4ef360dd6a
In order to determine allocation size of set, ->privsize is invoked.
At this point, both desc->size and size of each data structure of set
are used. desc->size means number of element that is given by user.
desc->size is u32 type. so that upperlimit of set element is 4294967295.
but return type of ->privsize is also u32. hence overflow can occurred.
test commands:
%nft add table ip filter
%nft add set ip filter hash1 { type ipv4_addr \; size 4294967295 \; }
%nft list ruleset
splat looks like:
[ 1239.202910] kasan: CONFIG_KASAN_INLINE enabled
[ 1239.208788] kasan: GPF could be caused by NULL-ptr deref or user memory access
[ 1239.217625] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 1239.219329] CPU: 0 PID: 1603 Comm: nft Not tainted 4.18.0-rc5+ #7
[ 1239.229091] RIP: 0010:nft_hash_walk+0x1d2/0x310 [nf_tables_set]
[ 1239.229091] Code: 84 d2 7f 10 4c 89 e7 89 44 24 38 e8 d8 5a 17 e0 8b 44 24 38 48 8d 7b 10 41 0f b6 0c 24 48 89 fa 48 89 fe 48 c1 ea 03 83 e6 07 <42> 0f b6 14 3a 40 38 f2 7f 1a 84 d2 74 16
[ 1239.229091] RSP: 0018:ffff8801118cf358 EFLAGS: 00010246
[ 1239.229091] RAX: 0000000000000000 RBX: 0000000000020400 RCX: 0000000000000001
[ 1239.229091] RDX: 0000000000004082 RSI: 0000000000000000 RDI: 0000000000020410
[ 1239.229091] RBP: ffff880114d5a988 R08: 0000000000007e94 R09: ffff880114dd8030
[ 1239.229091] R10: ffff880114d5a988 R11: ffffed00229bb006 R12: ffff8801118cf4d0
[ 1239.229091] R13: ffff8801118cf4d8 R14: 0000000000000000 R15: dffffc0000000000
[ 1239.229091] FS: 00007f5a8fe0b700(0000) GS:ffff88011b600000(0000) knlGS:0000000000000000
[ 1239.229091] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1239.229091] CR2: 00007f5a8ecc27b0 CR3: 000000010608e000 CR4: 00000000001006f0
[ 1239.229091] Call Trace:
[ 1239.229091] ? nft_hash_remove+0xf0/0xf0 [nf_tables_set]
[ 1239.229091] ? memset+0x1f/0x40
[ 1239.229091] ? __nla_reserve+0x9f/0xb0
[ 1239.229091] ? memcpy+0x34/0x50
[ 1239.229091] nf_tables_dump_set+0x9a1/0xda0 [nf_tables]
[ 1239.229091] ? __kmalloc_reserve.isra.29+0x2e/0xa0
[ 1239.229091] ? nft_chain_hash_obj+0x630/0x630 [nf_tables]
[ 1239.229091] ? nf_tables_commit+0x2c60/0x2c60 [nf_tables]
[ 1239.229091] netlink_dump+0x470/0xa20
[ 1239.229091] __netlink_dump_start+0x5ae/0x690
[ 1239.229091] nft_netlink_dump_start_rcu+0xd1/0x160 [nf_tables]
[ 1239.229091] nf_tables_getsetelem+0x2e5/0x4b0 [nf_tables]
[ 1239.229091] ? nft_get_set_elem+0x440/0x440 [nf_tables]
[ 1239.229091] ? nft_chain_hash_obj+0x630/0x630 [nf_tables]
[ 1239.229091] ? nf_tables_dump_obj_done+0x70/0x70 [nf_tables]
[ 1239.229091] ? nla_parse+0xab/0x230
[ 1239.229091] ? nft_get_set_elem+0x440/0x440 [nf_tables]
[ 1239.229091] nfnetlink_rcv_msg+0x7f0/0xab0 [nfnetlink]
[ 1239.229091] ? nfnetlink_bind+0x1d0/0x1d0 [nfnetlink]
[ 1239.229091] ? debug_show_all_locks+0x290/0x290
[ 1239.229091] ? sched_clock_cpu+0x132/0x170
[ 1239.229091] ? find_held_lock+0x39/0x1b0
[ 1239.229091] ? sched_clock_local+0x10d/0x130
[ 1239.229091] netlink_rcv_skb+0x211/0x320
[ 1239.229091] ? nfnetlink_bind+0x1d0/0x1d0 [nfnetlink]
