linux/net/ipv6/fib6_rules.c

507 lines
12 KiB
C
Raw Normal View History

/*
* net/ipv6/fib6_rules.c IPv6 Routing Policy Rules
*
* Copyright (C)2003-2006 Helsinki University of Technology
* Copyright (C)2003-2006 USAGI/WIDE Project
*
* 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, version 2.
*
* Authors
* Thomas Graf <tgraf@suug.ch>
* Ville Nuorvala <vnuorval@tcs.hut.fi>
*/
#include <linux/netdevice.h>
#include <linux/notifier.h>
#include <linux/export.h>
#include <net/fib_rules.h>
#include <net/ipv6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/netlink.h>
struct fib6_rule {
struct fib_rule common;
struct rt6key src;
struct rt6key dst;
u8 tclass;
};
static bool fib6_rule_matchall(const struct fib_rule *rule)
{
struct fib6_rule *r = container_of(rule, struct fib6_rule, common);
if (r->dst.plen || r->src.plen || r->tclass)
return false;
return fib_rule_matchall(rule);
}
bool fib6_rule_default(const struct fib_rule *rule)
{
if (!fib6_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
rule->l3mdev)
return false;
if (rule->table != RT6_TABLE_LOCAL && rule->table != RT6_TABLE_MAIN)
return false;
return true;
}
EXPORT_SYMBOL_GPL(fib6_rule_default);
int fib6_rules_dump(struct net *net, struct notifier_block *nb)
{
return fib_rules_dump(net, nb, AF_INET6);
}
unsigned int fib6_rules_seq_read(struct net *net)
{
return fib_rules_seq_read(net, AF_INET6);
}
/* called with rcu lock held; no reference taken on fib6_info */
struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
int flags)
{
struct fib6_info *f6i;
int err;
if (net->ipv6.fib6_has_custom_rules) {
struct fib_lookup_arg arg = {
.lookup_ptr = fib6_table_lookup,
.lookup_data = &oif,
.flags = FIB_LOOKUP_NOREF,
};
l3mdev_update_flow(net, flowi6_to_flowi(fl6));
err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
flowi6_to_flowi(fl6), flags, &arg);
if (err)
return ERR_PTR(err);
f6i = arg.result ? : net->ipv6.fib6_null_entry;
} else {
f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl,
oif, fl6, flags);
if (!f6i || f6i == net->ipv6.fib6_null_entry)
f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
oif, fl6, flags);
}
return f6i;
}
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
const struct sk_buff *skb,
int flags, pol_lookup_t lookup)
{
net: ipv6: avoid overhead when no custom FIB rules are installed If the user hasn't installed any custom rules, don't go through the whole FIB rules layer. This is pretty similar to f4530fa574df (ipv4: Avoid overhead when no custom FIB rules are installed). Using a micro-benchmark module [1], timing ip6_route_output() with get_cycles(), with 40,000 routes in the main routing table, before this patch: min=606 max=12911 count=627 average=1959 95th=4903 90th=3747 50th=1602 mad=821 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 600 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 199 880 │▒▒▒░░░░░░░░░░░░░░░░ 43 1160 │▒▒▒░░░░░░░░░░░░░░░░░░░░ 48 1440 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░ 43 1720 │▒▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░ 59 2000 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 50 2280 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2560 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 31 2840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 28 3120 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3400 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3680 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3960 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 11 4240 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4520 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4800 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 After: min=544 max=11687 count=627 average=1776 95th=4546 90th=3585 50th=1227 mad=565 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 540 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 201 800 │▒▒▒▒▒░░░░░░░░░░░░░░░░ 63 1060 │▒▒▒▒▒░░░░░░░░░░░░░░░░░░░░░ 68 1320 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░ 39 1580 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 1840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 2100 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 34 2360 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 33 2620 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2880 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 22 3140 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3400 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3660 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3920 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4180 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4440 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 At the frequency of the host during the bench (~ 3.7 GHz), this is about a 100 ns difference on the median value. A next step would be to collapse local and main tables, as in 0ddcf43d5d4a (ipv4: FIB Local/MAIN table collapse). [1]: https://github.com/vincentbernat/network-lab/blob/master/lab-routes-ipv6/kbench_mod.c Signed-off-by: Vincent Bernat <vincent@bernat.im> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-08 18:23:49 +00:00
