linux_old1/net/ipv4/fib_frontend.c

1114 lines
25 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: FIB frontend.
*
* 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 <linux/module.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/types.h>
#include <linux/kernel.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_addr.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/list.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/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#ifndef CONFIG_IP_MULTIPLE_TABLES
static int __net_init fib4_rules_init(struct net *net)
{
struct fib_table *local_table, *main_table;
local_table = fib_hash_table(RT_TABLE_LOCAL);
if (local_table == NULL)
return -ENOMEM;
main_table = fib_hash_table(RT_TABLE_MAIN);
if (main_table == NULL)
goto fail;
hlist_add_head_rcu(&local_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
hlist_add_head_rcu(&main_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
return 0;
fail:
kfree(local_table);
return -ENOMEM;
}
#else
struct fib_table *fib_new_table(struct net *net, u32 id)
{
struct fib_table *tb;
unsigned int h;
if (id == 0)
id = RT_TABLE_MAIN;
tb = fib_get_table(net, id);
if (tb)
return tb;
tb = fib_hash_table(id);
if (!tb)
return NULL;
h = id & (FIB_TABLE_HASHSZ - 1);
hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]);
return tb;
}
struct fib_table *fib_get_table(struct net *net, u32 id)
{
struct fib_table *tb;
struct hlist_node *node;
struct hlist_head *head;
unsigned int h;
if (id == 0)
id = RT_TABLE_MAIN;
h = id & (FIB_TABLE_HASHSZ - 1);
rcu_read_lock();
head = &net->ipv4.fib_table_hash[h];
hlist_for_each_entry_rcu(tb, node, head, tb_hlist) {
if (tb->tb_id == id) {
rcu_read_unlock();
return tb;
}
}
rcu_read_unlock();
return NULL;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */
void fib_select_default(struct net *net,
const struct flowi *flp, struct fib_result *res)
{
struct fib_table *tb;
int table = RT_TABLE_MAIN;
#ifdef CONFIG_IP_MULTIPLE_TABLES
if (res->r == NULL || res->r->action != FR_ACT_TO_TBL)
return;
table = res->r->table;
#endif
tb = fib_get_table(net, table);
if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
fib_table_select_default(tb, flp, res);
}
static void fib_flush(struct net *net)
{
int flushed = 0;
struct fib_table *tb;
struct hlist_node *node;
struct hlist_head *head;
unsigned int h;
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
head = &net->ipv4.fib_table_hash[h];
hlist_for_each_entry(tb, node, head, tb_hlist)
flushed += fib_table_flush(tb);
}
if (flushed)
rt_cache_flush(net, -1);
}
/**
* __ip_dev_find - find the first device with a given source address.
* @net: the net namespace
* @addr: the source address
* @devref: if true, take a reference on the found device
*
* If a caller uses devref=false, it should be protected by RCU, or RTNL
*/
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
{
struct flowi fl = {
.nl_u = {
.ip4_u = {
.daddr = addr
}
},
};
struct fib_result res = { 0 };
struct net_device *dev = NULL;
struct fib_table *local_table;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
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();
local_table = fib_get_table(net, RT_TABLE_LOCAL);
if (!local_table ||
fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) {
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_unlock();
return NULL;
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 (res.type != RTN_LOCAL)
goto out;
dev = FIB_RES_DEV(res);
if (dev && devref)
dev_hold(dev);
out:
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_unlock();
return dev;
}
EXPORT_SYMBOL(__ip_dev_find);
/*
* Find address type as if only "dev" was present in the system. If
* on_dev is NULL then all interfaces are taken into consideration.
*/
static inline unsigned __inet_dev_addr_type(struct net *net,
const struct net_device *dev,
__be32 addr)
{
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
struct fib_result res;
unsigned ret = RTN_BROADCAST;
struct fib_table *local_table;
if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
return RTN_BROADCAST;
if (ipv4_is_multicast(addr))
return RTN_MULTICAST;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
local_table = fib_get_table(net, RT_TABLE_LOCAL);
if (local_table) {
ret = RTN_UNICAST;
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();
if (!fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) {
if (!dev || dev == res.fi->fib_dev)
ret = res.type;
}
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_unlock();
}
return ret;
}
unsigned int inet_addr_type(struct net *net, __be32 addr)
{
return __inet_dev_addr_type(net, NULL, addr);
}
EXPORT_SYMBOL(inet_addr_type);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr)
{
return __inet_dev_addr_type(net, dev, addr);
}
EXPORT_SYMBOL(inet_dev_addr_type);
/* Given (packet source, input interface) and optional (dst, oif, tos):
* - (main) check, that source is valid i.e. not broadcast or our local
* address.