[ 1239.229091] ? netlink_ack+0x7b0/0x7b0
[ 1239.229091] ? ns_capable_common+0x6e/0x110
[ 1239.229091] nfnetlink_rcv+0x2d1/0x310 [nfnetlink]
[ 1239.229091] ? nfnetlink_rcv_batch+0x10f0/0x10f0 [nfnetlink]
[ 1239.229091] ? netlink_deliver_tap+0x829/0x930
[ 1239.229091] ? lock_acquire+0x265/0x2e0
[ 1239.229091] netlink_unicast+0x406/0x520
[ 1239.509725] ? netlink_attachskb+0x5b0/0x5b0
[ 1239.509725] ? find_held_lock+0x39/0x1b0
[ 1239.509725] netlink_sendmsg+0x987/0xa20
[ 1239.509725] ? netlink_unicast+0x520/0x520
[ 1239.509725] ? _copy_from_user+0xa9/0xc0
[ 1239.509725] __sys_sendto+0x21a/0x2c0
[ 1239.509725] ? __ia32_sys_getpeername+0xa0/0xa0
[ 1239.509725] ? retint_kernel+0x10/0x10
[ 1239.509725] ? sched_clock_cpu+0x132/0x170
[ 1239.509725] ? find_held_lock+0x39/0x1b0
[ 1239.509725] ? lock_downgrade+0x540/0x540
[ 1239.509725] ? up_read+0x1c/0x100
[ 1239.509725] ? __do_page_fault+0x763/0x970
[ 1239.509725] ? retint_user+0x18/0x18
[ 1239.509725] __x64_sys_sendto+0x177/0x180
[ 1239.509725] do_syscall_64+0xaa/0x360
[ 1239.509725] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 1239.509725] RIP: 0033:0x7f5a8f468e03
[ 1239.509725] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb d0 0f 1f 84 00 00 00 00 00 83 3d 49 c9 2b 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8
[ 1239.509725] RSP: 002b:00007ffd78d0b778 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[ 1239.509725] RAX: ffffffffffffffda RBX: 00007ffd78d0c890 RCX: 00007f5a8f468e03
[ 1239.509725] RDX: 0000000000000034 RSI: 00007ffd78d0b7e0 RDI: 0000000000000003
[ 1239.509725] RBP: 00007ffd78d0b7d0 R08: 00007f5a8f15c160 R09: 000000000000000c
[ 1239.509725] R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffd78d0b7e0
[ 1239.509725] R13: 0000000000000034 R14: 00007f5a8f9aff60 R15: 00005648040094b0
[ 1239.509725] Modules linked in: nf_tables_set nf_tables nfnetlink ip_tables x_tables
[ 1239.670713] ---[ end trace 39375adcda140f11 ]---
[ 1239.676016] RIP: 0010:nft_hash_walk+0x1d2/0x310 [nf_tables_set]
[ 1239.682834] Code: 84 d2 7f 10 4c 89 e7 89 44 24 38 e8 d8 5a 17 e0 8b 44 24 38 48 8d 7b 10 41 0f b6 0c 24 48 89 fa 48 89 fe 48 c1 ea 03 83 e6 07 <42> 0f b6 14 3a 40 38 f2 7f 1a 84 d2 74 16
[ 1239.705108] RSP: 0018:ffff8801118cf358 EFLAGS: 00010246
[ 1239.711115] RAX: 0000000000000000 RBX: 0000000000020400 RCX: 0000000000000001
[ 1239.719269] RDX: 0000000000004082 RSI: 0000000000000000 RDI: 0000000000020410
[ 1239.727401] RBP: ffff880114d5a988 R08: 0000000000007e94 R09: ffff880114dd8030
[ 1239.735530] R10: ffff880114d5a988 R11: ffffed00229bb006 R12: ffff8801118cf4d0
[ 1239.743658] R13: ffff8801118cf4d8 R14: 0000000000000000 R15: dffffc0000000000
[ 1239.751785] FS: 00007f5a8fe0b700(0000) GS:ffff88011b600000(0000) knlGS:0000000000000000
[ 1239.760993] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1239.767560] CR2: 00007f5a8ecc27b0 CR3: 000000010608e000 CR4: 00000000001006f0
[ 1239.775679] Kernel panic - not syncing: Fatal exception
[ 1239.776630] Kernel Offset: 0x1f000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[ 1239.776630] Rebooting in 5 seconds..
