linux-sg2042/net/ipv4/fib_semantics.c

1251 lines
29 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* IPv4 Forwarding Information Base: semantics.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/init.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/netlink.h>
#include <net/nexthop.h>
#include "fib_lookup.h"
static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
static unsigned int fib_info_hash_size;
static unsigned int fib_info_cnt;
#define DEVINDEX_HASHBITS 8
#define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS)
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
#ifdef CONFIG_IP_ROUTE_MULTIPATH
static DEFINE_SPINLOCK(fib_multipath_lock);
#define for_nexthops(fi) { \
int nhsel; const struct fib_nh *nh; \
for (nhsel = 0, nh = (fi)->fib_nh; \
nhsel < (fi)->fib_nhs; \
nh++, nhsel++)
#define change_nexthops(fi) { \
int nhsel; struct fib_nh *nexthop_nh; \
for (nhsel = 0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \
nhsel < (fi)->fib_nhs; \
nexthop_nh++, nhsel++)
#else /* CONFIG_IP_ROUTE_MULTIPATH */
/* Hope, that gcc will optimize it to get rid of dummy loop */
#define for_nexthops(fi) { \
int nhsel; const struct fib_nh *nh = (fi)->fib_nh; \
for (nhsel = 0; nhsel < 1; nhsel++)
#define change_nexthops(fi) { \
int nhsel; \
struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \
for (nhsel = 0; nhsel < 1; nhsel++)
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
#define endfor_nexthops(fi) }
const struct fib_prop fib_props[RTN_MAX + 1] = {
[RTN_UNSPEC] = {
.error = 0,
.scope = RT_SCOPE_NOWHERE,
},
[RTN_UNICAST] = {
.error = 0,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_LOCAL] = {
.error = 0,
.scope = RT_SCOPE_HOST,
},
[RTN_BROADCAST] = {
.error = 0,
.scope = RT_SCOPE_LINK,
},
[RTN_ANYCAST] = {
.error = 0,
.scope = RT_SCOPE_LINK,
},
[RTN_MULTICAST] = {
.error = 0,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_BLACKHOLE] = {
.error = -EINVAL,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_UNREACHABLE] = {
.error = -EHOSTUNREACH,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_PROHIBIT] = {
.error = -EACCES,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_THROW] = {
.error = -EAGAIN,
.scope = RT_SCOPE_UNIVERSE,
},
[RTN_NAT] = {
.error = -EINVAL,
.scope = RT_SCOPE_NOWHERE,
},
[RTN_XRESOLVE] = {
.error = -EINVAL,
.scope = RT_SCOPE_NOWHERE,
},
};
/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
struct fib_info *fi = container_of(head, struct fib_info, rcu);
if (fi->fib_metrics != (u32 *) dst_default_metrics)
kfree(fi->fib_metrics);
kfree(fi);
}
void free_fib_info(struct fib_info *fi)
{
if (fi->fib_dead == 0) {
pr_warning("Freeing alive fib_info %p\n", fi);
return;
}
change_nexthops(fi) {
if (nexthop_nh->nh_dev)
dev_put(nexthop_nh->nh_dev);
nexthop_nh->nh_dev = NULL;
} endfor_nexthops(fi);
fib_info_cnt--;
release_net(fi->fib_net);
call_rcu(&fi->rcu, free_fib_info_rcu);
}
void fib_release_info(struct fib_info *fi)
{
spin_lock_bh(&fib_info_lock);
if (fi && --fi->fib_treeref == 0) {
hlist_del(&fi->fib_hash);
if (fi->fib_prefsrc)
hlist_del(&fi->fib_lhash);
change_nexthops(fi) {
if (!nexthop_nh->nh_dev)
continue;
hlist_del(&nexthop_nh->nh_hash);
} endfor_nexthops(fi)
fi->fib_dead = 1;
fib_info_put(fi);
}
spin_unlock_bh(&fib_info_lock);
}
static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
{
const struct fib_nh *onh = ofi->fib_nh;
for_nexthops(fi) {
if (nh->nh_oif != onh->nh_oif ||
nh->nh_gw != onh->nh_gw ||
nh->nh_scope != onh->nh_scope ||
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight != onh->nh_weight ||
#endif
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid != onh->nh_tclassid ||
#endif
((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD))
return -1;
onh++;
} endfor_nexthops(fi);
return 0;
}
static inline unsigned int fib_devindex_hashfn(unsigned int val)
{
unsigned int mask = DEVINDEX_HASHSIZE - 1;
return (val ^
(val >> DEVINDEX_HASHBITS) ^
(val >> (DEVINDEX_HASHBITS * 2))) & mask;
}
static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
{
unsigned int mask = (fib_info_hash_size - 1);
unsigned int val = fi->fib_nhs;
val ^= (fi->fib_protocol << 8) | fi->fib_scope;
val ^= (__force u32)fi->fib_prefsrc;
val ^= fi->fib_priority;
for_nexthops(fi) {
val ^= fib_devindex_hashfn(nh->nh_oif);
} endfor_nexthops(fi)
return (val ^ (val >> 7) ^ (val >> 12)) & mask;
}
static struct fib_info *fib_find_info(const struct fib_info *nfi)
{
struct hlist_head *head;
struct hlist_node *node;
struct fib_info *fi;
unsigned int hash;
hash = fib_info_hashfn(nfi);
head = &fib_info_hash[hash];
hlist_for_each_entry(fi, node, head, fib_hash) {
if (!net_eq(fi->fib_net, nfi->fib_net))
continue;
if (fi->fib_nhs != nfi->fib_nhs)
continue;
if (nfi->fib_protocol == fi->fib_protocol &&
nfi->fib_scope == fi->fib_scope &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
nfi->fib_priority == fi->fib_priority &&
memcmp(nfi->fib_metrics, fi->fib_metrics,
sizeof(u32) * RTAX_MAX) == 0 &&
((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 &&
(nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
return fi;
}
return NULL;
}
/* Check, that the gateway is already configured.