if (net->ipv6.fib6_has_custom_rules) {
struct fib_lookup_arg arg = {
.lookup_ptr = lookup,
.lookup_data = skb,
net: ipv6: avoid overhead when no custom FIB rules are installed If the user hasn't installed any custom rules, don't go through the whole FIB rules layer. This is pretty similar to f4530fa574df (ipv4: Avoid overhead when no custom FIB rules are installed). Using a micro-benchmark module [1], timing ip6_route_output() with get_cycles(), with 40,000 routes in the main routing table, before this patch: min=606 max=12911 count=627 average=1959 95th=4903 90th=3747 50th=1602 mad=821 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 600 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 199 880 │▒▒▒░░░░░░░░░░░░░░░░ 43 1160 │▒▒▒░░░░░░░░░░░░░░░░░░░░ 48 1440 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░ 43 1720 │▒▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░ 59 2000 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 50 2280 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2560 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 31 2840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 28 3120 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3400 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3680 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3960 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 11 4240 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4520 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4800 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 After: min=544 max=11687 count=627 average=1776 95th=4546 90th=3585 50th=1227 mad=565 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 540 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 201 800 │▒▒▒▒▒░░░░░░░░░░░░░░░░ 63 1060 │▒▒▒▒▒░░░░░░░░░░░░░░░░░░░░░ 68 1320 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░ 39 1580 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 1840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 2100 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 34 2360 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 33 2620 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2880 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 22 3140 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3400 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3660 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3920 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4180 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4440 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 At the frequency of the host during the bench (~ 3.7 GHz), this is about a 100 ns difference on the median value. A next step would be to collapse local and main tables, as in 0ddcf43d5d4a (ipv4: FIB Local/MAIN table collapse). [1]: https://github.com/vincentbernat/network-lab/blob/master/lab-routes-ipv6/kbench_mod.c Signed-off-by: Vincent Bernat <vincent@bernat.im> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-08 18:23:49 +00:00
.flags = FIB_LOOKUP_NOREF,
};
/* update flow if oif or iif point to device enslaved to l3mdev */
l3mdev_update_flow(net, flowi6_to_flowi(fl6));
fib_rules_lookup(net->ipv6.fib6_rules_ops,
flowi6_to_flowi(fl6), flags, &arg);
if (arg.result)
return arg.result;
} else {
struct rt6_info *rt;
rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, skb, flags);
net: ipv6: avoid overhead when no custom FIB rules are installed If the user hasn't installed any custom rules, don't go through the whole FIB rules layer. This is pretty similar to f4530fa574df (ipv4: Avoid overhead when no custom FIB rules are installed). Using a micro-benchmark module [1], timing ip6_route_output() with get_cycles(), with 40,000 routes in the main routing table, before this patch: min=606 max=12911 count=627 average=1959 95th=4903 90th=3747 50th=1602 mad=821 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 600 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 199 880 │▒▒▒░░░░░░░░░░░░░░░░ 43 1160 │▒▒▒░░░░░░░░░░░░░░░░░░░░ 48 1440 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░ 43 1720 │▒▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░ 59 2000 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 50 2280 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2560 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 31 2840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 28 3120 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3400 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3680 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3960 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 11 4240 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4520 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4800 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 After: min=544 max=11687 count=627 average=1776 95th=4546 90th=3585 50th=1227 mad=565 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 540 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 201 800 │▒▒▒▒▒░░░░░░░░░░░░░░░░ 