linux/net/core/fib_rules.c

1320 lines
31 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* net/core/fib_rules.c Generic Routing Rules
*
* Authors: Thomas Graf <tgraf@suug.ch>
*/
#include <linux/types.h>
#include <linux/kernel.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 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/module.h>
#include <net/net_namespace.h>
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-17 18:56:21 +00:00
#include <net/sock.h>
#include <net/fib_rules.h>
#include <net/ip_tunnels.h>
#include <linux/indirect_call_wrapper.h>
#if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES)
#ifdef CONFIG_IP_MULTIPLE_TABLES
#define INDIRECT_CALL_MT(f, f2, f1, ...) \
INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__)
#else
#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
#endif
#elif defined(CONFIG_IP_MULTIPLE_TABLES)
#define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
#else
#define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__)
#endif
static const struct fib_kuid_range fib_kuid_range_unset = {
KUIDT_INIT(0),
KUIDT_INIT(~0),
};
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
bool fib_rule_matchall(const struct fib_rule *rule)
{
if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id ||
rule->flags)
return false;
if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1)
return false;
if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
!uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
return false;
if (fib_rule_port_range_set(&rule->sport_range))
return false;
if (fib_rule_port_range_set(&rule->dport_range))
return false;
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
return true;
}
EXPORT_SYMBOL_GPL(fib_rule_matchall);
int fib_default_rule_add(struct fib_rules_ops *ops,
u32 pref, u32 table, u32 flags)
{
struct fib_rule *r;
memcg: enable accounting for IP address and routing-related objects An netadmin inside container can use 'ip a a' and 'ip r a' to assign a large number of ipv4/ipv6 addresses and routing entries and force kernel to allocate megabytes of unaccounted memory for long-lived per-netdevice related kernel objects: 'struct in_ifaddr', 'struct inet6_ifaddr', 'struct fib6_node', 'struct rt6_info', 'struct fib_rules' and ip_fib caches. These objects can be manually removed, though usually they lives in memory till destroy of its net namespace. It makes sense to account for them to restrict the host's memory consumption from inside the memcg-limited container. One of such objects is the 'struct fib6_node' mostly allocated in net/ipv6/route.c::__ip6_ins_rt() inside the lock_bh()/unlock_bh() section: write_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc); write_unlock_bh(&table->tb6_lock); In this case it is not enough to simply add SLAB_ACCOUNT to corresponding kmem cache. The proper memory cgroup still cannot be found due to the incorrect 'in_interrupt()' check used in memcg_kmem_bypass(). Obsoleted in_interrupt() does not describe real execution context properly. >From include/linux/preempt.h: The following macros are deprecated and should not be used in new code: in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled To verify the current execution context new macro should be used instead: in_task() - We're in task context Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-19 10:44:31 +00:00
r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT);
if (r == NULL)
return -ENOMEM;
refcount_set(&r->refcnt, 1);
r->action = FR_ACT_TO_TBL;
r->pref = pref;
r->table = table;
r->flags = flags;
r->proto = RTPROT_KERNEL;
r->fr_net = ops->fro_net;
r->uid_range = fib_kuid_range_unset;
r->suppress_prefixlen = -1;
r->suppress_ifgroup = -1;
/* The lock is not required here, the list in unreacheable
* at the moment this function is called */
list_add_tail(&r->list, &ops->rules_list);
return 0;
}
EXPORT_SYMBOL(fib_default_rule_add);
static u32 fib_default_rule_pref(struct fib_rules_ops *ops)
{
struct list_head *pos;
struct fib_rule *rule;
if (!list_empty(&ops->rules_list)) {
pos = ops->rules_list.next;
if (pos->next != &ops->rules_list) {
rule = list_entry(pos->next, struct fib_rule, list);
if (rule->pref)
return rule->pref - 1;
}
}
return 0;
}
static void notify_rule_change(int event, struct fib_rule *rule,
struct fib_rules_ops *ops, struct nlmsghdr *nlh,
u32 pid);
static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family)
{
struct fib_rules_ops *ops;
rcu_read_lock();
list_for_each_entry_rcu(ops, &net->rules_ops, list) {