* Used only by redirect accept routine.
*/
int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
struct hlist_head *head;
struct hlist_node *node;
struct fib_nh *nh;
unsigned int hash;
spin_lock(&fib_info_lock);
hash = fib_devindex_hashfn(dev->ifindex);
head = &fib_info_devhash[hash];
hlist_for_each_entry(nh, node, head, nh_hash) {
if (nh->nh_dev == dev &&
nh->nh_gw == gw &&
!(nh->nh_flags & RTNH_F_DEAD)) {
spin_unlock(&fib_info_lock);
return 0;
}
}
spin_unlock(&fib_info_lock);
return -1;
}
static inline size_t fib_nlmsg_size(struct fib_info *fi)
{
size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(4) /* RTA_TABLE */
+ nla_total_size(4) /* RTA_DST */
+ nla_total_size(4) /* RTA_PRIORITY */
+ nla_total_size(4); /* RTA_PREFSRC */
/* space for nested metrics */
payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
if (fi->fib_nhs) {
/* Also handles the special case fib_nhs == 1 */
/* each nexthop is packed in an attribute */
size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
/* may contain flow and gateway attribute */
nhsize += 2 * nla_total_size(4);
/* all nexthops are packed in a nested attribute */
payload += nla_total_size(fi->fib_nhs * nhsize);
}
return payload;
}
void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
int dst_len, u32 tb_id, struct nl_info *info,
unsigned int nlm_flags)
{
struct sk_buff *skb;
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
int err = -ENOBUFS;
skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
if (skb == NULL)
goto errout;
err = fib_dump_info(skb, info->pid, seq, event, tb_id,
fa->fa_type, key, dst_len,
fa->fa_tos, fa->fa_info, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
2009-02-25 15:18:28 +08:00
rtnl_notify(skb, info->nl_net, info->pid, RTNLGRP_IPV4_ROUTE,
info->nlh, GFP_KERNEL);
return;
errout:
if (err < 0)
rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
}
/* Return the first fib alias matching TOS with
* priority less than or equal to PRIO.
*/
struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio)
{
if (fah) {
struct fib_alias *fa;
list_for_each_entry(fa, fah, fa_list) {
if (fa->fa_tos > tos)
continue;
if (fa->fa_info->fib_priority >= prio ||
fa->fa_tos < tos)
return fa;
}
}
return NULL;
}
int fib_detect_death(struct fib_info *fi, int order,
struct fib_info **last_resort, int *last_idx, int dflt)
{
struct neighbour *n;
int state = NUD_NONE;
n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
if (n) {
state = n->nud_state;
neigh_release(n);
}
if (state == NUD_REACHABLE)
return 0;
if ((state & NUD_VALID) && order != dflt)
return 0;
if ((state & NUD_VALID) ||
(*last_idx < 0 && order > dflt)) {
*last_resort = fi;
*last_idx = order;
}
return 1;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining)
{
int nhs = 0;
while (rtnh_ok(rtnh, remaining)) {
nhs++;
rtnh = rtnh_next(rtnh, &remaining);
}
/* leftover implies invalid nexthop configuration, discard it */
return remaining > 0 ? 0 : nhs;
}
static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
int remaining, struct fib_config *cfg)
{
change_nexthops(fi) {
int attrlen;
if (!rtnh_ok(rtnh, remaining))
return -EINVAL;
nexthop_nh->nh_flags =
(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
nexthop_nh->nh_weight = rtnh->rtnh_hops + 1;
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
#endif
}
rtnh = rtnh_next(rtnh, &remaining);
} endfor_nexthops(fi);
return 0;
}
#endif
int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
struct rtnexthop *rtnh;
int remaining;
#endif
if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
return 1;
if (cfg->fc_oif || cfg->fc_gw) {
if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
(!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw))
return 0;
return 1;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (cfg->fc_mp == NULL)
return 0;
rtnh = cfg->fc_mp;
remaining = cfg->fc_mp_len;
for_nexthops(fi) {
int attrlen;
if (!rtnh_ok(rtnh, remaining))
return -EINVAL;
if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
return 1;
attrlen = rtnh_attrlen(rtnh);
if (attrlen < 0) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
if (nla && nla_get_be32(nla) != nh->nh_gw)
return 1;
#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
if (nla && nla_get_u32(nla) != nh->nh_tclassid)
return 1;
#endif
}
rtnh = rtnh_next(rtnh, &remaining);
} endfor_nexthops(fi);
#endif
return 0;
}
/*
* Picture
* -------
*
* Semantics of nexthop is very messy by historical reasons.