* - figure out what "logical" interface this packet arrived
* and calculate "specific destination" address.
* - check, that packet arrived from expected physical interface.
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
* called with rcu_read_lock()
*/
int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
struct net_device *dev, __be32 *spec_dst,
u32 *itag, u32 mark)
{
struct in_device *in_dev;
struct flowi fl = {
.nl_u = {
.ip4_u = {
.daddr = src,
.saddr = dst,
.tos = tos
}
},
.mark = mark,
.iif = oif
};
struct fib_result res;
int no_addr, rpf, accept_local;
bool dev_match;
int ret;
struct net *net;
no_addr = rpf = accept_local = 0;
in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
no_addr = in_dev->ifa_list == NULL;
rpf = IN_DEV_RPFILTER(in_dev);
accept_local = IN_DEV_ACCEPT_LOCAL(in_dev);
if (mark && !IN_DEV_SRC_VMARK(in_dev))
fl.mark = 0;
}
if (in_dev == NULL)
goto e_inval;
net = dev_net(dev);
if (fib_lookup(net, &fl, &res))
goto last_resort;
if (res.type != RTN_UNICAST) {
if (res.type != RTN_LOCAL || !accept_local)
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
goto e_inval;
}
*spec_dst = FIB_RES_PREFSRC(res);
fib_combine_itag(itag, &res);
dev_match = false;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
for (ret = 0; ret < res.fi->fib_nhs; ret++) {
struct fib_nh *nh = &res.fi->fib_nh[ret];
if (nh->nh_dev == dev) {
dev_match = true;
break;
}
}
#else
if (FIB_RES_DEV(res) == dev)
dev_match = true;
#endif
if (dev_match) {
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
return ret;
}
if (no_addr)
goto last_resort;
if (rpf == 1)
goto e_rpf;
fl.oif = dev->ifindex;
ret = 0;
if (fib_lookup(net, &fl, &res) == 0) {
if (res.type == RTN_UNICAST) {
*spec_dst = FIB_RES_PREFSRC(res);
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
}
}
return ret;
last_resort:
if (rpf)
goto e_rpf;
*spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
*itag = 0;
return 0;
e_inval:
return -EINVAL;
e_rpf:
return -EXDEV;
}
static inline __be32 sk_extract_addr(struct sockaddr *addr)
{
return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
}
static int put_rtax(struct nlattr *mx, int len, int type, u32 value)
{
struct nlattr *nla;
nla = (struct nlattr *) ((char *) mx + len);
nla->nla_type = type;
nla->nla_len = nla_attr_size(4);
*(u32 *) nla_data(nla) = value;
return len + nla_total_size(4);
}
static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
struct fib_config *cfg)
{
__be32 addr;
int plen;
memset(cfg, 0, sizeof(*cfg));
cfg->fc_nlinfo.nl_net = net;
if (rt->rt_dst.sa_family != AF_INET)
return -EAFNOSUPPORT;
/*
* Check mask for validity:
* a) it must be contiguous.
* b) destination must have all host bits clear.
* c) if application forgot to set correct family (AF_INET),
* reject request unless it is absolutely clear i.e.
* both family and mask are zero.