if (ops->family == family) {
if (!try_module_get(ops->owner))
ops = NULL;
rcu_read_unlock();
return ops;
}
}
rcu_read_unlock();
return NULL;
}
static void rules_ops_put(struct fib_rules_ops *ops)
{
if (ops)
module_put(ops->owner);
}
static void flush_route_cache(struct fib_rules_ops *ops)
{
if (ops->flush_cache)
ops->flush_cache(ops);
}
static int __fib_rules_register(struct fib_rules_ops *ops)
{
int err = -EEXIST;
struct fib_rules_ops *o;
struct net *net;
net = ops->fro_net;
if (ops->rule_size < sizeof(struct fib_rule))
return -EINVAL;
if (ops->match == NULL || ops->configure == NULL ||
ops->compare == NULL || ops->fill == NULL ||
ops->action == NULL)
return -EINVAL;
spin_lock(&net->rules_mod_lock);
list_for_each_entry(o, &net->rules_ops, list)
if (ops->family == o->family)
goto errout;
list_add_tail_rcu(&ops->list, &net->rules_ops);
err = 0;
errout:
spin_unlock(&net->rules_mod_lock);
return err;
}
struct fib_rules_ops *
fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net)
{
struct fib_rules_ops *ops;
int err;
ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL);
if (ops == NULL)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&ops->rules_list);
ops->fro_net = net;
err = __fib_rules_register(ops);
if (err) {
kfree(ops);
ops = ERR_PTR(err);
}
return ops;
}
EXPORT_SYMBOL_GPL(fib_rules_register);
static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
{
struct fib_rule *rule, *tmp;
list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) {
list_del_rcu(&rule->list);
if (ops->delete)
ops->delete(rule);
fib_rule_put(rule);
}
}
void fib_rules_unregister(struct fib_rules_ops *ops)
{
struct net *net = ops->fro_net;
spin_lock(&net->rules_mod_lock);
list_del_rcu(&ops->list);
spin_unlock(&net->rules_mod_lock);
fib_rules_cleanup_ops(ops);
kfree_rcu(ops, rcu);
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
static int uid_range_set(struct fib_kuid_range *range)
{
return uid_valid(range->start) && uid_valid(range->end);
}
static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb)
{
struct fib_rule_uid_range *in;
struct fib_kuid_range out;
in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]);
out.start = make_kuid(current_user_ns(), in->start);
out.end = make_kuid(current_user_ns(), in->end);
return out;
}
static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
{
struct fib_rule_uid_range out = {
from_kuid_munged(current_user_ns(), range->start),
from_kuid_munged(current_user_ns(), range->end)
};
return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
}
static int nla_get_port_range(struct nlattr *pattr,
struct fib_rule_port_range *port_range)
{
const struct fib_rule_port_range *pr = nla_data(pattr);
if (!fib_rule_port_range_valid(pr))
return -EINVAL;
port_range->start = pr->start;
port_range->end = pr->end;
return 0;
}
static int nla_put_port_range(struct sk_buff *skb, int attrtype,
struct fib_rule_port_range *range)
{
return nla_put(skb, attrtype, sizeof(*range), range);
}
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
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
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
{
int ret = 0;
if (rule->iifindex && (rule->iifindex != fl->flowi_iif))
goto out;
if (rule->oifindex && (rule->oifindex != fl->flowi_oif))
goto out;
if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
goto out;
if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
goto out;
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->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
goto out;
if (uid_lt(fl->flowi_uid, rule->uid_range.start) ||
uid_gt(fl->flowi_uid, rule->uid_range.end))
goto out;
ret = INDIRECT_CALL_MT(ops->match,
fib6_rule_match,
fib4_rule_match,
rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
}
int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl,
int flags, struct fib_lookup_arg *arg)
{
struct fib_rule *rule;
int err;
rcu_read_lock();
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
jumped:
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 (!fib_rule_match(rule, ops, fl, flags, arg))
continue;
if (rule->action == FR_ACT_GOTO) {
struct fib_rule *target;
target = rcu_dereference(rule->ctarget);
if (target == NULL) {
continue;
} else {
rule = target;
goto jumped;
}
} else if (rule->action == FR_ACT_NOP)
continue;
else
err = INDIRECT_CALL_MT(ops->action,
fib6_rule_action,
fib4_rule_action,
rule, fl, flags, arg);
if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress,