63 1060 │▒▒▒▒▒░░░░░░░░░░░░░░░░░░░░░ 68 1320 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░ 39 1580 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 1840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 2100 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 34 2360 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 33 2620 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2880 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 22 3140 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3400 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3660 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3920 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4180 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4440 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 At the frequency of the host during the bench (~ 3.7 GHz), this is about a 100 ns difference on the median value. A next step would be to collapse local and main tables, as in 0ddcf43d5d4a (ipv4: FIB Local/MAIN table collapse). [1]: https://github.com/vincentbernat/network-lab/blob/master/lab-routes-ipv6/kbench_mod.c Signed-off-by: Vincent Bernat <vincent@bernat.im> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-08 18:23:49 +00:00
if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN)
return &rt->dst;
ip6_rt_put(rt);
rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
net: ipv6: avoid overhead when no custom FIB rules are installed If the user hasn't installed any custom rules, don't go through the whole FIB rules layer. This is pretty similar to f4530fa574df (ipv4: Avoid overhead when no custom FIB rules are installed). Using a micro-benchmark module [1], timing ip6_route_output() with get_cycles(), with 40,000 routes in the main routing table, before this patch: min=606 max=12911 count=627 average=1959 95th=4903 90th=3747 50th=1602 mad=821 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 600 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 199 880 │▒▒▒░░░░░░░░░░░░░░░░ 43 1160 │▒▒▒░░░░░░░░░░░░░░░░░░░░ 48 1440 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░ 43 1720 │▒▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░ 59 2000 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 50 2280 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2560 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 31 2840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 28 3120 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3400 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3680 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3960 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 11 4240 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4520 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4800 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 After: min=544 max=11687 count=627 average=1776 95th=4546 90th=3585 50th=1227 mad=565 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 540 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 201 800 │▒▒▒▒▒░░░░░░░░░░░░░░░░ 63 1060 │▒▒▒▒▒░░░░░░░░░░░░░░░░░░░░░ 68 1320 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░ 39 1580 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 1840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 2100 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 34 2360 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 33 2620 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2880 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 22 3140 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3400 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3660 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3920 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4180 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4440 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 At the frequency of the host during the bench (~ 3.7 GHz), this is about a 100 ns difference on the median value. A next step would be to collapse local and main tables, as in 0ddcf43d5d4a (ipv4: FIB Local/MAIN table collapse). [1]: https://github.com/vincentbernat/network-lab/blob/master/lab-routes-ipv6/kbench_mod.c Signed-off-by: Vincent Bernat <vincent@bernat.im> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-08 18:23:49 +00:00
if (rt->dst.error != -EAGAIN)
return &rt->dst;
ip6_rt_put(rt);
}
dst_hold(&net->ipv6.ip6_null_entry->dst);
return &net->ipv6.ip6_null_entry->dst;
}
static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
struct flowi6 *flp6, const struct net_device *dev)
{
struct fib6_rule *r = (struct fib6_rule *)rule;
/* If we need to find a source address for this traffic,
* we check the result if it meets requirement of the rule.
*/
if ((rule->flags & FIB_RULE_FIND_SADDR) &&
r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
struct in6_addr saddr;
if (ipv6_dev_get_saddr(net, dev, &flp6->daddr,
rt6_flags2srcprefs(flags), &saddr))
return -EAGAIN;
if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen))
return -EAGAIN;
flp6->saddr = saddr;
}
return 0;
}
static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