*/
plen = 32;
addr = sk_extract_addr(&rt->rt_dst);
if (!(rt->rt_flags & RTF_HOST)) {
__be32 mask = sk_extract_addr(&rt->rt_genmask);
if (rt->rt_genmask.sa_family != AF_INET) {
if (mask || rt->rt_genmask.sa_family)
return -EAFNOSUPPORT;
}
if (bad_mask(mask, addr))
return -EINVAL;
plen = inet_mask_len(mask);
}
cfg->fc_dst_len = plen;
cfg->fc_dst = addr;
if (cmd != SIOCDELRT) {
cfg->fc_nlflags = NLM_F_CREATE;
cfg->fc_protocol = RTPROT_BOOT;
}
if (rt->rt_metric)
cfg->fc_priority = rt->rt_metric - 1;
if (rt->rt_flags & RTF_REJECT) {
cfg->fc_scope = RT_SCOPE_HOST;
cfg->fc_type = RTN_UNREACHABLE;
return 0;
}
cfg->fc_scope = RT_SCOPE_NOWHERE;
cfg->fc_type = RTN_UNICAST;
if (rt->rt_dev) {
char *colon;
struct net_device *dev;
char devname[IFNAMSIZ];
if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1))
return -EFAULT;
devname[IFNAMSIZ-1] = 0;
colon = strchr(devname, ':');
if (colon)
*colon = 0;
dev = __dev_get_by_name(net, devname);
if (!dev)
return -ENODEV;
cfg->fc_oif = dev->ifindex;
if (colon) {
struct in_ifaddr *ifa;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
if (!in_dev)
return -ENODEV;
*colon = ':';
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
if (strcmp(ifa->ifa_label, devname) == 0)
break;
if (ifa == NULL)
return -ENODEV;
cfg->fc_prefsrc = ifa->ifa_local;
}
}
addr = sk_extract_addr(&rt->rt_gateway);
if (rt->rt_gateway.sa_family == AF_INET && addr) {
cfg->fc_gw = addr;
if (rt->rt_flags & RTF_GATEWAY &&
inet_addr_type(net, addr) == RTN_UNICAST)
cfg->fc_scope = RT_SCOPE_UNIVERSE;
}
if (cmd == SIOCDELRT)
return 0;
if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw)
return -EINVAL;
if (cfg->fc_scope == RT_SCOPE_NOWHERE)
cfg->fc_scope = RT_SCOPE_LINK;
if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) {
struct nlattr *mx;
int len = 0;
mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL);
if (mx == NULL)
return -ENOMEM;
if (rt->rt_flags & RTF_MTU)
len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40);
if (rt->rt_flags & RTF_WINDOW)
len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window);
if (rt->rt_flags & RTF_IRTT)
len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3);
cfg->fc_mx = mx;
cfg->fc_mx_len = len;
}
return 0;
}
/*
* Handle IP routing ioctl calls.
* These are used to manipulate the routing tables
*/
int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct fib_config cfg;
struct rtentry rt;
int err;
switch (cmd) {
case SIOCADDRT: /* Add a route */
case SIOCDELRT: /* Delete a route */
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (copy_from_user(&rt, arg, sizeof(rt)))
return -EFAULT;
rtnl_lock();
err = rtentry_to_fib_config(net, cmd, &rt, &cfg);
if (err == 0) {
struct fib_table *tb;
if (cmd == SIOCDELRT) {
tb = fib_get_table(net, cfg.fc_table);
if (tb)
err = fib_table_delete(tb, &cfg);
else
err = -ESRCH;
} else {
tb = fib_new_table(net, cfg.fc_table);
if (tb)
err = fib_table_insert(tb, &cfg);
else
err = -ENOBUFS;
}
/* allocated by rtentry_to_fib_config() */
kfree(cfg.fc_mx);
}
rtnl_unlock();
return err;
}
return -EINVAL;
}
const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_DST] = { .type = NLA_U32 },
[RTA_SRC] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_GATEWAY] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_PREFSRC] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_FLOW] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
struct nlmsghdr *nlh, struct fib_config *cfg)
{
struct nlattr *attr;
int err, remaining;
struct rtmsg *rtm;
err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy);
if (err < 0)
goto errout;
memset(cfg, 0, sizeof(*cfg));
rtm = nlmsg_data(nlh);
cfg->fc_dst_len = rtm->rtm_dst_len;
cfg->fc_tos = rtm->rtm_tos;
cfg->fc_table = rtm->rtm_table;
cfg->fc_protocol = rtm->rtm_protocol;
cfg->fc_scope = rtm->rtm_scope;
cfg->fc_type = rtm->rtm_type;
cfg->fc_flags = rtm->rtm_flags;
cfg->fc_nlflags = nlh->nlmsg_flags;
cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = net;
if (cfg->fc_type > RTN_MAX) {
err = -EINVAL;
goto errout;
}
nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