fib6_rule_suppress,
fib4_rule_suppress,
ipv6: fix memory leak in fib6_rule_suppress The kernel leaks memory when a `fib` rule is present in IPv6 nftables firewall rules and a suppress_prefix rule is present in the IPv6 routing rules (used by certain tools such as wg-quick). In such scenarios, every incoming packet will leak an allocation in `ip6_dst_cache` slab cache. After some hours of `bpftrace`-ing and source code reading, I tracked down the issue to ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule"). The problem with that change is that the generic `args->flags` always have `FIB_LOOKUP_NOREF` set[1][2] but the IPv6-specific flag `RT6_LOOKUP_F_DST_NOREF` might not be, leading to `fib6_rule_suppress` not decreasing the refcount when needed. How to reproduce: - Add the following nftables rule to a prerouting chain: meta nfproto ipv6 fib saddr . mark . iif oif missing drop This can be done with: sudo nft create table inet test sudo nft create chain inet test test_chain '{ type filter hook prerouting priority filter + 10; policy accept; }' sudo nft add rule inet test test_chain meta nfproto ipv6 fib saddr . mark . iif oif missing drop - Run: sudo ip -6 rule add table main suppress_prefixlength 0 - Watch `sudo slabtop -o | grep ip6_dst_cache` to see memory usage increase with every incoming ipv6 packet. This patch exposes the protocol-specific flags to the protocol specific `suppress` function, and check the protocol-specific `flags` argument for RT6_LOOKUP_F_DST_NOREF instead of the generic FIB_LOOKUP_NOREF when decreasing the refcount, like this. [1]: https://github.com/torvalds/linux/blob/ca7a03c4175366a92cee0ccc4fec0038c3266e26/net/ipv6/fib6_rules.c#L71 [2]: https://github.com/torvalds/linux/blob/ca7a03c4175366a92cee0ccc4fec0038c3266e26/net/ipv6/fib6_rules.c#L99 Link: https://bugzilla.kernel.org/show_bug.cgi?id=215105 Fixes: ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule") Cc: stable@vger.kernel.org Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-11-23 12:48:32 +00:00
rule, flags, arg))
continue;
if (err != -EAGAIN) {
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 10:41:36 +00:00
if ((arg->flags & FIB_LOOKUP_NOREF) ||
likely(refcount_inc_not_zero(&rule->refcnt))) {
arg->rule = rule;
goto out;
}
break;
}
}
err = -ESRCH;
out:
rcu_read_unlock();
return err;
}
EXPORT_SYMBOL_GPL(fib_rules_lookup);
static int call_fib_rule_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_rule *rule, int family,
struct netlink_ext_ack *extack)
{
struct fib_rule_notifier_info info = {
.info.family = family,
.info.extack = extack,
.rule = rule,
};
return call_fib_notifier(nb, event_type, &info.info);
}
static int call_fib_rule_notifiers(struct net *net,
enum fib_event_type event_type,
struct fib_rule *rule,
struct fib_rules_ops *ops,
struct netlink_ext_ack *extack)
{
struct fib_rule_notifier_info info = {
.info.family = ops->family,
.info.extack = extack,
.rule = rule,
};
ops->fib_rules_seq++;
return call_fib_notifiers(net, event_type, &info.info);
}
/* Called with rcu_read_lock() */
int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
struct netlink_ext_ack *extack)
{
struct fib_rules_ops *ops;
struct fib_rule *rule;
int err = 0;
ops = lookup_rules_ops(net, family);
if (!ops)
return -EAFNOSUPPORT;
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD,
rule, family, extack);
if (err)
break;
}
rules_ops_put(ops);
return err;
}
EXPORT_SYMBOL_GPL(fib_rules_dump);
unsigned int fib_rules_seq_read(struct net *net, int family)
{
unsigned int fib_rules_seq;
struct fib_rules_ops *ops;
ASSERT_RTNL();
ops = lookup_rules_ops(net, family);
if (!ops)
return 0;
fib_rules_seq = ops->fib_rules_seq;
rules_ops_put(ops);
return fib_rules_seq;
}
EXPORT_SYMBOL_GPL(fib_rules_seq_read);
static struct fib_rule *rule_find(struct fib_rules_ops *ops,
struct fib_rule_hdr *frh,
struct nlattr **tb,
struct fib_rule *rule,
bool user_priority)
{
struct fib_rule *r;
list_for_each_entry(r, &ops->rules_list, list) {
if (rule->action && r->action != rule->action)
continue;
if (rule->table && r->table != rule->table)
continue;
if (user_priority && r->pref != rule->pref)
continue;
if (rule->iifname[0] &&
memcmp(r->iifname, rule->iifname, IFNAMSIZ))
continue;
if (rule->oifname[0] &&
memcmp(r->oifname, rule->oifname, IFNAMSIZ))
continue;
if (rule->mark && r->mark != rule->mark)
continue;
if (rule->suppress_ifgroup != -1 &&
r->suppress_ifgroup != rule->suppress_ifgroup)
continue;
if (rule->suppress_prefixlen != -1 &&