* We have to take into account, that:
* a) gateway can be actually local interface address,
* so that gatewayed route is direct.
* b) gateway must be on-link address, possibly
* described not by an ifaddr, but also by a direct route.
* c) If both gateway and interface are specified, they should not
* contradict.
* d) If we use tunnel routes, gateway could be not on-link.
*
* Attempt to reconcile all of these (alas, self-contradictory) conditions
* results in pretty ugly and hairy code with obscure logic.
*
* I chose to generalized it instead, so that the size
* of code does not increase practically, but it becomes
* much more general.
* Every prefix is assigned a "scope" value: "host" is local address,
* "link" is direct route,
* [ ... "site" ... "interior" ... ]
* and "universe" is true gateway route with global meaning.
*
* Every prefix refers to a set of "nexthop"s (gw, oif),
* where gw must have narrower scope. This recursion stops
* when gw has LOCAL scope or if "nexthop" is declared ONLINK,
* which means that gw is forced to be on link.
*
* Code is still hairy, but now it is apparently logically
* consistent and very flexible. F.e. as by-product it allows
* to co-exists in peace independent exterior and interior
* routing processes.
*
* Normally it looks as following.
*
* {universe prefix} -> (gw, oif) [scope link]
* |
* |-> {link prefix} -> (gw, oif) [scope local]
* |
* |-> {local prefix} (terminal node)
*/
static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
struct fib_nh *nh)
{
int err;
struct net *net;
struct net_device *dev;
net = cfg->fc_nlinfo.nl_net;
if (nh->nh_gw) {
struct fib_result res;
if (nh->nh_flags & RTNH_F_ONLINK) {
if (cfg->fc_scope >= RT_SCOPE_LINK)
return -EINVAL;
if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST)
return -EINVAL;
dev = __dev_get_by_index(net, nh->nh_oif);
if (!dev)
return -ENODEV;
if (!(dev->flags & IFF_UP))
return -ENETDOWN;
nh->nh_dev = dev;
dev_hold(dev);
nh->nh_scope = RT_SCOPE_LINK;
return 0;
}
fib: RCU conversion of fib_lookup() fib_lookup() converted to be called in RCU protected context, no reference taken and released on a contended cache line (fib_clntref) fib_table_lookup() and fib_semantic_match() get an additional parameter. struct fib_info gets an rcu_head field, and is freed after an rcu grace period. Stress test : (Sending 160.000.000 UDP frames on same neighbour, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_HASH) (about same results for FIB_TRIE) Before patch : real 1m31.199s user 0m13.761s sys 23m24.780s After patch: real 1m5.375s user 0m14.997s sys 15m50.115s Before patch Profile : 13044.00 15.4% __ip_route_output_key vmlinux 8438.00 10.0% dst_destroy vmlinux 5983.00 7.1% fib_semantic_match vmlinux 5410.00 6.4% fib_rules_lookup vmlinux 4803.00 5.7% neigh_lookup vmlinux 4420.00 5.2% _raw_spin_lock vmlinux 3883.00 4.6% rt_set_nexthop vmlinux 3261.00 3.9% _raw_read_lock vmlinux 2794.00 3.3% fib_table_lookup vmlinux 2374.00 2.8% neigh_resolve_output vmlinux 2153.00 2.5% dst_alloc vmlinux 1502.00 1.8% _raw_read_lock_bh vmlinux 1484.00 1.8% kmem_cache_alloc vmlinux 1407.00 1.7% eth_header vmlinux 1406.00 1.7% ipv4_dst_destroy vmlinux 1298.00 1.5% __copy_from_user_ll vmlinux 1174.00 1.4% dev_queue_xmit vmlinux 1000.00 1.2% ip_output vmlinux After patch Profile : 13712.00 15.8% dst_destroy vmlinux 8548.00 9.9% __ip_route_output_key vmlinux 7017.00 8.1% neigh_lookup vmlinux 4554.00 5.3% fib_semantic_match vmlinux 4067.00 4.7% _raw_read_lock vmlinux 3491.00 4.0% dst_alloc vmlinux 3186.00 3.7% neigh_resolve_output vmlinux 3103.00 3.6% fib_table_lookup vmlinux 2098.00 2.4% _raw_read_lock_bh vmlinux 2081.00 2.4% kmem_cache_alloc vmlinux 2013.00 2.3% _raw_spin_lock vmlinux 1763.00 2.0% __copy_from_user_ll vmlinux 1763.00 2.0% ip_output vmlinux 1761.00 2.0% ipv4_dst_destroy