struct flowi6 *flp6 = &flp->u.ip6;
struct net *net = rule->fr_net;
struct fib6_table *table;
struct fib6_info *f6i;
int err = -EAGAIN, *oif;
u32 tb_id;
switch (rule->action) {
case FR_ACT_TO_TBL:
break;
case FR_ACT_UNREACHABLE:
return -ENETUNREACH;
case FR_ACT_PROHIBIT:
return -EACCES;
case FR_ACT_BLACKHOLE:
default:
return -EINVAL;
}
tb_id = fib_rule_get_table(rule, arg);
table = fib6_get_table(net, tb_id);
if (!table)
return -EAGAIN;
oif = (int *)arg->lookup_data;
f6i = fib6_table_lookup(net, table, *oif, flp6, flags);
if (f6i != net->ipv6.fib6_null_entry) {
err = fib6_rule_saddr(net, rule, flags, flp6,
fib6_info_nh_dev(f6i));
if (likely(!err))
arg->result = f6i;
}
return err;
}
static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
struct flowi6 *flp6 = &flp->u.ip6;
struct rt6_info *rt = NULL;
struct fib6_table *table;
struct net *net = rule->fr_net;
pol_lookup_t lookup = arg->lookup_ptr;
int err = 0;
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 17:55:39 +00:00
u32 tb_id;
switch (rule->action) {
case FR_ACT_TO_TBL:
break;
case FR_ACT_UNREACHABLE:
err = -ENETUNREACH;
rt = net->ipv6.ip6_null_entry;
goto discard_pkt;
default:
case FR_ACT_BLACKHOLE:
err = -EINVAL;
rt = net->ipv6.ip6_blk_hole_entry;
goto discard_pkt;
case FR_ACT_PROHIBIT:
err = -EACCES;
rt = net->ipv6.ip6_prohibit_entry;
goto discard_pkt;
}
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 17:55:39 +00:00
tb_id = fib_rule_get_table(rule, arg);
table = fib6_get_table(net, tb_id);
if (!table) {
err = -EAGAIN;
goto out;
}
rt = lookup(net, table, flp6, arg->lookup_data, flags);
if (rt != net->ipv6.ip6_null_entry) {
err = fib6_rule_saddr(net, rule, flags, flp6,
ip6_dst_idev(&rt->dst)->dev);
if (err == -EAGAIN)
goto again;
err = rt->dst.error;
if (err != -EAGAIN)
goto out;
}
again:
ip6_rt_put(rt);
err = -EAGAIN;
rt = NULL;
goto out;
discard_pkt:
dst_hold(&rt->dst);
out:
arg->result = rt;
return err;
}
static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
if (arg->lookup_ptr == fib6_table_lookup)
return fib6_rule_action_alt(rule, flp, flags, arg);
return __fib6_rule_action(rule, flp, flags, arg);
}
static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
{
struct rt6_info *rt = (struct rt6_info *) arg->result;
struct net_device *dev = NULL;
if (rt->rt6i_idev)
dev = rt->rt6i_idev->dev;
/* do not accept result if the route does
* not meet the required prefix length
*/
if (rt->rt6i_dst.plen <= rule->suppress_prefixlen)
goto suppress_route;
/* do not accept result if the route uses a device
* belonging to a forbidden interface group
*/
if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup)
goto suppress_route;
return false;
suppress_route:
ip6_rt_put(rt);
return true;
}
static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
{
struct fib6_rule *r = (struct fib6_rule *) rule;
struct flowi6 *fl6 = &fl->u.ip6;
if (r->dst.plen &&
!ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen))
return 0;
/*
* If FIB_RULE_FIND_SADDR is set and we do not have a
* source address for the traffic, we defer check for
* source address.
*/
if (r->src.plen) {
if (flags & RT6_LOOKUP_F_HAS_SADDR) {
if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr,
r->src.plen))
return 0;
} else if (!(r->common.flags & FIB_RULE_FIND_SADDR))
return 0;
}
if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel))
return 0;
if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
return 0;
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport))
return 0;
if (fib_rule_port_range_set(&rule->dport_range) &&
!fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport))
return 0;
return 1;
}
static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = {
FRA_GENERIC_POLICY,
};
static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
int err = -EINVAL;
struct net *net = sock_net(skb->sk);
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-08 17:55:39 +00:00
if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
if (rule->table == RT6_TABLE_UNSPEC) {
NL_SET_ERR_MSG(extack, "Invalid table");
goto errout;
}
if (fib6_new_table(net, rule->table) == NULL) {
err = -ENOBUFS;
goto errout;
}
}
if (frh->src_len)
rule6->src.addr = nla_get_in6_addr(tb[FRA_SRC]);
if (frh->dst_len)
rule6->dst.addr = nla_get_in6_addr(tb[FRA_DST]);
rule6->src.plen = frh->src_len;
rule6->dst.plen = frh->dst_len;
rule6->tclass = frh->tos;
if (fib_rule_requires_fldissect(rule))
net->ipv6.fib6_rules_require_fldissect++;