r->suppress_prefixlen != rule->suppress_prefixlen)
continue;
if (rule->mark_mask && r->mark_mask != rule->mark_mask)
continue;
if (rule->tun_id && r->tun_id != rule->tun_id)
continue;
if (r->fr_net != rule->fr_net)
continue;
if (rule->l3mdev && r->l3mdev != rule->l3mdev)
continue;
if (uid_range_set(&rule->uid_range) &&
(!uid_eq(r->uid_range.start, rule->uid_range.start) ||
!uid_eq(r->uid_range.end, rule->uid_range.end)))
continue;
if (rule->ip_proto && r->ip_proto != rule->ip_proto)
continue;
if (rule->proto && r->proto != rule->proto)
continue;
if (fib_rule_port_range_set(&rule->sport_range) &&
!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
continue;
if (fib_rule_port_range_set(&rule->dport_range) &&
!fib_rule_port_range_compare(&r->dport_range,
&rule->dport_range))
continue;
if (!ops->compare(r, frh, tb))
continue;
return r;
}
return NULL;
}
#ifdef CONFIG_NET_L3_MASTER_DEV
static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule,
struct netlink_ext_ack *extack)
{
nlrule->l3mdev = nla_get_u8(nla);
if (nlrule->l3mdev != 1) {
NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute");
return -1;
}
return 0;
}
#else
static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule,
struct netlink_ext_ack *extack)
{
NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel");
return -1;
}
#endif
static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack,
struct fib_rules_ops *ops,
struct nlattr *tb[],
struct fib_rule **rule,
bool *user_priority)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
struct fib_rule *nlrule = NULL;
int err = -EINVAL;
if (frh->src_len)
if (!tb[FRA_SRC] ||
frh->src_len > (ops->addr_size * 8) ||
nla_len(tb[FRA_SRC]) != ops->addr_size) {
NL_SET_ERR_MSG(extack, "Invalid source address");
goto errout;
}
if (frh->dst_len)
if (!tb[FRA_DST] ||
frh->dst_len > (ops->addr_size * 8) ||
nla_len(tb[FRA_DST]) != ops->addr_size) {
NL_SET_ERR_MSG(extack, "Invalid dst address");
goto errout;
}
memcg: enable accounting for IP address and routing-related objects An netadmin inside container can use 'ip a a' and 'ip r a' to assign a large number of ipv4/ipv6 addresses and routing entries and force kernel to allocate megabytes of unaccounted memory for long-lived per-netdevice related kernel objects: 'struct in_ifaddr', 'struct inet6_ifaddr', 'struct fib6_node', 'struct rt6_info', 'struct fib_rules' and ip_fib caches. These objects can be manually removed, though usually they lives in memory till destroy of its net namespace. It makes sense to account for them to restrict the host's memory consumption from inside the memcg-limited container. One of such objects is the 'struct fib6_node' mostly allocated in net/ipv6/route.c::__ip6_ins_rt() inside the lock_bh()/unlock_bh() section: write_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc); write_unlock_bh(&table->tb6_lock); In this case it is not enough to simply add SLAB_ACCOUNT to corresponding kmem cache. The proper memory cgroup still cannot be found due to the incorrect 'in_interrupt()' check used in memcg_kmem_bypass(). Obsoleted in_interrupt() does not describe real execution context properly. >From include/linux/preempt.h: The following macros are deprecated and should not be used in new code: in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled To verify the current execution context new macro should be used instead: in_task() - We're in task context Signed-off-by: Vasily Averin <vvs@virtuozzo.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-19 10:44:31 +00:00
nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT);
if (!nlrule) {
err = -ENOMEM;
goto errout;
}
refcount_set(&nlrule->refcnt, 1);
nlrule->fr_net = net;
if (tb[FRA_PRIORITY]) {
nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]);
*user_priority = true;
} else {
nlrule->pref = fib_default_rule_pref(ops);
}
nlrule->proto = tb[FRA_PROTOCOL] ?
nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC;
if (tb[FRA_IIFNAME]) {
struct net_device *dev;
nlrule->iifindex = -1;
nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->iifname);
if (dev)
nlrule->iifindex = dev->ifindex;
}
if (tb[FRA_OIFNAME]) {
struct net_device *dev;
nlrule->oifindex = -1;
nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->oifname);
if (dev)
nlrule->oifindex = dev->ifindex;
}
if (tb[FRA_FWMARK]) {
nlrule->mark = nla_get_u32(tb[FRA_FWMARK]);
if (nlrule->mark)
/* compatibility: if the mark value is non-zero all bits
* are compared unless a mask is explicitly specified.