vmlinux 1631.00 1.9% eth_header vmlinux 1440.00 1.7% _raw_read_unlock_bh vmlinux Reference results, if IP route cache is enabled : real 0m29.718s user 0m10.845s sys 7m37.341s 25213.00 29.5% __ip_route_output_key vmlinux 9011.00 10.5% dst_release vmlinux 4817.00 5.6% ip_push_pending_frames vmlinux 4232.00 5.0% ip_finish_output vmlinux 3940.00 4.6% udp_sendmsg vmlinux 3730.00 4.4% __copy_from_user_ll vmlinux 3716.00 4.4% ip_route_output_flow vmlinux 2451.00 2.9% __xfrm_lookup vmlinux 2221.00 2.6% ip_append_data vmlinux 1718.00 2.0% _raw_spin_lock_bh vmlinux 1655.00 1.9% __alloc_skb vmlinux 1572.00 1.8% sock_wfree vmlinux 1345.00 1.6% kfree vmlinux Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 18:41:36 +08:00
rcu_read_lock();
{
struct flowi4 fl4 = {
.daddr = nh->nh_gw,
.flowi4_scope = cfg->fc_scope + 1,
.flowi4_oif = nh->nh_oif,
};
/* It is not necessary, but requires a bit of thinking */
if (fl4.flowi4_scope < RT_SCOPE_LINK)
fl4.flowi4_scope = RT_SCOPE_LINK;
err = fib_lookup(net, &fl4, &res);
fib: RCU conversion of fib_lookup() fib_lookup() converted to be called in RCU protected context, no reference taken and released on a contended cache line (fib_clntref) fib_table_lookup() and fib_semantic_match() get an additional parameter. struct fib_info gets an rcu_head field, and is freed after an rcu grace period. Stress test : (Sending 160.000.000 UDP frames on same neighbour, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_HASH) (about same results for FIB_TRIE) Before patch : real 1m31.199s user 0m13.761s sys 23m24.780s After patch: real 1m5.375s user 0m14.997s sys 15m50.115s Before patch Profile : 13044.00 15.4% __ip_route_output_key vmlinux 8438.00 10.0% dst_destroy vmlinux 5983.00 7.1% fib_semantic_match vmlinux 5410.00 6.4% fib_rules_lookup vmlinux 4803.00 5.7% neigh_lookup vmlinux 4420.00 5.2% _raw_spin_lock vmlinux 3883.00 4.6% rt_set_nexthop vmlinux 3261.00 3.9% _raw_read_lock vmlinux 2794.00 3.3% fib_table_lookup vmlinux 2374.00 2.8% neigh_resolve_output vmlinux 2153.00 2.5% dst_alloc vmlinux 1502.00 1.8% _raw_read_lock_bh vmlinux 1484.00 1.8% kmem_cache_alloc vmlinux 1407.00 1.7% eth_header vmlinux 1406.00 1.7% ipv4_dst_destroy vmlinux 1298.00 1.5% __copy_from_user_ll vmlinux 1174.00 1.4% dev_queue_xmit vmlinux 1000.00 1.2% ip_output vmlinux After patch Profile : 13712.00 15.8% dst_destroy vmlinux 8548.00 9.9% __ip_route_output_key vmlinux 7017.00 8.1% neigh_lookup vmlinux 4554.00 5.3% fib_semantic_match vmlinux 4067.00 4.7% _raw_read_lock vmlinux 3491.00 4.0% dst_alloc vmlinux 3186.00 3.7% neigh_resolve_output vmlinux 3103.00 3.6% fib_table_lookup vmlinux 2098.00 2.4% _raw_read_lock_bh vmlinux 2081.00 2.4% kmem_cache_alloc vmlinux 2013.00 2.3% _raw_spin_lock vmlinux 1763.00 2.0% __copy_from_user_ll vmlinux 1763.00 2.0% ip_output vmlinux 1761.00 2.0% ipv4_dst_destroy vmlinux 1631.00 1.9% eth_header vmlinux 1440.00 1.7% _raw_read_unlock_bh vmlinux Reference results, if IP route cache is enabled : real 0m29.718s user 0m10.845s sys 7m37.341s 25213.00 29.5% __ip_route_output_key vmlinux 9011.00 10.5% dst_release vmlinux 4817.00 5.6% ip_push_pending_frames vmlinux 4232.00 5.0% ip_finish_output vmlinux 3940.00 4.6% udp_sendmsg vmlinux 3730.00 4.4% __copy_from_user_ll vmlinux 3716.00 4.4% ip_route_output_flow vmlinux 2451.00 2.9% __xfrm_lookup vmlinux 2221.00 2.6% ip_append_data vmlinux 1718.00 2.0% _raw_spin_lock_bh vmlinux 1655.00 1.9% __alloc_skb vmlinux 1572.00 1.8% sock_wfree vmlinux 1345.00 1.6% kfree vmlinux Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 18:41:36 +08:00
if (err) {
rcu_read_unlock();
return err;