net: ipv6: avoid overhead when no custom FIB rules are installed If the user hasn't installed any custom rules, don't go through the whole FIB rules layer. This is pretty similar to f4530fa574df (ipv4: Avoid overhead when no custom FIB rules are installed). Using a micro-benchmark module [1], timing ip6_route_output() with get_cycles(), with 40,000 routes in the main routing table, before this patch: min=606 max=12911 count=627 average=1959 95th=4903 90th=3747 50th=1602 mad=821 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 600 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 199 880 │▒▒▒░░░░░░░░░░░░░░░░ 43 1160 │▒▒▒░░░░░░░░░░░░░░░░░░░░ 48 1440 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░ 43 1720 │▒▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░ 59 2000 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 50 2280 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2560 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 31 2840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 28 3120 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3400 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 17 3680 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3960 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 11 4240 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4520 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 6 4800 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 After: min=544 max=11687 count=627 average=1776 95th=4546 90th=3585 50th=1227 mad=565 table=254 avgdepth=21.8 maxdepth=39 value │ ┊ count 540 │▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒ 201 800 │▒▒▒▒▒░░░░░░░░░░░░░░░░ 63 1060 │▒▒▒▒▒░░░░░░░░░░░░░░░░░░░░░ 68 1320 │▒▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░ 39 1580 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 1840 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 32 2100 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 34 2360 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 33 2620 │▒▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 26 2880 │▒░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 22 3140 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3400 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 3660 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 9 3920 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4180 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 4440 │░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 8 At the frequency of the host during the bench (~ 3.7 GHz), this is about a 100 ns difference on the median value. A next step would be to collapse local and main tables, as in 0ddcf43d5d4a (ipv4: FIB Local/MAIN table collapse). [1]: https://github.com/vincentbernat/network-lab/blob/master/lab-routes-ipv6/kbench_mod.c Signed-off-by: Vincent Bernat <vincent@bernat.im> Reviewed-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-08 18:23:49 +00:00
net->ipv6.fib6_has_custom_rules = true;
err = 0;
errout:
return err;
}
static int fib6_rule_delete(struct fib_rule *rule)
{
struct net *net = rule->fr_net;
if (net->ipv6.fib6_rules_require_fldissect &&
fib_rule_requires_fldissect(rule))
net->ipv6.fib6_rules_require_fldissect--;
return 0;
}
static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
struct nlattr **tb)
{
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
if (frh->src_len && (rule6->src.plen != frh->src_len))
return 0;
if (frh->dst_len && (rule6->dst.plen != frh->dst_len))
return 0;
if (frh->tos && (rule6->tclass != frh->tos))
return 0;
if (frh->src_len &&
nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
return 0;
if (frh->dst_len &&
nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr)))
return 0;
return 1;
}
static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh)
{
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
frh->dst_len = rule6->dst.plen;
frh->src_len = rule6->src.plen;
frh->tos = rule6->tclass;
if ((rule6->dst.plen &&
nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) ||
(rule6->src.plen &&
nla_put_in6_addr(skb, FRA_SRC, &rule6->src.addr)))
goto nla_put_failure;
return 0;
nla_put_failure:
return -ENOBUFS;
}
static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
{
return nla_total_size(16) /* dst */
+ nla_total_size(16); /* src */
}
static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
.family = AF_INET6,
.rule_size = sizeof(struct fib6_rule),
.addr_size = sizeof(struct in6_addr),
.action = fib6_rule_action,
.match = fib6_rule_match,
.suppress = fib6_rule_suppress,
.configure = fib6_rule_configure,
.delete = fib6_rule_delete,
.compare = fib6_rule_compare,
.fill = fib6_rule_fill,
.nlmsg_payload = fib6_rule_nlmsg_payload,
.nlgroup = RTNLGRP_IPV6_RULE,
.policy = fib6_rule_policy,
.owner = THIS_MODULE,
.fro_net = &init_net,
};
static int __net_init fib6_rules_net_init(struct net *net)
{
struct fib_rules_ops *ops;
int err = -ENOMEM;
ops = fib_rules_register(&fib6_rules_ops_template, net);
if (IS_ERR(ops))
return PTR_ERR(ops);
err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0);
if (err)
goto out_fib6_rules_ops;
err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0);
if (err)
goto out_fib6_rules_ops;
net->ipv6.fib6_rules_ops = ops;
net->ipv6.fib6_rules_require_fldissect = 0;
out:
return err;
out_fib6_rules_ops:
fib_rules_unregister(ops);
goto out;
}
static void __net_exit fib6_rules_net_exit(struct net *net)
{
rtnl_lock();
fib_rules_unregister(net->ipv6.fib6_rules_ops);
rtnl_unlock();
}
static struct pernet_operations fib6_rules_net_ops = {
.init = fib6_rules_net_init,
.exit = fib6_rules_net_exit,
};
int __init fib6_rules_init(void)
{
return register_pernet_subsys(&fib6_rules_net_ops);
}
void fib6_rules_cleanup(void)
{
unregister_pernet_subsys(&fib6_rules_net_ops);
}