remarkable-linux/net/netfilter/nft_set_rbtree.c
David S. Miller 52a623bd61 Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for your net-next
tree. This batch contains connection tracking updates for the cleanup
iteration path, patches from Florian Westphal:

X) Skip unconfirmed conntracks in nf_ct_iterate_cleanup_net(), just set
   dying bit to let the CPU release them.

X) Add nf_ct_iterate_destroy() to be used on module removal, to kill
   conntrack from all namespace.

X) Restart iteration on hashtable resizing, since both may occur at
   the same time.

X) Use the new nf_ct_iterate_destroy() to remove conntrack with NAT
   mapping on module removal.

X) Use nf_ct_iterate_destroy() to remove conntrack entries helper
   module removal, from Liping Zhang.

X) Use nf_ct_iterate_cleanup_net() to remove the timeout extension
   if user requests this, also from Liping.

X) Add net_ns_barrier() and use it from FTP helper, so make sure
   no concurrent namespace removal happens at the same time while
   the helper module is being removed.

X) Use NFPROTO_MAX in layer 3 conntrack protocol array, to reduce
   module size. Same thing in nf_tables.

Updates for the nf_tables infrastructure:

X) Prepare usage of the extended ACK reporting infrastructure for
   nf_tables.

X) Remove unnecessary forward declaration in nf_tables hash set.

X) Skip set size estimation if number of element is not specified.

X) Changes to accomodate a (faster) unresizable hash set implementation,
   for anonymous sets and dynamic size fixed sets with no timeouts.

X) Faster lookup function for unresizable hash table for 2 and 4
   bytes key.

And, finally, a bunch of asorted small updates and cleanups:

X) Do not hold reference to netdev from ipt_CLUSTER, instead subscribe
   to device events and look up for index from the packet path, this
   is fixing an issue that is present since the very beginning, patch
   from Xin Long.

X) Use nf_register_net_hook() in ipt_CLUSTER, from Florian Westphal.

X) Use ebt_invalid_target() whenever possible in the ebtables tree,
   from Gao Feng.

X) Calm down compilation warning in nf_dup infrastructure, patch from
   stephen hemminger.

X) Statify functions in nftables rt expression, also from stephen.

X) Update Makefile to use canonical method to specify nf_tables-objs.
   From Jike Song.

X) Use nf_conntrack_helpers_register() in amanda and H323.

X) Space cleanup for ctnetlink, from linzhang.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-30 06:27:09 -07:00