switch (nla_type(attr)) {
case RTA_DST:
cfg->fc_dst = nla_get_be32(attr);
break;
case RTA_OIF:
cfg->fc_oif = nla_get_u32(attr);
break;
case RTA_GATEWAY:
cfg->fc_gw = nla_get_be32(attr);
break;
case RTA_PRIORITY:
cfg->fc_priority = nla_get_u32(attr);
break;
case RTA_PREFSRC:
cfg->fc_prefsrc = nla_get_be32(attr);
break;
case RTA_METRICS:
cfg->fc_mx = nla_data(attr);
cfg->fc_mx_len = nla_len(attr);
break;
case RTA_MULTIPATH:
cfg->fc_mp = nla_data(attr);
cfg->fc_mp_len = nla_len(attr);
break;
case RTA_FLOW:
cfg->fc_flow = nla_get_u32(attr);
break;
case RTA_TABLE:
cfg->fc_table = nla_get_u32(attr);
break;
}
}
return 0;
errout:
return err;
}
static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
struct fib_table *tb;
int err;
err = rtm_to_fib_config(net, skb, nlh, &cfg);
if (err < 0)
goto errout;
tb = fib_get_table(net, cfg.fc_table);
if (tb == NULL) {
err = -ESRCH;
goto errout;
}
err = fib_table_delete(tb, &cfg);
errout:
return err;
}
static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
struct fib_table *tb;
int err;
err = rtm_to_fib_config(net, skb, nlh, &cfg);
if (err < 0)
goto errout;
tb = fib_new_table(net, cfg.fc_table);
if (tb == NULL) {
err = -ENOBUFS;
goto errout;
}
err = fib_table_insert(tb, &cfg);
errout:
return err;
}
static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
struct fib_table *tb;
struct hlist_node *node;
struct hlist_head *head;
int dumped = 0;
if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
return ip_rt_dump(skb, cb);
s_h = cb->args[0];
s_e = cb->args[1];
for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
e = 0;
head = &net->ipv4.fib_table_hash[h];
hlist_for_each_entry(tb, node, head, tb_hlist) {
if (e < s_e)
goto next;
if (dumped)
memset(&cb->args[2], 0, sizeof(cb->args) -
2 * sizeof(cb->args[0]));
if (fib_table_dump(tb, skb, cb) < 0)
goto out;
dumped = 1;
next:
e++;
}
}
out:
cb->args[1] = e;
cb->args[0] = h;
return skb->len;
}
/* Prepare and feed intra-kernel routing request.
* Really, it should be netlink message, but :-( netlink
* can be not configured, so that we feed it directly
* to fib engine. It is legal, because all events occur
* only when netlink is already locked.
*/
static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
{
struct net *net = dev_net(ifa->ifa_dev->dev);
struct fib_table *tb;
struct fib_config cfg = {
.fc_protocol = RTPROT_KERNEL,
.fc_type = type,
.fc_dst = dst,
.fc_dst_len = dst_len,
.fc_prefsrc = ifa->ifa_local,
.fc_oif = ifa->ifa_dev->dev->ifindex,
.fc_nlflags = NLM_F_CREATE | NLM_F_APPEND,
.fc_nlinfo = {
.nl_net = net,
},
};
if (type == RTN_UNICAST)
tb = fib_new_table(net, RT_TABLE_MAIN);
else
tb = fib_new_table(net, RT_TABLE_LOCAL);
if (tb == NULL)
return;
cfg.fc_table = tb->tb_id;
if (type != RTN_LOCAL)
cfg.fc_scope = RT_SCOPE_LINK;
else
cfg.fc_scope = RT_SCOPE_HOST;
if (cmd == RTM_NEWROUTE)
fib_table_insert(tb, &cfg);
else
fib_table_delete(tb, &cfg);
}
void fib_add_ifaddr(struct in_ifaddr *ifa)
{
struct in_device *in_dev = ifa->ifa_dev;
struct net_device *dev = in_dev->dev;
struct in_ifaddr *prim = ifa;
__be32 mask = ifa->ifa_mask;
__be32 addr = ifa->ifa_local;
__be32 prefix = ifa->ifa_address & mask;
if (ifa->ifa_flags & IFA_F_SECONDARY) {
prim = inet_ifa_byprefix(in_dev, prefix, mask);
if (prim == NULL) {
printk(KERN_WARNING "fib_add_ifaddr: bug: prim == NULL\n");
return;
}
}
fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim);
if (!(dev->flags & IFF_UP))
return;
/* Add broadcast address, if it is explicitly assigned. */
if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
(prefix != addr || ifa->ifa_prefixlen < 32)) {
fib_magic(RTM_NEWROUTE,
dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
prefix, ifa->ifa_prefixlen, prim);
/* Add network specific broadcasts, when it takes a sense */
if (ifa->ifa_prefixlen < 31) {
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim);
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
32, prim);
}
}
}
static void fib_del_ifaddr(struct in_ifaddr *ifa)
{
struct in_device *in_dev = ifa->ifa_dev;
struct net_device *dev = in_dev->dev;