*/
nlrule->mark_mask = 0xFFFFFFFF;
}
if (tb[FRA_FWMASK])
nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]);
if (tb[FRA_TUN_ID])
nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
err = -EINVAL;
if (tb[FRA_L3MDEV] &&
fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0)
goto errout_free;
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
nlrule->action = frh->action;
nlrule->flags = frh->flags;
nlrule->table = frh_get_table(frh, tb);
if (tb[FRA_SUPPRESS_PREFIXLEN])
nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]);
else
nlrule->suppress_prefixlen = -1;
if (tb[FRA_SUPPRESS_IFGROUP])
nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]);
else
nlrule->suppress_ifgroup = -1;
if (tb[FRA_GOTO]) {
if (nlrule->action != FR_ACT_GOTO) {
NL_SET_ERR_MSG(extack, "Unexpected goto");
goto errout_free;
}
nlrule->target = nla_get_u32(tb[FRA_GOTO]);
/* Backward jumps are prohibited to avoid endless loops */
if (nlrule->target <= nlrule->pref) {
NL_SET_ERR_MSG(extack, "Backward goto not supported");
goto errout_free;
}
} else if (nlrule->action == FR_ACT_GOTO) {
NL_SET_ERR_MSG(extack, "Missing goto target for action goto");
goto errout_free;
}
if (nlrule->l3mdev && nlrule->table) {
NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive");
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
goto errout_free;
}
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 (tb[FRA_UID_RANGE]) {
if (current_user_ns() != net->user_ns) {
err = -EPERM;
NL_SET_ERR_MSG(extack, "No permission to set uid");
goto errout_free;
}
nlrule->uid_range = nla_get_kuid_range(tb);
if (!uid_range_set(&nlrule->uid_range) ||
!uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) {
NL_SET_ERR_MSG(extack, "Invalid uid range");
goto errout_free;
}
} else {
nlrule->uid_range = fib_kuid_range_unset;
}
if (tb[FRA_IP_PROTO])
nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]);
if (tb[FRA_SPORT_RANGE]) {
err = nla_get_port_range(tb[FRA_SPORT_RANGE],
&nlrule->sport_range);
if (err) {
NL_SET_ERR_MSG(extack, "Invalid sport range");
goto errout_free;
}
}
if (tb[FRA_DPORT_RANGE]) {
err = nla_get_port_range(tb[FRA_DPORT_RANGE],
&nlrule->dport_range);
if (err) {
NL_SET_ERR_MSG(extack, "Invalid dport range");
goto errout_free;
}
}
*rule = nlrule;
return 0;
errout_free:
kfree(nlrule);
errout:
return err;
}
static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
struct nlattr **tb, struct fib_rule *rule)
{
struct fib_rule *r;
list_for_each_entry(r, &ops->rules_list, list) {
if (r->action != rule->action)
continue;
if (r->table != rule->table)
continue;
if (r->pref != rule->pref)
continue;
if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
continue;
if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
continue;
if (r->mark != rule->mark)
continue;
if (r->suppress_ifgroup != rule->suppress_ifgroup)
continue;
if (r->suppress_prefixlen != rule->suppress_prefixlen)
continue;
if (r->mark_mask != rule->mark_mask)
continue;
if (r->tun_id != rule->tun_id)
continue;
if (r->fr_net != rule->fr_net)
continue;
if (r->l3mdev != rule->l3mdev)
continue;
if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
!uid_eq(r->uid_range.end, rule->uid_range.end))
continue;
if (r->ip_proto != rule->ip_proto)
continue;
if (r->proto != rule->proto)
continue;
if (!fib_rule_port_range_compare(&r->sport_range,
&rule->sport_range))
continue;
if (!fib_rule_port_range_compare(&r->dport_range,
&rule->dport_range))
continue;
if (!ops->compare(r, frh, tb))
continue;
return 1;
}
return 0;
}
static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
[FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 },
[FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
[FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
[FRA_PRIORITY] = { .type = NLA_U32 },
[FRA_FWMARK] = { .type = NLA_U32 },
[FRA_FLOW] = { .type = NLA_U32 },
[FRA_TUN_ID] = { .type = NLA_U64 },
[FRA_FWMASK] = { .type = NLA_U32 },
[FRA_TABLE] = { .type = NLA_U32 },
[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 },