Fixes: 20a69341f2
("netfilter: nf_tables: add netlink set API")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
720 lines
17 KiB
C
720 lines
17 KiB
C
/*
|
|
* Copyright (c) 2008-2014 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/log2.h>
|
|
#include <linux/jhash.h>
|
|
#include <linux/netlink.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/rhashtable.h>
|
|
#include <linux/netfilter.h>
|
|
#include <linux/netfilter/nf_tables.h>
|
|
#include <net/netfilter/nf_tables.h>
|
|
|
|
/* We target a hash table size of 4, element hint is 75% of final size */
|
|
#define NFT_RHASH_ELEMENT_HINT 3
|
|
|
|
struct nft_rhash {
|
|
struct rhashtable ht;
|
|
struct delayed_work gc_work;
|
|
};
|
|
|
|
struct nft_rhash_elem {
|
|
struct rhash_head node;
|
|
struct nft_set_ext ext;
|
|
};
|
|
|
|
struct nft_rhash_cmp_arg {
|
|
const struct nft_set *set;
|
|
const u32 *key;
|
|
u8 genmask;
|
|
};
|
|
|
|
static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed)
|
|
{
|
|
const struct nft_rhash_cmp_arg *arg = data;
|
|
|
|
return jhash(arg->key, len, seed);
|
|
}
|
|
|
|
static inline u32 nft_rhash_obj(const void *data, u32 len, u32 seed)
|
|
{
|
|
const struct nft_rhash_elem *he = data;
|
|
|
|
return jhash(nft_set_ext_key(&he->ext), len, seed);
|
|
}
|
|
|
|
static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
|
|
const void *ptr)
|
|
{
|
|
const struct nft_rhash_cmp_arg *x = arg->key;
|
|
const struct nft_rhash_elem *he = ptr;
|
|
|
|
if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen))
|
|
return 1;
|
|
if (nft_set_elem_expired(&he->ext))
|
|
return 1;
|
|
if (!nft_set_elem_active(&he->ext, x->genmask))
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
static const struct rhashtable_params nft_rhash_params = {
|
|
.head_offset = offsetof(struct nft_rhash_elem, node),
|
|
.hashfn = nft_rhash_key,
|
|
.obj_hashfn = nft_rhash_obj,
|
|
.obj_cmpfn = nft_rhash_cmp,
|
|
.automatic_shrinking = true,
|
|
};
|
|
|
|
static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
|
|
const u32 *key, const struct nft_set_ext **ext)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
const struct nft_rhash_elem *he;
|
|
struct nft_rhash_cmp_arg arg = {
|
|
.genmask = nft_genmask_cur(net),
|
|
.set = set,
|
|
.key = key,
|
|
};
|
|
|
|
he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params);
|
|
if (he != NULL)
|
|
*ext = &he->ext;
|
|
|
|
return !!he;
|
|
}
|
|
|
|
static void *nft_rhash_get(const struct net *net, const struct nft_set *set,
|
|
const struct nft_set_elem *elem, unsigned int flags)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct nft_rhash_elem *he;
|
|
struct nft_rhash_cmp_arg arg = {
|
|
.genmask = nft_genmask_cur(net),
|
|
.set = set,
|
|
.key = elem->key.val.data,
|
|
};
|
|
|
|
he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params);
|
|
if (he != NULL)
|
|
return he;
|
|
|
|
return ERR_PTR(-ENOENT);
|
|
}
|
|
|
|
static bool nft_rhash_update(struct nft_set *set, const u32 *key,
|
|
void *(*new)(struct nft_set *,
|
|
const struct nft_expr *,
|
|
struct nft_regs *regs),
|
|
const struct nft_expr *expr,
|
|
struct nft_regs *regs,
|
|