struct in_ifaddr *ifa1;
struct in_ifaddr *prim = ifa;
__be32 brd = ifa->ifa_address | ~ifa->ifa_mask;
__be32 any = ifa->ifa_address & ifa->ifa_mask;
#define LOCAL_OK 1
#define BRD_OK 2
#define BRD0_OK 4
#define BRD1_OK 8
unsigned ok = 0;
if (!(ifa->ifa_flags & IFA_F_SECONDARY))
fib_magic(RTM_DELROUTE,
dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
any, ifa->ifa_prefixlen, prim);
else {
prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
if (prim == NULL) {
printk(KERN_WARNING "fib_del_ifaddr: bug: prim == NULL\n");
return;
}
}
/* Deletion is more complicated than add.
* We should take care of not to delete too much :-)
*
* Scan address list to be sure that addresses are really gone.
*/
for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
if (ifa->ifa_local == ifa1->ifa_local)
ok |= LOCAL_OK;
if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
ok |= BRD_OK;
if (brd == ifa1->ifa_broadcast)
ok |= BRD1_OK;
if (any == ifa1->ifa_broadcast)
ok |= BRD0_OK;
}
if (!(ok & BRD_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
if (!(ok & BRD1_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
if (!(ok & BRD0_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
if (!(ok & LOCAL_OK)) {
fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
/* Check, that this local address finally disappeared. */
if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) {
/* And the last, but not the least thing.
* We must flush stray FIB entries.
*
* First of all, we scan fib_info list searching
* for stray nexthop entries, then ignite fib_flush.
*/
if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local))
fib_flush(dev_net(dev));
}
}
#undef LOCAL_OK
#undef BRD_OK
#undef BRD0_OK
#undef BRD1_OK
}
static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
{
struct fib_result res;
struct flowi fl = {
.mark = frn->fl_mark,
.nl_u = {
.ip4_u = {
.daddr = frn->fl_addr,
.tos = frn->fl_tos,
.scope = frn->fl_scope
}
}
};
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
frn->err = -ENOENT;
if (tb) {
local_bh_disable();
frn->tb_id = tb->tb_id;
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();
frn->err = fib_table_lookup(tb, &fl, &res, FIB_LOOKUP_NOREF);
if (!frn->err) {
frn->prefixlen = res.prefixlen;
frn->nh_sel = res.nh_sel;
frn->type = res.type;
frn->scope = res.scope;
}
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_unlock();
local_bh_enable();
}
}
static void nl_fib_input(struct sk_buff *skb)
{
struct net *net;
struct fib_result_nl *frn;
struct nlmsghdr *nlh;
struct fib_table *tb;
u32 pid;
net = sock_net(skb->sk);
nlh = nlmsg_hdr(skb);
if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len ||
nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn)))
return;
skb = skb_clone(skb, GFP_KERNEL);
if (skb == NULL)
return;
nlh = nlmsg_hdr(skb);
frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
tb = fib_get_table(net, frn->tb_id_in);
nl_fib_lookup(frn, tb);
pid = NETLINK_CB(skb).pid; /* pid of sending process */
NETLINK_CB(skb).pid = 0; /* from kernel */
NETLINK_CB(skb).dst_group = 0; /* unicast */
netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT);
}
static int __net_init nl_fib_lookup_init(struct net *net)
{
struct sock *sk;
sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0,
nl_fib_input, NULL, THIS_MODULE);
if (sk == NULL)
return -EAFNOSUPPORT;
net->ipv4.fibnl = sk;
return 0;
}
static void nl_fib_lookup_exit(struct net *net)
{
netlink_kernel_release(net->ipv4.fibnl);
net->ipv4.fibnl = NULL;
}
static void fib_disable_ip(struct net_device *dev, int force, int delay)
{
if (fib_sync_down_dev(dev, force))
fib_flush(dev_net(dev));
rt_cache_flush(dev_net(dev), delay);
arp_ifdown(dev);
}
static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
struct net_device *dev = ifa->ifa_dev->dev;
switch (event) {
case NETDEV_UP:
fib_add_ifaddr(ifa);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev);
#endif
rt_cache_flush(dev_net(dev), -1);
break;
case NETDEV_DOWN:
fib_del_ifaddr(ifa);
if (ifa->ifa_dev->ifa_list == NULL) {
/* Last address was deleted from this interface.