338 lines
8.4 KiB
C

/*
* Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/rbtree.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
struct nft_rbtree {
rwlock_t lock;
struct rb_root root;
};
struct nft_rbtree_elem {
struct rb_node node;
struct nft_set_ext ext;
};
static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe)
{
return nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) &&
(*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END);
}
static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
const struct nft_rbtree_elem *interval)
{
return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0;
}
static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
const u32 *key, const struct nft_set_ext **ext)
{
struct nft_rbtree *priv = nft_set_priv(set);
const struct nft_rbtree_elem *rbe, *interval = NULL;
u8 genmask = nft_genmask_cur(net);
const struct rb_node *parent;
const void *this;
int d;
read_lock_bh(&priv->lock);
parent = priv->root.rb_node;
while (parent != NULL) {
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
this = nft_set_ext_key(&rbe->ext);
d = memcmp(this, key, set->klen);
if (d < 0) {
parent = parent->rb_left;
if (interval &&
nft_rbtree_equal(set, this, interval) &&
nft_rbtree_interval_end(this) &&
!nft_rbtree_interval_end(interval))
continue;
interval = rbe;
} else if (d > 0)
parent = parent->rb_right;
else {
if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
}
if (nft_rbtree_interval_end(rbe))
goto out;
read_unlock_bh(&priv->lock);
*ext = &rbe->ext;
return true;
}
}
if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
nft_set_elem_active(&interval->ext, genmask) &&
!nft_rbtree_interval_end(interval)) {
read_unlock_bh(&priv->lock);
*ext = &interval->ext;
return true;
}
out:
read_unlock_bh(&priv->lock);
return false;
}
static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree_elem *new,
struct nft_set_ext **ext)
{
struct nft_rbtree *priv = nft_set_priv(set);
u8 genmask = nft_genmask_next(net);
struct nft_rbtree_elem *rbe;
struct rb_node *parent, **p;
int d;
parent = NULL;
p = &priv->root.rb_node;
while (*p != NULL) {
parent = *p;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
d = memcmp(nft_set_ext_key(&rbe->ext),
nft_set_ext_key(&new->ext),
set->klen);
if (d < 0)
p = &parent->rb_left;
else if (d > 0)
p = &parent->rb_right;
else {
if (nft_rbtree_interval_end(rbe) &&
!nft_rbtree_interval_end(new)) {
p = &parent->rb_left;
} else if (!nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_end(new)) {
p = &parent->rb_right;
} else if (nft_set_elem_active(&rbe->ext, genmask)) {
*ext = &rbe->ext;
return -EEXIST;
} else {
p = &parent->rb_left;
}
}
}
rb_link_node(&new->node, parent, p);
rb_insert_color(&new->node, &priv->root);
return 0;
}
static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem,
struct nft_set_ext **ext)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe = elem->priv;
int err;
write_lock_bh(&priv->lock);
err = __nft_rbtree_insert(net, set, rbe, ext);
write_unlock_bh(&priv->lock);
return err;
}
static void nft_rbtree_remove(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe = elem->priv;
write_lock_bh(&priv->lock);
rb_erase(&rbe->node, &priv->root);
write_unlock_bh(&priv->lock);
}
static void nft_rbtree_activate(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
struct nft_rbtree_elem *rbe = elem->priv;
nft_set_elem_change_active(net, set, &rbe->ext);
}
static bool nft_rbtree_flush(const struct net *net,
const struct nft_set *set, void *priv)
{
struct nft_rbtree_elem *rbe = priv;
nft_set_elem_change_active(net, set, &rbe->ext);
return true;
}
static void *nft_rbtree_deactivate(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
const struct nft_rbtree *priv = nft_set_priv(set);
const struct rb_node *parent = priv->root.rb_node;
struct nft_rbtree_elem *rbe, *this = elem->priv;
u8 genmask = nft_genmask_next(net);
int d;
while (parent != NULL) {
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val,
set->klen);
if (d < 0)
parent = parent->rb_left;
else if (d > 0)
parent = parent->rb_right;
else {
if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
}
if (nft_rbtree_interval_end(rbe) &&
!nft_rbtree_interval_end(this)) {
parent = parent->rb_left;
continue;
} else if (!nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_end(this)) {
parent = parent->rb_right;
continue;
}
nft_rbtree_flush(net, set, rbe);
return rbe;
}
}
return NULL;
}
static void nft_rbtree_walk(const struct nft_ctx *ctx,
struct nft_set *set,
struct nft_set_iter *iter)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe;
struct nft_set_elem elem;
struct rb_node *node;
read_lock_bh(&priv->lock);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
if (iter->count < iter->skip)
goto cont;
if (!nft_set_elem_active(&rbe->ext, iter->genmask))
goto cont;
elem.priv = rbe;
iter->err = iter->fn(ctx, set, iter, &elem);
if (iter->err < 0) {
read_unlock_bh(&priv->lock);
return;
}
cont:
iter->count++;
}
read_unlock_bh(&priv->lock);
}
static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[],
const struct nft_set_desc *desc)
{
return sizeof(struct nft_rbtree);
}
static int nft_rbtree_init(const struct nft_set *set,
const struct nft_set_desc *desc,
const struct nlattr * const nla[])
{
struct nft_rbtree *priv = nft_set_priv(set);
rwlock_init(&priv->lock);
priv->root = RB_ROOT;
return 0;
}
static void nft_rbtree_destroy(const struct nft_set *set)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe;
struct rb_node *node;
while ((node = priv->root.rb_node) != NULL) {
rb_erase(node, &priv->root);
rbe = rb_entry(node, struct nft_rbtree_elem, node);
nft_set_elem_destroy(set, rbe, true);
}
}
static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
struct nft_set_estimate *est)
{
if (desc->size)
est->size = sizeof(struct nft_rbtree) +
desc->size * sizeof(struct nft_rbtree_elem);
else
est->size = ~0;
est->lookup = NFT_SET_CLASS_O_LOG_N;
est->space = NFT_SET_CLASS_O_N;
return true;
}
static struct nft_set_type nft_rbtree_type;
static struct nft_set_ops nft_rbtree_ops __read_mostly = {
.type = &nft_rbtree_type,
.privsize = nft_rbtree_privsize,
.elemsize = offsetof(struct nft_rbtree_elem, ext),
.estimate = nft_rbtree_estimate,
.init = nft_rbtree_init,
.destroy = nft_rbtree_destroy,
.insert = nft_rbtree_insert,
.remove = nft_rbtree_remove,
.deactivate = nft_rbtree_deactivate,
.flush = nft_rbtree_flush,
.activate = nft_rbtree_activate,
.lookup = nft_rbtree_lookup,
.walk = nft_rbtree_walk,
.features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT,
};
static struct nft_set_type nft_rbtree_type __read_mostly = {
.ops = &nft_rbtree_ops,
.owner = THIS_MODULE,
};
static int __init nft_rbtree_module_init(void)
{
return nft_register_set(&nft_rbtree_type);
}
static void __exit nft_rbtree_module_exit(void)
{
nft_unregister_set(&nft_rbtree_type);
}
module_init(nft_rbtree_module_init);
module_exit(nft_rbtree_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_SET();