fib: RCU conversion of fib_lookup() fib_lookup() converted to be called in RCU protected context, no reference taken and released on a contended cache line (fib_clntref) fib_table_lookup() and fib_semantic_match() get an additional parameter. struct fib_info gets an rcu_head field, and is freed after an rcu grace period. Stress test : (Sending 160.000.000 UDP frames on same neighbour, IP route cache disabled, dual E5540 @2.53GHz, 32bit kernel, FIB_HASH) (about same results for FIB_TRIE) Before patch : real 1m31.199s user 0m13.761s sys 23m24.780s After patch: real 1m5.375s user 0m14.997s sys 15m50.115s Before patch Profile : 13044.00 15.4% __ip_route_output_key vmlinux 8438.00 10.0% dst_destroy vmlinux 5983.00 7.1% fib_semantic_match vmlinux 5410.00 6.4% fib_rules_lookup vmlinux 4803.00 5.7% neigh_lookup vmlinux 4420.00 5.2% _raw_spin_lock vmlinux 3883.00 4.6% rt_set_nexthop vmlinux 3261.00 3.9% _raw_read_lock vmlinux 2794.00 3.3% fib_table_lookup vmlinux 2374.00 2.8% neigh_resolve_output vmlinux 2153.00 2.5% dst_alloc vmlinux 1502.00 1.8% _raw_read_lock_bh vmlinux 1484.00 1.8% kmem_cache_alloc vmlinux 1407.00 1.7% eth_header vmlinux 1406.00 1.7% ipv4_dst_destroy vmlinux 1298.00 1.5% __copy_from_user_ll vmlinux 1174.00 1.4% dev_queue_xmit vmlinux 1000.00 1.2% ip_output vmlinux After patch Profile : 13712.00 15.8% dst_destroy vmlinux 8548.00 9.9% __ip_route_output_key vmlinux 7017.00 8.1% neigh_lookup vmlinux 4554.00 5.3% fib_semantic_match vmlinux 4067.00 4.7% _raw_read_lock vmlinux 3491.00 4.0% dst_alloc vmlinux 3186.00 3.7% neigh_resolve_output vmlinux 3103.00 3.6% fib_table_lookup vmlinux 2098.00 2.4% _raw_read_lock_bh vmlinux 2081.00 2.4% kmem_cache_alloc vmlinux 2013.00 2.3% _raw_spin_lock vmlinux 1763.00 2.0% __copy_from_user_ll vmlinux 1763.00 2.0% ip_output vmlinux 1761.00 2.0% ipv4_dst_destroy vmlinux 1631.00 1.9% eth_header vmlinux 1440.00 1.7% _raw_read_unlock_bh vmlinux Reference results, if IP route cache is enabled : real 0m29.718s user 0m10.845s sys 7m37.341s 25213.00 29.5% __ip_route_output_key vmlinux 9011.00 10.5% dst_release vmlinux 4817.00 5.6% ip_push_pending_frames vmlinux 4232.00 5.0% ip_finish_output vmlinux 3940.00 4.6% udp_sendmsg vmlinux 3730.00 4.4% __copy_from_user_ll vmlinux 3716.00 4.4% ip_route_output_flow vmlinux 2451.00 2.9% __xfrm_lookup vmlinux 2221.00 2.6% ip_append_data vmlinux 1718.00 2.0% _raw_spin_lock_bh vmlinux 1655.00 1.9% __alloc_skb vmlinux 1572.00 1.8% sock_wfree vmlinux 1345.00 1.6% kfree vmlinux Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 18:41:36 +08:00
}
}
err = -EINVAL;
if (res.type != RTN_UNICAST && res.type != RTN_LOCAL)
goto out;
nh->nh_scope = res.scope;
nh->nh_oif = FIB_RES_OIF(res);
nh->nh_dev = dev = FIB_RES_DEV(res);
if (!dev)
goto out;
dev_hold(dev);
err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
} else {
struct in_device *in_dev;
if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK))
return -EINVAL;
rcu_read_lock();
err = -ENODEV;
in_dev = inetdev_by_index(net, nh->nh_oif);
if (in_dev == NULL)
goto out;
err = -ENETDOWN;
if (!(in_dev->dev->flags & IFF_UP))
goto out;
nh->nh_dev = in_dev->dev;
dev_hold(nh->nh_dev);
nh->nh_scope = RT_SCOPE_HOST;
err = 0;
}
out:
rcu_read_unlock();
return err;
}
static inline unsigned int fib_laddr_hashfn(__be32 val)
{
unsigned int mask = (fib_info_hash_size - 1);
return ((__force u32)val ^
((__force u32)val >> 7) ^
((__force u32)val >> 14)) & mask;
}
static struct hlist_head *fib_info_hash_alloc(int bytes)
{
if (bytes <= PAGE_SIZE)
return kzalloc(bytes, GFP_KERNEL);
else
return (struct hlist_head *)
__get_free_pages(GFP_KERNEL | __GFP_ZERO,
get_order(bytes));
}
static void fib_info_hash_free(struct hlist_head *hash, int bytes)
{
if (!hash)
return;
if (bytes <= PAGE_SIZE)
kfree(hash);
else
free_pages((unsigned long) hash, get_order(bytes));
}
static void fib_info_hash_move(struct hlist_head *new_info_hash,
struct hlist_head *new_laddrhash,
unsigned int new_size)
{
struct hlist_head *old_info_hash, *old_laddrhash;