const struct nft_set_ext **ext)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct nft_rhash_elem *he, *prev;
|
|
struct nft_rhash_cmp_arg arg = {
|
|
.genmask = NFT_GENMASK_ANY,
|
|
.set = set,
|
|
.key = key,
|
|
};
|
|
|
|
he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params);
|
|
if (he != NULL)
|
|
goto out;
|
|
|
|
he = new(set, expr, regs);
|
|
if (he == NULL)
|
|
goto err1;
|
|
|
|
prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
|
|
nft_rhash_params);
|
|
if (IS_ERR(prev))
|
|
goto err2;
|
|
|
|
/* Another cpu may race to insert the element with the same key */
|
|
if (prev) {
|
|
nft_set_elem_destroy(set, he, true);
|
|
he = prev;
|
|
}
|
|
|
|
out:
|
|
*ext = &he->ext;
|
|
return true;
|
|
|
|
err2:
|
|
nft_set_elem_destroy(set, he, true);
|
|
err1:
|
|
return false;
|
|
}
|
|
|
|
static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
|
|
const struct nft_set_elem *elem,
|
|
struct nft_set_ext **ext)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct nft_rhash_elem *he = elem->priv;
|
|
struct nft_rhash_cmp_arg arg = {
|
|
.genmask = nft_genmask_next(net),
|
|
.set = set,
|
|
.key = elem->key.val.data,
|
|
};
|
|
struct nft_rhash_elem *prev;
|
|
|
|
prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
|
|
nft_rhash_params);
|
|
if (IS_ERR(prev))
|
|
return PTR_ERR(prev);
|
|
if (prev) {
|
|
*ext = &prev->ext;
|
|
return -EEXIST;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void nft_rhash_activate(const struct net *net, const struct nft_set *set,
|
|
const struct nft_set_elem *elem)
|
|
{
|
|
struct nft_rhash_elem *he = elem->priv;
|
|
|
|
nft_set_elem_change_active(net, set, &he->ext);
|
|
nft_set_elem_clear_busy(&he->ext);
|
|
}
|
|
|
|
static bool nft_rhash_flush(const struct net *net,
|
|
const struct nft_set *set, void *priv)
|
|
{
|
|
struct nft_rhash_elem *he = priv;
|
|
|
|
if (!nft_set_elem_mark_busy(&he->ext) ||
|
|
!nft_is_active(net, &he->ext)) {
|
|
nft_set_elem_change_active(net, set, &he->ext);
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
static void *nft_rhash_deactivate(const struct net *net,
|
|
const struct nft_set *set,
|
|
const struct nft_set_elem *elem)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct nft_rhash_elem *he;
|
|
struct nft_rhash_cmp_arg arg = {
|
|
.genmask = nft_genmask_next(net),
|
|
.set = set,
|
|
.key = elem->key.val.data,
|
|
};
|
|
|
|
rcu_read_lock();
|
|
he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params);
|
|
if (he != NULL &&
|
|
!nft_rhash_flush(net, set, he))
|
|
he = NULL;
|
|
|
|
rcu_read_unlock();
|
|
|
|
return he;
|
|
}
|
|
|
|
static void nft_rhash_remove(const struct net *net,
|
|
const struct nft_set *set,
|
|
const struct nft_set_elem *elem)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct nft_rhash_elem *he = elem->priv;
|
|
|
|
rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params);
|
|
}
|
|
|
|
static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
|
|
struct nft_set_iter *iter)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct nft_rhash_elem *he;
|
|
struct rhashtable_iter hti;
|
|
struct nft_set_elem elem;
|
|
int err;
|
|
|
|
err = rhashtable_walk_init(&priv->ht, &hti, GFP_ATOMIC);