[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 },
[FRA_GOTO] = { .type = NLA_U32 },
[FRA_L3MDEV] = { .type = NLA_U8 },
[FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) },
[FRA_PROTOCOL] = { .type = NLA_U8 },
[FRA_IP_PROTO] = { .type = NLA_U8 },
[FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
[FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }
};
int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
struct fib_rules_ops *ops = NULL;
struct fib_rule *rule = NULL, *r, *last = NULL;
struct nlattr *tb[FRA_MAX + 1];
int err = -EINVAL, unresolved = 0;
bool user_priority = false;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
NL_SET_ERR_MSG(extack, "Invalid msg length");
goto errout;
}
ops = lookup_rules_ops(net, frh->family);
if (!ops) {
err = -EAFNOSUPPORT;
NL_SET_ERR_MSG(extack, "Rule family not supported");
goto errout;
}
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX,
fib_rule_policy, extack);
if (err < 0) {
NL_SET_ERR_MSG(extack, "Error parsing msg");
goto errout;
}
err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority);
if (err)
goto errout;
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
goto errout_free;
}
err = ops->configure(rule, skb, frh, tb, extack);
if (err < 0)
goto errout_free;
err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops,
extack);
if (err < 0)
goto errout_free;
list_for_each_entry(r, &ops->rules_list, list) {
if (r->pref == rule->target) {
RCU_INIT_POINTER(rule->ctarget, r);
break;
}
}
if (rcu_dereference_protected(rule->ctarget, 1) == NULL)
unresolved = 1;
list_for_each_entry(r, &ops->rules_list, list) {
if (r->pref > rule->pref)
break;
last = r;
}
if (last)
list_add_rcu(&rule->list, &last->list);
else
list_add_rcu(&rule->list, &ops->rules_list);
if (ops->unresolved_rules) {
/*
* There are unresolved goto rules in the list, check if
* any of them are pointing to this new rule.
*/
list_for_each_entry(r, &ops->rules_list, list) {
if (r->action == FR_ACT_GOTO &&
r->target == rule->pref &&
rtnl_dereference(r->ctarget) == NULL) {
rcu_assign_pointer(r->ctarget, rule);
if (--ops->unresolved_rules == 0)
break;
}
}
}
if (rule->action == FR_ACT_GOTO)
ops->nr_goto_rules++;
if (unresolved)
ops->unresolved_rules++;
if (rule->tun_id)
ip_tunnel_need_metadata();
notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
flush_route_cache(ops);
rules_ops_put(ops);
return 0;
errout_free:
kfree(rule);
errout:
rules_ops_put(ops);
return err;
}
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
EXPORT_SYMBOL_GPL(fib_nl_newrule);
int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
struct fib_rules_ops *ops = NULL;
struct fib_rule *rule = NULL, *r, *nlrule = NULL;
struct nlattr *tb[FRA_MAX+1];
int err = -EINVAL;
bool user_priority = false;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
NL_SET_ERR_MSG(extack, "Invalid msg length");
goto errout;
}
ops = lookup_rules_ops(net, frh->family);
if (ops == NULL) {
err = -EAFNOSUPPORT;
NL_SET_ERR_MSG(extack, "Rule family not supported");
goto errout;
}
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX,
fib_rule_policy, extack);
if (err < 0) {
NL_SET_ERR_MSG(extack, "Error parsing msg");
goto errout;
}
err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority);
if (err)
goto errout;
rule = rule_find(ops, frh, tb, nlrule, user_priority);
if (!rule) {
err = -ENOENT;
goto errout;
}
if (rule->flags & FIB_RULE_PERMANENT) {
err = -EPERM;
goto errout;
}
if (ops->delete) {
err = ops->delete(rule);
if (err)
goto errout;
}
if (rule->tun_id)
ip_tunnel_unneed_metadata();
list_del_rcu(&rule->list);
if (rule->action == FR_ACT_GOTO) {
ops->nr_goto_rules--;
if (rtnl_dereference(rule->ctarget) == NULL)
ops->unresolved_rules--;
}
/*
* Check if this rule is a target to any of them. If so,
* adjust to the next one with the same preference or
* disable them. As this operation is eventually very
* expensive, it is only performed if goto rules, except
* current if it is goto rule, have actually been added.
