linux/net/ipv4/fib_rules.c

430 lines
9.7 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: policy rules.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
* Thomas Graf <tgraf@suug.ch>
*
* 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.
*
* Fixes:
* Rani Assaf : local_rule cannot be deleted
* Marc Boucher : routing by fwmark
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/netlink.h>
#include <linux/inetdevice.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/ip_fib.h>
#include <net/fib_rules.h>
struct fib4_rule {
struct fib_rule common;
u8 dst_len;
u8 src_len;
u8 tos;
__be32 src;
__be32 srcmask;
__be32 dst;
__be32 dstmask;
#ifdef CONFIG_IP_ROUTE_CLASSID
u32 tclassid;
#endif
};
ipv4: fib_rules: Check if rule is a default rule Currently, when non-default (custom) FIB rules are used, devices capable of layer 3 offloading flush their tables and let the kernel do the forwarding instead. When these devices' drivers are loaded they register to the FIB notification chain, which lets them know about the existence of any custom FIB rules. This is done by sending a RULE_ADD notification based on the value of 'net->ipv4.fib_has_custom_rules'. This approach is problematic when VRF offload is taken into account, as upon the creation of the first VRF netdev, a l3mdev rule is programmed to direct skbs to the VRF's table. Instead of merely reading the above value and sending a single RULE_ADD notification, we should iterate over all the FIB rules and send a detailed notification for each, thereby allowing offloading drivers to sanitize the rules they don't support and potentially flush their tables. While l3mdev rules are uniquely marked, the default rules are not. Therefore, when they are being notified they might invoke offloading drivers to unnecessarily flush their tables. Solve this by adding an helper to check if a FIB rule is a default rule. Namely, its selector should match all packets and its action should point to the local, main or default tables. As noted by David Ahern, uniquely marking the default rules is insufficient. When using VRFs, it's common to avoid false hits by moving the rule for the local table to just before the main table: Default configuration: $ ip rule show 0: from all lookup local 32766: from all lookup main 32767: from all lookup default Common configuration with VRFs: $ ip rule show 1000: from all lookup [l3mdev-table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default Signed-off-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-16 08:08:12 +00:00
static bool fib4_rule_matchall(const struct fib_rule *rule)
{
struct fib4_rule *r = container_of(rule, struct fib4_rule, common);
if (r->dst_len || r->src_len || r->tos)
return false;
return fib_rule_matchall(rule);
}
bool fib4_rule_default(const struct fib_rule *rule)
{
if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
rule->l3mdev)
return false;
if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN &&
rule->table != RT_TABLE_DEFAULT)
return false;
return true;
}
EXPORT_SYMBOL_GPL(fib4_rule_default);
int fib4_rules_dump(struct net *net, struct notifier_block *nb)
{
return fib_rules_dump(net, nb, AF_INET);
}
unsigned int fib4_rules_seq_read(struct net *net)
{
return fib_rules_seq_read(net, AF_INET);
}
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
int __fib_lookup(struct net *net, struct flowi4 *flp,
struct fib_result *res, unsigned int flags)
{
struct fib_lookup_arg arg = {
.result = res,
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
.flags = flags,
};
int err;
/* update flow if oif or iif point to device enslaved to l3mdev */
l3mdev_update_flow(net, flowi4_to_flowi(flp));
err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (arg.rule)
res->tclassid = ((struct fib4_rule *)arg.rule)->tclassid;
else
res->tclassid = 0;
#endif
if (err == -ESRCH)
err = -ENETUNREACH;
return err;
}
EXPORT_SYMBOL_GPL(__fib_lookup);
static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
int err = -EAGAIN;
struct fib_table *tbl;
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:
return -ENETUNREACH;
case FR_ACT_PROHIBIT:
return -EACCES;
case FR_ACT_BLACKHOLE:
default:
return -EINVAL;
}
rcu_read_lock();
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);
tbl = fib_get_table(rule->fr_net, tb_id);
if (tbl)
err = fib_table_lookup(tbl, &flp->u.ip4,
(struct fib_result *)arg->result,
arg->flags);
rcu_read_unlock();
return err;
}
static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
{
struct fib_result *result = (struct fib_result *) arg->result;
struct net_device *dev = NULL;
if (result->fi)
dev = result->fi->fib_dev;
/* do not accept result if the route does
* not meet the required prefix length
*/
if (result->prefixlen <= 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:
if (!(arg->flags & FIB_LOOKUP_NOREF))
fib_info_put(result->fi);
return true;
}
static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
{
struct fib4_rule *r = (struct fib4_rule *) rule;
struct flowi4 *fl4 = &fl->u.ip4;
__be32 daddr = fl4->daddr;
__be32 saddr = fl4->saddr;
if (((saddr ^ r->src) & r->srcmask) ||
((daddr ^ r->dst) & r->dstmask))