unsigned int old_size = fib_info_hash_size;
unsigned int i, bytes;
spin_lock_bh(&fib_info_lock);
old_info_hash = fib_info_hash;
old_laddrhash = fib_info_laddrhash;
fib_info_hash_size = new_size;
for (i = 0; i < old_size; i++) {
struct hlist_head *head = &fib_info_hash[i];
struct hlist_node *node, *n;
struct fib_info *fi;
hlist_for_each_entry_safe(fi, node, n, head, fib_hash) {
struct hlist_head *dest;
unsigned int new_hash;
hlist_del(&fi->fib_hash);
new_hash = fib_info_hashfn(fi);
dest = &new_info_hash[new_hash];
hlist_add_head(&fi->fib_hash, dest);
}
}
fib_info_hash = new_info_hash;
for (i = 0; i < old_size; i++) {
struct hlist_head *lhead = &fib_info_laddrhash[i];
struct hlist_node *node, *n;
struct fib_info *fi;
hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) {
struct hlist_head *ldest;
unsigned int new_hash;
hlist_del(&fi->fib_lhash);
new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
ldest = &new_laddrhash[new_hash];
hlist_add_head(&fi->fib_lhash, ldest);
}
}
fib_info_laddrhash = new_laddrhash;
spin_unlock_bh(&fib_info_lock);
bytes = old_size * sizeof(struct hlist_head *);
fib_info_hash_free(old_info_hash, bytes);
fib_info_hash_free(old_laddrhash, bytes);
}
__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
{
nh->nh_saddr = inet_select_addr(nh->nh_dev,
nh->nh_gw,
nh->nh_parent->fib_scope);
nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
return nh->nh_saddr;
}
struct fib_info *fib_create_info(struct fib_config *cfg)
{
int err;
struct fib_info *fi = NULL;
struct fib_info *ofi;
int nhs = 1;
struct net *net = cfg->fc_nlinfo.nl_net;
if (cfg->fc_type > RTN_MAX)
goto err_inval;
/* Fast check to catch the most weird cases */
if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
goto err_inval;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (cfg->fc_mp) {
nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
if (nhs == 0)
goto err_inval;
}
#endif
err = -ENOBUFS;
if (fib_info_cnt >= fib_info_hash_size) {
unsigned int new_size = fib_info_hash_size << 1;
struct hlist_head *new_info_hash;
struct hlist_head *new_laddrhash;
unsigned int bytes;
if (!new_size)
new_size = 1;
bytes = new_size * sizeof(struct hlist_head *);
new_info_hash = fib_info_hash_alloc(bytes);
new_laddrhash = fib_info_hash_alloc(bytes);
if (!new_info_hash || !new_laddrhash) {
fib_info_hash_free(new_info_hash, bytes);
fib_info_hash_free(new_laddrhash, bytes);
} else
fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
if (!fib_info_hash_size)
goto failure;
}
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
if (fi == NULL)
goto failure;
if (cfg->fc_mx) {
fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
if (!fi->fib_metrics)
goto failure;
} else
fi->fib_metrics = (u32 *) dst_default_metrics;
fib_info_cnt++;
fi->fib_net = hold_net(net);
fi->fib_protocol = cfg->fc_protocol;
fi->fib_scope = cfg->fc_scope;
fi->fib_flags = cfg->fc_flags;
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
fi->fib_nhs = nhs;
change_nexthops(fi) {
nexthop_nh->nh_parent = fi;
} endfor_nexthops(fi)
if (cfg->fc_mx) {
struct nlattr *nla;
int remaining;
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
if (type) {
if (type > RTAX_MAX)
goto err_inval;
fi->fib_metrics[type - 1] = nla_get_u32(nla);
}
}
}
if (cfg->fc_mp) {
#ifdef CONFIG_IP_ROUTE_MULTIPATH
err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg);
if (err != 0)
goto failure;
if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif)
goto err_inval;
if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
goto err_inval;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
goto err_inval;
#endif
#else
goto err_inval;
#endif
} else {
struct fib_nh *nh = fi->fib_nh;
nh->nh_oif = cfg->fc_oif;
nh->nh_gw = cfg->fc_gw;
nh->nh_flags = cfg->fc_flags;
#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid = cfg->fc_flow;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight = 1;
