nrt6;
if (iph) {
daddr = &iph->daddr;
saddr = &iph->saddr;
} else if (sk) {
daddr = &sk->sk_v6_daddr;
saddr = &inet6_sk(sk)->saddr;
} else {
return;
}
nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
/* ip6_ins_rt(nrt6) will bump the
* rt6->rt6i_node->fn_sernum
* which will fail the next rt6_check() and
* invalidate the sk->sk_dst_cache.
*/
ip6_ins_rt(nrt6);
}
}
}
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
int oif, u32 mark)
{
......@@ -1152,7 +1362,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
......@@ -1879,7 +2089,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NEIGH_UPDATE_F_ISROUTER))
);
nrt = ip6_rt_copy(rt, &msg->dest);
nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
if (!nrt)
goto out;
......@@ -1921,46 +2131,25 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
}
static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest)
static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
{
struct net *net = dev_net(ort->dst.dev);
struct rt6_info *rt;
if (ort->rt6i_flags & RTF_CACHE)
ort = (struct rt6_info *)ort->dst.from;
rt = ip6_dst_alloc(net, ort->dst.dev, 0,
ort->rt6i_table);
if (rt) {
rt->dst.input = ort->dst.input;
rt->dst.output = ort->dst.output;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *dest;
rt->rt6i_dst.plen = 128;
rt->dst.error = ort->dst.error;
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
if (ort->rt6i_flags & RTF_GATEWAY)
rt->rt6i_gateway = ort->rt6i_gateway;
else
rt->rt6i_gateway = *dest;
rt->rt6i_flags = ort->rt6i_flags;
rt6_set_from(rt, ort);
rt->rt6i_metric = 0;
rt->dst.input = ort->dst.input;
rt->dst.output = ort->dst.output;
rt->rt6i_dst = ort->rt6i_dst;
rt->dst.error = ort->dst.error;
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags;
rt6_set_from(rt, ort);
rt->rt6i_metric = ort->rt6i_metric;
#ifdef CONFIG_IPV6_SUBTREES
memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
rt->rt6i_src = ort->rt6i_src;
#endif
memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key));
rt->rt6i_table = ort->rt6i_table;
}
return rt;
rt->rt6i_prefsrc = ort->rt6i_prefsrc;
rt->rt6i_table = ort->rt6i_table;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
......@@ -2335,6 +2524,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
fib6_clean_all(net, fib6_ifdown, &adn);
icmp6_clean_all(fib6_ifdown, &adn);
rt6_uncached_list_flush_dev(net, dev);
}
struct rt6_mtu_change_arg {
......@@ -3231,6 +3421,7 @@ static struct notifier_block ip6_route_dev_notifier = {
int __init ip6_route_init(void)
{
int ret;
int cpu;
ret = -ENOMEM;
ip6_dst_ops_template.kmem_cachep =
......@@ -3290,6 +3481,13 @@ int __init ip6_route_init(void)
if (ret)
goto out_register_late_subsys;
for_each_possible_cpu(cpu) {
struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
INIT_LIST_HEAD(&ul->head);
spin_lock_init(&ul->lock);
}
out:
return ret;
......
......@@ -99,8 +99,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
dst_hold(dst);
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
if (rt->rt6i_node)
inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
}
}
......@@ -262,7 +261,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
rt = (struct rt6_info *) dst;
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr))
ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr))
tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
......
......@@ -76,8 +76,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
{
if (dst->ops->family == AF_INET6) {
struct rt6_info *rt = (struct rt6_info *)dst;
if (rt->rt6i_node)
path->path_cookie = rt->rt6i_node->fn_sernum;
path->path_cookie = rt6_get_cookie(rt);
}
path->u.rt6.rt6i_nfheader_len = nfheader_len;
......@@ -105,8 +104,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
xdst->u.rt6.rt6i_node = rt->rt6i_node;
if (rt->rt6i_node)
xdst->route_cookie = rt->rt6i_node->fn_sernum;
xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
......
......@@ -364,13 +364,16 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
#ifdef CONFIG_IP_VS_IPV6
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
struct in6_addr *ret_saddr, int do_xfrm, int rt_mode)
{
struct dst_entry *dst;
struct flowi6 fl6 = {
.daddr = *daddr,
};
if (rt_mode & IP_VS_RT_MODE_KNOWN_NH)
fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error)
goto out_err;
......@@ -427,7 +430,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
}
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest_dst->dst_saddr.in6,
do_xfrm);
do_xfrm, rt_mode);
if (!dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
......@@ -435,7 +438,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
goto err_unreach;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
cookie = rt6_get_cookie(rt);
__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
......@@ -446,7 +449,8 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
*ret_saddr = dest_dst->dst_saddr.in6;
} else {
noref = 0;
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm,
rt_mode);
if (!dst)
goto err_unreach;
rt = (struct rt6_info *) dst;
......@@ -781,7 +785,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
......@@ -1164,7 +1168,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
NULL, ipvsh, 0,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL);
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_KNOWN_NH);
if (local < 0)
goto tx_error;
if (local) {
......@@ -1346,7 +1351,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI6\n",
__func__, &cp->daddr.in6);
......
......@@ -779,8 +779,8 @@ static int callforward_do_filter(struct net *net,
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(net, (struct dst_entry **)&rt2,
flowi6_to_flowi(&fl2), false)) {
if (ipv6_addr_equal(rt6_nexthop(rt1),
rt6_nexthop(rt2)) &&
if (ipv6_addr_equal(rt6_nexthop(rt1, &fl1.daddr),
rt6_nexthop(rt2, &fl2.daddr)) &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
......
......@@ -152,6 +152,7 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
fl6.daddr = info->gw.in6;
fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
(iph->flow_lbl[1] << 8) | iph->flow_lbl[2];
fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
......
......@@ -73,7 +73,7 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
if (dev == NULL && rt->rt6i_flags & RTF_LOCAL)
ret |= XT_ADDRTYPE_LOCAL;
if (rt->rt6i_flags & RTF_ANYCAST)
if (ipv6_anycast_destination((struct dst_entry *)rt, addr))
ret |= XT_ADDRTYPE_ANYCAST;
dst_release(&rt->dst);
......
......@@ -331,8 +331,9 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
rt = (struct rt6_info *)dst;
t->dst = dst;
t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
pr_debug("rt6_dst:%pI6 rt6_src:%pI6\n", &rt->rt6i_dst.addr,
t->dst_cookie = rt6_get_cookie(rt);
pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n",
&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
&fl6->saddr);
} else {
t->dst = NULL;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册