return 0;
if (r->tos && (r->tos != fl4->flowi4_tos))
return 0;
if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
return 0;
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport))
return 0;
if (fib_rule_port_range_set(&rule->dport_range) &&
!fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport))
return 0;
return 1;
}
static struct fib_table *fib_empty_table(struct net *net)
{
u32 id = 1;
while (1) {
if (!fib_get_table(net, id))
return fib_new_table(net, id);
if (id++ == RT_TABLE_MAX)
break;
}
return NULL;
}
static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = {
FRA_GENERIC_POLICY,
[FRA_FLOW] = { .type = NLA_U32 },
};
static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
int err = -EINVAL;
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
if (frh->tos & ~IPTOS_TOS_MASK) {
NL_SET_ERR_MSG(extack, "Invalid tos");
goto errout;
}
/* split local/main if they are not already split */
err = fib_unmerge(net);
if (err)
goto errout;
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->table == RT_TABLE_UNSPEC && !rule->l3mdev) {
if (rule->action == FR_ACT_TO_TBL) {
struct fib_table *table;
table = fib_empty_table(net);
if (!table) {
err = -ENOBUFS;
goto errout;
}
rule->table = table->tb_id;
}
}
if (frh->src_len)
rule4->src = nla_get_in_addr(tb[FRA_SRC]);
if (frh->dst_len)
rule4->dst = nla_get_in_addr(tb[FRA_DST]);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (tb[FRA_FLOW]) {
rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
if (rule4->tclassid)
net->ipv4.fib_num_tclassid_users++;
}
#endif
if (fib_rule_requires_fldissect(rule))
net->ipv4.fib_rules_require_fldissect++;
rule4->src_len = frh->src_len;
rule4->srcmask = inet_make_mask(rule4->src_len);
rule4->dst_len = frh->dst_len;
rule4->dstmask = inet_make_mask(rule4->dst_len);
rule4->tos = frh->tos;
net->ipv4.fib_has_custom_rules = true;
err = 0;
errout:
return err;
}
static int fib4_rule_delete(struct fib_rule *rule)
{
struct net *net = rule->fr_net;
int err;
/* split local/main if they are not already split */
err = fib_unmerge(net);
if (err)
goto errout;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (((struct fib4_rule *)rule)->tclassid)
net->ipv4.fib_num_tclassid_users--;
#endif
net->ipv4.fib_has_custom_rules = true;
if (net->ipv4.fib_rules_require_fldissect &&
fib_rule_requires_fldissect(rule))
net->ipv4.fib_rules_require_fldissect--;
errout:
return err;
}
static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
struct nlattr **tb)
{
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
if (frh->src_len && (rule4->src_len != frh->src_len))
return 0;
if (frh->dst_len && (rule4->dst_len != frh->dst_len))
return 0;
if (frh->tos && (rule4->tos != frh->tos))
return 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
return 0;
#endif
if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC])))
return 0;
if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST])))
return 0;
return 1;
}
static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh)
{
struct fib4_rule *rule4 = (struct fib4_rule *) rule;
frh->dst_len = rule4->dst_len;
frh->src_len = rule4->src_len;
frh->tos = rule4->tos;
if ((rule4->dst_len &&
nla_put_in_addr(skb, FRA_DST, rule4->dst)) ||
(rule4->src_len &&
nla_put_in_addr(skb, FRA_SRC, rule4->src)))
goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (rule4->tclassid &&
nla_put_u32(skb, FRA_FLOW, rule4->tclassid))
goto nla_put_failure;
#endif
return 0;
nla_put_failure:
return -ENOBUFS;
}
static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
{
return nla_total_size(4) /* dst */
+ nla_total_size(4) /* src */
+ nla_total_size(4); /* flow */
}
static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
{
rt_cache_flush(ops->fro_net);
}
static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = {
.family = AF_INET,
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
.action = fib4_rule_action,
.suppress = fib4_rule_suppress,
.match = fib4_rule_match,
.configure = fib4_rule_configure,
.delete = fib4_rule_delete,
.compare = fib4_rule_compare,
.fill = fib4_rule_fill,
.nlmsg_payload = fib4_rule_nlmsg_payload,
.flush_cache = fib4_rule_flush_cache,
.nlgroup = RTNLGRP_IPV4_RULE,
.policy = fib4_rule_policy,
.owner = THIS_MODULE,
};
static int fib_default_rules_init(struct fib_rules_ops *ops)
{
int err;
err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0);
if (err < 0)
return err;
err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0);
if (err < 0)
return err;
err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT, 0);
if (err < 0)
return err;
return 0;
}
int __net_init fib4_rules_init(struct net *net)
{
int err;
struct fib_rules_ops *ops;
ops = fib_rules_register(&fib4_rules_ops_template, net);
if (IS_ERR(ops))
return PTR_ERR(ops);
err = fib_default_rules_init(ops);
if (err < 0)
goto fail;
net->ipv4.rules_ops = ops;
net->ipv4.fib_has_custom_rules = false;
net->ipv4.fib_rules_require_fldissect = 0;
return 0;
fail:
/* also cleans all rules already added */
fib_rules_unregister(ops);
return err;
}
void __net_exit fib4_rules_exit(struct net *net)
{
fib_rules_unregister(net->ipv4.rules_ops);
}