#endif
}
if (fib_props[cfg->fc_type].error) {
if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
goto err_inval;
goto link_it;
} else {
switch (cfg->fc_type) {
case RTN_UNICAST:
case RTN_LOCAL:
case RTN_BROADCAST:
case RTN_ANYCAST:
case RTN_MULTICAST:
break;
default:
goto err_inval;
}
}
if (cfg->fc_scope > RT_SCOPE_HOST)
goto err_inval;
if (cfg->fc_scope == RT_SCOPE_HOST) {
struct fib_nh *nh = fi->fib_nh;
/* Local address is added. */
if (nhs != 1 || nh->nh_gw)
goto err_inval;
nh->nh_scope = RT_SCOPE_NOWHERE;
nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
err = -ENODEV;
if (nh->nh_dev == NULL)
goto failure;
} else {
change_nexthops(fi) {
err = fib_check_nh(cfg, fi, nexthop_nh);
if (err != 0)
goto failure;
} endfor_nexthops(fi)
}
if (fi->fib_prefsrc) {
if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
fi->fib_prefsrc != cfg->fc_dst)
if (inet_addr_type(net, fi->fib_prefsrc) != RTN_LOCAL)
goto err_inval;
}
change_nexthops(fi) {
fib_info_update_nh_saddr(net, nexthop_nh);
} endfor_nexthops(fi)
link_it:
ofi = fib_find_info(fi);
if (ofi) {
fi->fib_dead = 1;
free_fib_info(fi);
ofi->fib_treeref++;
return ofi;
}
fi->fib_treeref++;
atomic_inc(&fi->fib_clntref);
spin_lock_bh(&fib_info_lock);
hlist_add_head(&fi->fib_hash,
&fib_info_hash[fib_info_hashfn(fi)]);
if (fi->fib_prefsrc) {
struct hlist_head *head;
head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
hlist_add_head(&fi->fib_lhash, head);
}
change_nexthops(fi) {
struct hlist_head *head;
unsigned int hash;
if (!nexthop_nh->nh_dev)
continue;
hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
head = &fib_info_devhash[hash];
hlist_add_head(&nexthop_nh->nh_hash, head);
} endfor_nexthops(fi)
spin_unlock_bh(&fib_info_lock);
return fi;
err_inval:
err = -EINVAL;
failure:
if (fi) {
fi->fib_dead = 1;
free_fib_info(fi);
}
return ERR_PTR(err);
}
int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET;
rtm->rtm_dst_len = dst_len;
rtm->rtm_src_len = 0;
rtm->rtm_tos = tos;
if (tb_id < 256)
rtm->rtm_table = tb_id;
else
rtm->rtm_table = RT_TABLE_COMPAT;
NLA_PUT_U32(skb, RTA_TABLE, tb_id);
rtm->rtm_type = type;
rtm->rtm_flags = fi->fib_flags;
rtm->rtm_scope = fi->fib_scope;
rtm->rtm_protocol = fi->fib_protocol;
if (rtm->rtm_dst_len)
NLA_PUT_BE32(skb, RTA_DST, dst);
if (fi->fib_priority)
NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority);
if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
goto nla_put_failure;
if (fi->fib_prefsrc)
NLA_PUT_BE32(skb, RTA_PREFSRC, fi->fib_prefsrc);
if (fi->fib_nhs == 1) {
if (fi->fib_nh->nh_gw)
NLA_PUT_BE32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw);
if (fi->fib_nh->nh_oif)
NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (fi->fib_nh[0].nh_tclassid)
NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
#endif
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (fi->fib_nhs > 1) {
struct rtnexthop *rtnh;
struct nlattr *mp;
mp = nla_nest_start(skb, RTA_MULTIPATH);
if (mp == NULL)
goto nla_put_failure;
for_nexthops(fi) {
rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
if (rtnh == NULL)
goto nla_put_failure;
rtnh->rtnh_flags = nh->nh_flags & 0xFF;
rtnh->rtnh_hops = nh->nh_weight - 1;
rtnh->rtnh_ifindex = nh->nh_oif;
if (nh->nh_gw)
NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (nh->nh_tclassid)
NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
#endif
/* length of rtnetlink header + attributes */
rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
} endfor_nexthops(fi);
nla_nest_end(skb, mp);
}
#endif
return nlmsg_end(skb, nlh);
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
/*
* Update FIB if:
* - local address disappeared -> we must delete all the entries
* referring to it.
* - device went down -> we must shutdown all nexthops going via it.