* Disable IP.
*/
fib_disable_ip(dev, 1, 0);
} else {
rt_cache_flush(dev_net(dev), -1);
}
break;
}
return NOTIFY_DONE;
}
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
if (event == NETDEV_UNREGISTER) {
fib_disable_ip(dev, 2, -1);
return NOTIFY_DONE;
}
if (!in_dev)
return NOTIFY_DONE;
switch (event) {
case NETDEV_UP:
for_ifa(in_dev) {
fib_add_ifaddr(ifa);
} endfor_ifa(in_dev);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev);
#endif
rt_cache_flush(dev_net(dev), -1);
break;
case NETDEV_DOWN:
fib_disable_ip(dev, 0, 0);
break;
case NETDEV_CHANGEMTU:
case NETDEV_CHANGE:
rt_cache_flush(dev_net(dev), 0);
break;
case NETDEV_UNREGISTER_BATCH:
rt_cache_flush_batch();
break;
}
return NOTIFY_DONE;
}
static struct notifier_block fib_inetaddr_notifier = {
.notifier_call = fib_inetaddr_event,
};
static struct notifier_block fib_netdev_notifier = {
.notifier_call = fib_netdev_event,
};
static int __net_init ip_fib_net_init(struct net *net)
{
int err;
size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ;
/* Avoid false sharing : Use at least a full cache line */
size = max_t(size_t, size, L1_CACHE_BYTES);
net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL);
if (net->ipv4.fib_table_hash == NULL)
return -ENOMEM;
err = fib4_rules_init(net);
if (err < 0)
goto fail;
return 0;
fail:
kfree(net->ipv4.fib_table_hash);
return err;
}
static void ip_fib_net_exit(struct net *net)
{
unsigned int i;
#ifdef CONFIG_IP_MULTIPLE_TABLES
fib4_rules_exit(net);
#endif
for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
struct fib_table *tb;
struct hlist_head *head;
struct hlist_node *node, *tmp;
head = &net->ipv4.fib_table_hash[i];
hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) {
hlist_del(node);
fib_table_flush(tb);
fib_free_table(tb);
}
}
kfree(net->ipv4.fib_table_hash);
}
static int __net_init fib_net_init(struct net *net)
{
int error;
error = ip_fib_net_init(net);
if (error < 0)
goto out;
error = nl_fib_lookup_init(net);
if (error < 0)
goto out_nlfl;
error = fib_proc_init(net);
if (error < 0)
goto out_proc;
out:
return error;
out_proc:
nl_fib_lookup_exit(net);
out_nlfl:
ip_fib_net_exit(net);
goto out;
}
static void __net_exit fib_net_exit(struct net *net)
{
fib_proc_exit(net);
nl_fib_lookup_exit(net);
ip_fib_net_exit(net);
}
static struct pernet_operations fib_net_ops = {
.init = fib_net_init,
.exit = fib_net_exit,
};
void __init ip_fib_init(void)
{
rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL);
rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL);
rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib);
register_pernet_subsys(&fib_net_ops);
register_netdevice_notifier(&fib_netdev_notifier);
register_inetaddr_notifier(&fib_inetaddr_notifier);
fib_hash_init();
}