*/
if (ops->nr_goto_rules > 0) {
struct fib_rule *n;
n = list_next_entry(rule, list);
if (&n->list == &ops->rules_list || n->pref != rule->pref)
n = NULL;
list_for_each_entry(r, &ops->rules_list, list) {
if (rtnl_dereference(r->ctarget) != rule)
continue;
rcu_assign_pointer(r->ctarget, n);
if (!n)
ops->unresolved_rules++;
}
}
call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops,
NULL);
notify_rule_change(RTM_DELRULE, rule, ops, nlh,
NETLINK_CB(skb).portid);
fib_rule_put(rule);
flush_route_cache(ops);
rules_ops_put(ops);
kfree(nlrule);
return 0;
errout:
kfree(nlrule);
rules_ops_put(ops);
return err;
}
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
EXPORT_SYMBOL_GPL(fib_nl_delrule);
static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
struct fib_rule *rule)
{
size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr))
+ nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */
+ nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */
+ nla_total_size(4) /* FRA_PRIORITY */
+ nla_total_size(4) /* FRA_TABLE */
+ nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
+ nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
+ nla_total_size(4) /* FRA_FWMARK */
+ nla_total_size(4) /* FRA_FWMASK */
+ nla_total_size_64bit(8) /* FRA_TUN_ID */
+ nla_total_size(sizeof(struct fib_kuid_range))
+ nla_total_size(1) /* FRA_PROTOCOL */
+ nla_total_size(1) /* FRA_IP_PROTO */
+ nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */
+ nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
return payload;
}
static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
u32 pid, u32 seq, int type, int flags,
struct fib_rules_ops *ops)
{
struct nlmsghdr *nlh;
struct fib_rule_hdr *frh;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags);
if (nlh == NULL)
return -EMSGSIZE;
frh = nlmsg_data(nlh);
frh->family = ops->family;
frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
if (nla_put_u32(skb, FRA_TABLE, rule->table))
goto nla_put_failure;
if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
goto nla_put_failure;
frh->res1 = 0;
frh->res2 = 0;
frh->action = rule->action;
frh->flags = rule->flags;
if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto))
goto nla_put_failure;
if (rule->action == FR_ACT_GOTO &&
rcu_access_pointer(rule->ctarget) == NULL)
frh->flags |= FIB_RULE_UNRESOLVED;
if (rule->iifname[0]) {
if (nla_put_string(skb, FRA_IIFNAME, rule->iifname))
goto nla_put_failure;
if (rule->iifindex == -1)
frh->flags |= FIB_RULE_IIF_DETACHED;
}
if (rule->oifname[0]) {
if (nla_put_string(skb, FRA_OIFNAME, rule->oifname))
goto nla_put_failure;
if (rule->oifindex == -1)
frh->flags |= FIB_RULE_OIF_DETACHED;
}
if ((rule->pref &&
nla_put_u32(skb, FRA_PRIORITY, rule->pref)) ||
(rule->mark &&
nla_put_u32(skb, FRA_FWMARK, rule->mark)) ||
((rule->mark_mask || rule->mark) &&
nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
(rule->target &&
nla_put_u32(skb, FRA_GOTO, rule->target)) ||
(rule->tun_id &&
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
nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
(rule->l3mdev &&
nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
(uid_range_set(&rule->uid_range) &&
nla_put_uid_range(skb, &rule->uid_range)) ||
(fib_rule_port_range_set(&rule->sport_range) &&
nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) ||
(fib_rule_port_range_set(&rule->dport_range) &&
nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) ||
(rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto)))
goto nla_put_failure;
if (rule->suppress_ifgroup != -1) {
if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup))
goto nla_put_failure;
}
if (ops->fill(rule, skb, frh) < 0)
goto nla_put_failure;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
struct fib_rules_ops *ops)
{
int idx = 0;
struct fib_rule *rule;
int err = 0;
rcu_read_lock();
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
if (idx < cb->args[1])
goto skip;
err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, RTM_NEWRULE,
NLM_F_MULTI, ops);
if (err)