|
|
iter->err = err;
|
|
if (err)
|
|
return;
|
|
|
|
rhashtable_walk_start(&hti);
|
|
|
|
while ((he = rhashtable_walk_next(&hti))) {
|
|
if (IS_ERR(he)) {
|
|
err = PTR_ERR(he);
|
|
if (err != -EAGAIN) {
|
|
iter->err = err;
|
|
goto out;
|
|
}
|
|
|
|
continue;
|
|
}
|
|
|
|
if (iter->count < iter->skip)
|
|
goto cont;
|
|
if (nft_set_elem_expired(&he->ext))
|
|
goto cont;
|
|
if (!nft_set_elem_active(&he->ext, iter->genmask))
|
|
goto cont;
|
|
|
|
elem.priv = he;
|
|
|
|
iter->err = iter->fn(ctx, set, iter, &elem);
|
|
if (iter->err < 0)
|
|
goto out;
|
|
|
|
cont:
|
|
iter->count++;
|
|
}
|
|
|
|
out:
|
|
rhashtable_walk_stop(&hti);
|
|
rhashtable_walk_exit(&hti);
|
|
}
|
|
|
|
static void nft_rhash_gc(struct work_struct *work)
|
|
{
|
|
struct nft_set *set;
|
|
struct nft_rhash_elem *he;
|
|
struct nft_rhash *priv;
|
|
struct nft_set_gc_batch *gcb = NULL;
|
|
struct rhashtable_iter hti;
|
|
int err;
|
|
|
|
priv = container_of(work, struct nft_rhash, gc_work.work);
|
|
set = nft_set_container_of(priv);
|
|
|
|
err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL);
|
|
if (err)
|
|
goto schedule;
|
|
|
|
rhashtable_walk_start(&hti);
|
|
|
|
while ((he = rhashtable_walk_next(&hti))) {
|
|
if (IS_ERR(he)) {
|
|
if (PTR_ERR(he) != -EAGAIN)
|
|
goto out;
|
|
continue;
|
|
}
|
|
|
|
if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPR)) {
|
|
struct nft_expr *expr = nft_set_ext_expr(&he->ext);
|
|
|
|
if (expr->ops->gc &&
|
|
expr->ops->gc(read_pnet(&set->net), expr))
|
|
goto gc;
|
|
}
|
|
if (!nft_set_elem_expired(&he->ext))
|
|
continue;
|
|
gc:
|
|
if (nft_set_elem_mark_busy(&he->ext))
|
|
continue;
|
|
|
|
gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
|
|
if (gcb == NULL)
|
|
goto out;
|
|
rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params);
|
|
atomic_dec(&set->nelems);
|
|
nft_set_gc_batch_add(gcb, he);
|
|
}
|
|
out:
|
|
rhashtable_walk_stop(&hti);
|
|
rhashtable_walk_exit(&hti);
|
|
|
|
nft_set_gc_batch_complete(gcb);
|
|
schedule:
|
|
queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
|
|
nft_set_gc_interval(set));
|
|
}
|
|
|
|
static u64 nft_rhash_privsize(const struct nlattr * const nla[],
|
|
const struct nft_set_desc *desc)
|
|
{
|
|
return sizeof(struct nft_rhash);
|
|
}
|
|
|
|
static void nft_rhash_gc_init(const struct nft_set *set)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
|
|
queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
|
|
nft_set_gc_interval(set));
|
|
}
|
|
|
|
static int nft_rhash_init(const struct nft_set *set,
|
|
const struct nft_set_desc *desc,
|
|
const struct nlattr * const tb[])
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
struct rhashtable_params params = nft_rhash_params;
|
|
int err;
|
|
|
|
params.nelem_hint = desc->size ?: NFT_RHASH_ELEMENT_HINT;
|
|
params.key_len = set->klen;
|
|
|
|
err = rhashtable_init(&priv->ht, ¶ms);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc);
|
|
if (set->flags & NFT_SET_TIMEOUT)
|
|
nft_rhash_gc_init(set);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void nft_rhash_elem_destroy(void *ptr, void *arg)
|
|
{
|
|
nft_set_elem_destroy(arg, ptr, true);