*/
int fib_sync_down_addr(struct net *net, __be32 local)
{
int ret = 0;
unsigned int hash = fib_laddr_hashfn(local);
struct hlist_head *head = &fib_info_laddrhash[hash];
struct hlist_node *node;
struct fib_info *fi;
if (fib_info_laddrhash == NULL || local == 0)
return 0;
hlist_for_each_entry(fi, node, head, fib_lhash) {
if (!net_eq(fi->fib_net, net))
continue;
if (fi->fib_prefsrc == local) {
fi->fib_flags |= RTNH_F_DEAD;
ret++;
}
}
return ret;
}
int fib_sync_down_dev(struct net_device *dev, int force)
{
int ret = 0;
int scope = RT_SCOPE_NOWHERE;
struct fib_info *prev_fi = NULL;
unsigned int hash = fib_devindex_hashfn(dev->ifindex);
struct hlist_head *head = &fib_info_devhash[hash];
struct hlist_node *node;
struct fib_nh *nh;
if (force)
scope = -1;
hlist_for_each_entry(nh, node, head, nh_hash) {
struct fib_info *fi = nh->nh_parent;
int dead;
BUG_ON(!fi->fib_nhs);
if (nh->nh_dev != dev || fi == prev_fi)
continue;
prev_fi = fi;
dead = 0;
change_nexthops(fi) {
if (nexthop_nh->nh_flags & RTNH_F_DEAD)
dead++;
else if (nexthop_nh->nh_dev == dev &&
nexthop_nh->nh_scope != scope) {
nexthop_nh->nh_flags |= RTNH_F_DEAD;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
spin_lock_bh(&fib_multipath_lock);
fi->fib_power -= nexthop_nh->nh_power;
nexthop_nh->nh_power = 0;
spin_unlock_bh(&fib_multipath_lock);
#endif
dead++;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (force > 1 && nexthop_nh->nh_dev == dev) {
dead = fi->fib_nhs;
break;
}
#endif
} endfor_nexthops(fi)
if (dead == fi->fib_nhs) {
fi->fib_flags |= RTNH_F_DEAD;
ret++;
}
}
return ret;
}
/* Must be invoked inside of an RCU protected region. */
void fib_select_default(struct fib_result *res)
{
struct fib_info *fi = NULL, *last_resort = NULL;
struct list_head *fa_head = res->fa_head;
struct fib_table *tb = res->table;
int order = -1, last_idx = -1;
struct fib_alias *fa;
list_for_each_entry_rcu(fa, fa_head, fa_list) {
struct fib_info *next_fi = fa->fa_info;
if (next_fi->fib_scope != res->scope ||
fa->fa_type != RTN_UNICAST)
continue;
if (next_fi->fib_priority > res->fi->fib_priority)
break;
if (!next_fi->fib_nh[0].nh_gw ||
next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
continue;
fib_alias_accessed(fa);
if (fi == NULL) {
if (next_fi != res->fi)
break;
} else if (!fib_detect_death(fi, order, &last_resort,
&last_idx, tb->tb_default)) {
fib_result_assign(res, fi);
tb->tb_default = order;
goto out;
}
fi = next_fi;
order++;
}
if (order <= 0 || fi == NULL) {
tb->tb_default = -1;
goto out;
}
if (!fib_detect_death(fi, order, &last_resort, &last_idx,
tb->tb_default)) {
fib_result_assign(res, fi);
tb->tb_default = order;
goto out;
}
if (last_idx >= 0)
fib_result_assign(res, last_resort);
tb->tb_default = last_idx;
out:
return;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
/*
* Dead device goes up. We wake up dead nexthops.
* It takes sense only on multipath routes.
*/
int fib_sync_up(struct net_device *dev)
{
struct fib_info *prev_fi;
unsigned int hash;
struct hlist_head *head;
struct hlist_node *node;
struct fib_nh *nh;
int ret;
if (!(dev->flags & IFF_UP))
return 0;
prev_fi = NULL;
hash = fib_devindex_hashfn(dev->ifindex);
head = &fib_info_devhash[hash];
ret = 0;
hlist_for_each_entry(nh, node, head, nh_hash) {
struct fib_info *fi = nh->nh_parent;
int alive;
BUG_ON(!fi->fib_nhs);
if (nh->nh_dev != dev || fi == prev_fi)
continue;
prev_fi = fi;
alive = 0;
change_nexthops(fi) {
if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) {
alive++;
continue;
}
if (nexthop_nh->nh_dev == NULL ||
!(nexthop_nh->nh_dev->flags & IFF_UP))
continue;
if (nexthop_nh->nh_dev != dev ||
!__in_dev_get_rtnl(dev))
continue;
alive++;
spin_lock_bh(&fib_multipath_lock);
nexthop_nh->nh_power = 0;
nexthop_nh->nh_flags &= ~RTNH_F_DEAD;
spin_unlock_bh(&fib_multipath_lock);
} endfor_nexthops(fi)
if (alive > 0) {
fi->fib_flags &= ~RTNH_F_DEAD;
ret++;
}
}
return ret;
}
/*
* The algorithm is suboptimal, but it provides really
* fair weighted route distribution.
*/
void fib_select_multipath(struct fib_result *res)
{
struct fib_info *fi = res->fi;
int w;
spin_lock_bh(&fib_multipath_lock);
if (fi->fib_power <= 0) {
int power = 0;
change_nexthops(fi) {
if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) {
power += nexthop_nh->nh_weight;
nexthop_nh->nh_power = nexthop_nh->nh_weight;
}
} endfor_nexthops(fi);
fi->fib_power = power;
if (power <= 0) {
spin_unlock_bh(&fib_multipath_lock);
/* Race condition: route has just become dead. */
res->nh_sel = 0;
return;
}
}
/* w should be random number [0..fi->fib_power-1],
* it is pretty bad approximation.
*/
w = jiffies % fi->fib_power;
change_nexthops(fi) {
if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) &&
nexthop_nh->nh_power) {
w -= nexthop_nh->nh_power;
if (w <= 0) {
nexthop_nh->nh_power--;
fi->fib_power--;
res->nh_sel = nhsel;
spin_unlock_bh(&fib_multipath_lock);
return;
}
}
} endfor_nexthops(fi);
/* Race condition: route has just become dead. */
res->nh_sel = 0;
spin_unlock_bh(&fib_multipath_lock);
}
#endif