break;
skip:
idx++;
}
rcu_read_unlock();
cb->args[1] = idx;
rules_ops_put(ops);
return err;
}
static int fib_valid_dumprule_req(const struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct fib_rule_hdr *frh;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request");
return -EINVAL;
}
frh = nlmsg_data(nlh);
if (frh->dst_len || frh->src_len || frh->tos || frh->table ||
frh->res1 || frh->res2 || frh->action || frh->flags) {
NL_SET_ERR_MSG(extack,
"Invalid values in header for fib rule dump request");
return -EINVAL;
}
if (nlmsg_attrlen(nlh, sizeof(*frh))) {
NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request");
return -EINVAL;
}
return 0;
}
static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
{
const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct fib_rules_ops *ops;
int idx = 0, family;
if (cb->strict_check) {
int err = fib_valid_dumprule_req(nlh, cb->extack);
if (err < 0)
return err;
}
family = rtnl_msg_family(nlh);
if (family != AF_UNSPEC) {
/* Protocol specific dump request */
ops = lookup_rules_ops(net, family);
if (ops == NULL)
return -EAFNOSUPPORT;
dump_rules(skb, cb, ops);
return skb->len;
}
rcu_read_lock();
list_for_each_entry_rcu(ops, &net->rules_ops, list) {
if (idx < cb->args[0] || !try_module_get(ops->owner))
goto skip;
if (dump_rules(skb, cb, ops) < 0)
break;
cb->args[1] = 0;
skip:
idx++;
}
rcu_read_unlock();
cb->args[0] = idx;
return skb->len;
}
static void notify_rule_change(int event, struct fib_rule *rule,
struct fib_rules_ops *ops, struct nlmsghdr *nlh,
u32 pid)
{
struct net *net;
struct sk_buff *skb;
int err = -ENOMEM;
net = ops->fro_net;
skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL);
if (skb == NULL)
goto errout;
err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
2009-02-25 07:18:28 +00:00
rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
return;
errout:
if (err < 0)
rtnl_set_sk_err(net, ops->nlgroup, err);
}
static void attach_rules(struct list_head *rules, struct net_device *dev)
{
struct fib_rule *rule;
list_for_each_entry(rule, rules, list) {
if (rule->iifindex == -1 &&
strcmp(dev->name, rule->iifname) == 0)
rule->iifindex = dev->ifindex;
if (rule->oifindex == -1 &&
strcmp(dev->name, rule->oifname) == 0)
rule->oifindex = dev->ifindex;
}
}
static void detach_rules(struct list_head *rules, struct net_device *dev)
{
struct fib_rule *rule;
list_for_each_entry(rule, rules, list) {
if (rule->iifindex == dev->ifindex)
rule->iifindex = -1;
if (rule->oifindex == dev->ifindex)
rule->oifindex = -1;
}
}
static int fib_rules_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct fib_rules_ops *ops;
ASSERT_RTNL();
switch (event) {
case NETDEV_REGISTER:
list_for_each_entry(ops, &net->rules_ops, list)
attach_rules(&ops->rules_list, dev);
break;
case NETDEV_CHANGENAME:
list_for_each_entry(ops, &net->rules_ops, list) {
detach_rules(&ops->rules_list, dev);
attach_rules(&ops->rules_list, dev);
}
break;
case NETDEV_UNREGISTER:
list_for_each_entry(ops, &net->rules_ops, list)
detach_rules(&ops->rules_list, dev);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block fib_rules_notifier = {
.notifier_call = fib_rules_event,
};
static int __net_init fib_rules_net_init(struct net *net)
{
INIT_LIST_HEAD(&net->rules_ops);
spin_lock_init(&net->rules_mod_lock);
return 0;
}
static void __net_exit fib_rules_net_exit(struct net *net)
{
WARN_ON_ONCE(!list_empty(&net->rules_ops));
}
static struct pernet_operations fib_rules_net_ops = {
.init = fib_rules_net_init,
.exit = fib_rules_net_exit,
};
static int __init fib_rules_init(void)
{
int err;
rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0);
err = register_pernet_subsys(&fib_rules_net_ops);
if (err < 0)
goto fail;
err = register_netdevice_notifier(&fib_rules_notifier);
if (err < 0)
goto fail_unregister;
return 0;
fail_unregister:
unregister_pernet_subsys(&fib_rules_net_ops);
fail:
rtnl_unregister(PF_UNSPEC, RTM_NEWRULE);
rtnl_unregister(PF_UNSPEC, RTM_DELRULE);
rtnl_unregister(PF_UNSPEC, RTM_GETRULE);
return err;
}
subsys_initcall(fib_rules_init);