|
|
}
|
|
|
|
static void nft_rhash_destroy(const struct nft_set *set)
|
|
{
|
|
struct nft_rhash *priv = nft_set_priv(set);
|
|
|
|
cancel_delayed_work_sync(&priv->gc_work);
|
|
rcu_barrier();
|
|
rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
|
|
(void *)set);
|
|
}
|
|
|
|
static u32 nft_hash_buckets(u32 size)
|
|
{
|
|
return roundup_pow_of_two(size * 4 / 3);
|
|
}
|
|
|
|
static bool nft_rhash_estimate(const struct nft_set_desc *desc, u32 features,
|
|
struct nft_set_estimate *est)
|
|
{
|
|
est->size = ~0;
|
|
est->lookup = NFT_SET_CLASS_O_1;
|
|
est->space = NFT_SET_CLASS_O_N;
|
|
|
|
return true;
|
|
}
|
|
|
|
struct nft_hash {
|
|
u32 seed;
|
|
u32 buckets;
|
|
struct hlist_head table[];
|
|
};
|
|
|
|
struct nft_hash_elem {
|
|
struct hlist_node node;
|
|
struct nft_set_ext ext;
|
|
};
|
|
|
|
static bool nft_hash_lookup(const struct net *net, const struct nft_set *set,
|
|
const u32 *key, const struct nft_set_ext **ext)
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
u8 genmask = nft_genmask_cur(net);
|
|
const struct nft_hash_elem *he;
|
|
u32 hash;
|
|
|
|
hash = jhash(key, set->klen, priv->seed);
|
|
hash = reciprocal_scale(hash, priv->buckets);
|
|
hlist_for_each_entry_rcu(he, &priv->table[hash], node) {
|
|
if (!memcmp(nft_set_ext_key(&he->ext), key, set->klen) &&
|
|
nft_set_elem_active(&he->ext, genmask)) {
|
|
*ext = &he->ext;
|
|
return true;
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
static void *nft_hash_get(const struct net *net, const struct nft_set *set,
|
|
const struct nft_set_elem *elem, unsigned int flags)
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
u8 genmask = nft_genmask_cur(net);
|
|
struct nft_hash_elem *he;
|
|
u32 hash;
|
|
|
|
hash = jhash(elem->key.val.data, set->klen, priv->seed);
|
|
hash = reciprocal_scale(hash, priv->buckets);
|
|
hlist_for_each_entry_rcu(he, &priv->table[hash], node) {
|
|
if (!memcmp(nft_set_ext_key(&he->ext), elem->key.val.data, set->klen) &&
|
|
nft_set_elem_active(&he->ext, genmask))
|
|
return he;
|
|
}
|
|
return ERR_PTR(-ENOENT);
|
|
}
|
|
|
|
/* nft_hash_select_ops() makes sure key size can be either 2 or 4 bytes . */
|
|
static inline u32 nft_hash_key(const u32 *key, u32 klen)
|
|
{
|
|
if (klen == 4)
|
|
return *key;
|
|
|
|
return *(u16 *)key;
|
|
}
|
|
|
|
static bool nft_hash_lookup_fast(const struct net *net,
|
|
const struct nft_set *set,
|
|
const u32 *key, const struct nft_set_ext **ext)
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
u8 genmask = nft_genmask_cur(net);
|
|
const struct nft_hash_elem *he;
|
|
u32 hash, k1, k2;
|
|
|
|
k1 = nft_hash_key(key, set->klen);
|
|
hash = jhash_1word(k1, priv->seed);
|
|
hash = reciprocal_scale(hash, priv->buckets);
|
|
hlist_for_each_entry_rcu(he, &priv->table[hash], node) {
|
|
k2 = nft_hash_key(nft_set_ext_key(&he->ext)->data, set->klen);
|
|
if (k1 == k2 &&
|
|
nft_set_elem_active(&he->ext, genmask)) {
|
|
*ext = &he->ext;
|
|
return true;
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
static int nft_hash_insert(const struct net *net, const struct nft_set *set,
|
|
const struct nft_set_elem *elem,
|
|
struct nft_set_ext **ext)
|
|
{
|
|
struct nft_hash_elem *this = elem->priv, *he;
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
u8 genmask = nft_genmask_next(net);
|
|
u32 hash;
|
|
|
|
hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed);
|
|
hash = reciprocal_scale(hash, priv->buckets);
|
|
hlist_for_each_entry(he, &priv->table[hash], node) {
|
|
if (!memcmp(nft_set_ext_key(&this->ext),
|
|
nft_set_ext_key(&he->ext), set->klen) &&
|
|
nft_set_elem_active(&he->ext, genmask)) {
|
|
*ext = &he->ext;
|
|
return -EEXIST;
|
|
}
|
|
}
|
|
hlist_add_head_rcu(&this->node, &priv->table[hash]);
|
|
return 0;
|
|
}
|
|
|
|
static void nft_hash_activate(const struct net *net, const struct nft_set *set,
|
|
const struct nft_set_elem *elem)
|
|
{
|
|
struct nft_hash_elem *he = elem->priv;
|
|
|
|
nft_set_elem_change_active(net, set, &he->ext);
|
|
}
|
|
|
|
static bool nft_hash_flush(const struct net *net,
|
|
const struct nft_set *set, void *priv)
|
|
{
|
|
struct nft_hash_elem *he = priv;
|
|
|
|
nft_set_elem_change_active(net, set, &he->ext);
|
|
return true;
|
|
}
|
|
|
|
static void *nft_hash_deactivate(const struct net *net,
|
|
const struct nft_set *set,
|
|
const struct nft_set_elem *elem)
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
struct nft_hash_elem *this = elem->priv, *he;
|
|
u8 genmask = nft_genmask_next(net);
|
|
u32 hash;
|
|
|
|
hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed);
|
|
hash = reciprocal_scale(hash, priv->buckets);
|
|
hlist_for_each_entry(he, &priv->table[hash], node) {
|
|
if (!memcmp(nft_set_ext_key(&this->ext), &elem->key.val,
|
|
set->klen) &&
|
|
nft_set_elem_active(&he->ext, genmask)) {
|
|
nft_set_elem_change_active(net, set, &he->ext);
|
|
return he;
|
|
}
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static void nft_hash_remove(const struct net *net,
|
|
const struct nft_set *set,
|
|
const struct nft_set_elem *elem)
|
|
{
|
|
struct nft_hash_elem *he = elem->priv;
|
|
|
|
hlist_del_rcu(&he->node);
|
|
}
|
|
|
|
static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set,
|
|
struct nft_set_iter *iter)
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
struct nft_hash_elem *he;
|
|
struct nft_set_elem elem;
|
|
int i;
|
|
|
|
for (i = 0; i < priv->buckets; i++) {
|
|
hlist_for_each_entry_rcu(he, &priv->table[i], node) {
|
|
if (iter->count < iter->skip)
|
|
goto cont;
|
|
if (!nft_set_elem_active(&he->ext, iter->genmask))
|
|
goto cont;
|
|
|
|
elem.priv = he;
|
|
|
|
iter->err = iter->fn(ctx, set, iter, &elem);
|
|
if (iter->err < 0)
|
|
return;
|
|
cont:
|
|
iter->count++;
|
|
}
|
|
}
|
|
}
|
|
|
|
static u64 nft_hash_privsize(const struct nlattr * const nla[],
|
|
const struct nft_set_desc *desc)
|
|
{
|
|
return sizeof(struct nft_hash) +
|
|
nft_hash_buckets(desc->size) * sizeof(struct hlist_head);
|
|
}
|
|
|
|
static int nft_hash_init(const struct nft_set *set,
|
|
const struct nft_set_desc *desc,
|
|
const struct nlattr * const tb[])
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
|
|
priv->buckets = nft_hash_buckets(desc->size);
|
|
get_random_bytes(&priv->seed, sizeof(priv->seed));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void nft_hash_destroy(const struct nft_set *set)
|
|
{
|
|
struct nft_hash *priv = nft_set_priv(set);
|
|
struct nft_hash_elem *he;
|
|
struct hlist_node *next;
|
|
int i;
|
|
|
|
for (i = 0; i < priv->buckets; i++) {
|
|
hlist_for_each_entry_safe(he, next, &priv->table[i], node) {
|
|
hlist_del_rcu(&he->node);
|
|
nft_set_elem_destroy(set, he, true);
|
|
}
|
|
}
|
|
}
|
|
|
|
static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
|
|
struct nft_set_estimate *est)
|
|
{
|
|
if (!desc->size)
|
|
return false;
|
|
|
|
if (desc->klen == 4)
|
|
return false;
|
|
|
|
est->size = sizeof(struct nft_hash) +
|
|
nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
|
|
desc->size * sizeof(struct nft_hash_elem);
|
|
est->lookup = NFT_SET_CLASS_O_1;
|
|
est->space = NFT_SET_CLASS_O_N;
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features,
|
|
struct nft_set_estimate *est)
|
|
{
|
|
if (!desc->size)
|
|
return false;
|
|
|
|
if (desc->klen != 4)
|
|
return false;
|
|
|
|
est->size = sizeof(struct nft_hash) +
|
|
nft_hash_buckets(desc->size) * sizeof(struct hlist_head) +
|
|
desc->size * sizeof(struct nft_hash_elem);
|
|
est->lookup = NFT_SET_CLASS_O_1;
|
|
est->space = NFT_SET_CLASS_O_N;
|
|
|
|
return true;
|
|
}
|
|
|
|
struct nft_set_type nft_set_rhash_type __read_mostly = {
|
|
.owner = THIS_MODULE,
|
|
.features = NFT_SET_MAP | NFT_SET_OBJECT |
|
|
NFT_SET_TIMEOUT | NFT_SET_EVAL,
|
|
.ops = {
|
|
.privsize = nft_rhash_privsize,
|
|
.elemsize = offsetof(struct nft_rhash_elem, ext),
|
|
.estimate = nft_rhash_estimate,
|
|
.init = nft_rhash_init,
|
|
.gc_init = nft_rhash_gc_init,
|
|
.destroy = nft_rhash_destroy,
|
|
.insert = nft_rhash_insert,
|
|
.activate = nft_rhash_activate,
|
|
.deactivate = nft_rhash_deactivate,
|
|
.flush = nft_rhash_flush,
|
|
.remove = nft_rhash_remove,
|
|
.lookup = nft_rhash_lookup,
|
|
.update = nft_rhash_update,
|
|
.walk = nft_rhash_walk,
|
|
.get = nft_rhash_get,
|
|
},
|
|
};
|
|
|
|
struct nft_set_type nft_set_hash_type __read_mostly = {
|
|
.owner = THIS_MODULE,
|
|
.features = NFT_SET_MAP | NFT_SET_OBJECT,
|
|
.ops = {
|
|
.privsize = nft_hash_privsize,
|
|
.elemsize = offsetof(struct nft_hash_elem, ext),
|
|
.estimate = nft_hash_estimate,
|
|
.init = nft_hash_init,
|
|
.destroy = nft_hash_destroy,
|
|
.insert = nft_hash_insert,
|
|
.activate = nft_hash_activate,
|
|
.deactivate = nft_hash_deactivate,
|
|
.flush = nft_hash_flush,
|
|
.remove = nft_hash_remove,
|
|
.lookup = nft_hash_lookup,
|
|
.walk = nft_hash_walk,
|
|
.get = nft_hash_get,
|
|
},
|
|
};
|
|
|
|
struct nft_set_type nft_set_hash_fast_type __read_mostly = {
|
|
.owner = THIS_MODULE,
|
|
.features = NFT_SET_MAP | NFT_SET_OBJECT,
|
|
.ops = {
|
|
.privsize = nft_hash_privsize,
|
|
.elemsize = offsetof(struct nft_hash_elem, ext),
|
|
.estimate = nft_hash_fast_estimate,
|
|
.init = nft_hash_init,
|
|
.destroy = nft_hash_destroy,
|
|
.insert = nft_hash_insert,
|
|
.activate = nft_hash_activate,
|
|
.deactivate = nft_hash_deactivate,
|
|
.flush = nft_hash_flush,
|
|
.remove = nft_hash_remove,
|
|
.lookup = nft_hash_lookup_fast,
|
|
.walk = nft_hash_walk,
|
|
.get = nft_hash_get,
|
|
},
|
|
};
|