From: Pablo Neira Ayuso Date: Tue, 9 Aug 2016 14:11:46 +0000 (+0200) Subject: netfilter: nf_tables: rename set implementations X-Git-Url: http://drtracing.org/?a=commitdiff_plain;h=0ed6389c483dc77cdbdd48de0ca7ce41723dd667;p=deliverable%2Flinux.git netfilter: nf_tables: rename set implementations Use nft_set_* prefix for backend set implementations, thus we can use nft_hash for the new hash expression. Signed-off-by: Pablo Neira Ayuso --- diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 9266ceebd112..e5740e108a0b 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -481,13 +481,13 @@ config NFT_CT This option adds the "meta" expression that you can use to match connection tracking information such as the flow state. -config NFT_RBTREE +config NFT_SET_RBTREE tristate "Netfilter nf_tables rbtree set module" help This option adds the "rbtree" set type (Red Black tree) that is used to build interval-based sets. -config NFT_HASH +config NFT_SET_HASH tristate "Netfilter nf_tables hash set module" help This option adds the "hash" set type that is used to build one-way diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 69134541d65b..101fb859203c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -86,8 +86,8 @@ obj-$(CONFIG_NFT_NAT) += nft_nat.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o -obj-$(CONFIG_NFT_RBTREE) += nft_rbtree.o -obj-$(CONFIG_NFT_HASH) += nft_hash.o +obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o +obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c deleted file mode 100644 index 564fa7929ed5..000000000000 --- a/net/netfilter/nft_hash.c +++ /dev/null @@ -1,395 +0,0 @@ -/* - * Copyright (c) 2008-2014 Patrick McHardy - * - * 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 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* We target a hash table size of 4, element hint is 75% of final size */ -#define NFT_HASH_ELEMENT_HINT 3 - -struct nft_hash { - struct rhashtable ht; - struct delayed_work gc_work; -}; - -struct nft_hash_elem { - struct rhash_head node; - struct nft_set_ext ext; -}; - -struct nft_hash_cmp_arg { - const struct nft_set *set; - const u32 *key; - u8 genmask; -}; - -static const struct rhashtable_params nft_hash_params; - -static inline u32 nft_hash_key(const void *data, u32 len, u32 seed) -{ - const struct nft_hash_cmp_arg *arg = data; - - return jhash(arg->key, len, seed); -} - -static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) -{ - const struct nft_hash_elem *he = data; - - return jhash(nft_set_ext_key(&he->ext), len, seed); -} - -static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct nft_hash_cmp_arg *x = arg->key; - const struct nft_hash_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 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); - const struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_cur(net), - .set = set, - .key = key, - }; - - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); - if (he != NULL) - *ext = &he->ext; - - return !!he; -} - -static bool nft_hash_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_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct nft_hash_cmp_arg arg = { - .genmask = NFT_GENMASK_ANY, - .set = set, - .key = key, - }; - - he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); - if (he != NULL) - goto out; - - he = new(set, expr, regs); - if (he == NULL) - goto err1; - if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params)) - goto err2; -out: - *ext = &he->ext; - return true; - -err2: - nft_set_elem_destroy(set, he); -err1: - return false; -} - -static int nft_hash_insert(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 *he = elem->priv; - struct nft_hash_cmp_arg arg = { - .genmask = nft_genmask_next(net), - .set = set, - .key = elem->key.val.data, - }; - - return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params); -} - -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); - nft_set_elem_clear_busy(&he->ext); -} - -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 *he; - struct nft_hash_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_hash_params); - if (he != NULL) { - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) - nft_set_elem_change_active(net, set, &he->ext); - else - he = NULL; - } - rcu_read_unlock(); - - return he; -} - -static void nft_hash_remove(const struct nft_set *set, - const struct nft_set_elem *elem) -{ - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he = elem->priv; - - rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); -} - -static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, - struct nft_set_iter *iter) -{ - struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; - struct rhashtable_iter hti; - struct nft_set_elem elem; - int err; - - err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); - iter->err = err; - if (err) - return; - - err = rhashtable_walk_start(&hti); - if (err && err != -EAGAIN) { - iter->err = err; - goto out; - } - - 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_hash_gc(struct work_struct *work) -{ - struct nft_set *set; - struct nft_hash_elem *he; - struct nft_hash *priv; - struct nft_set_gc_batch *gcb = NULL; - struct rhashtable_iter hti; - int err; - - priv = container_of(work, struct nft_hash, gc_work.work); - set = nft_set_container_of(priv); - - err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); - if (err) - goto schedule; - - err = rhashtable_walk_start(&hti); - if (err && err != -EAGAIN) - goto out; - - while ((he = rhashtable_walk_next(&hti))) { - if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - goto out; - continue; - } - - if (!nft_set_elem_expired(&he->ext)) - continue; - 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_hash_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 unsigned int nft_hash_privsize(const struct nlattr * const nla[]) -{ - return sizeof(struct nft_hash); -} - -static const struct rhashtable_params nft_hash_params = { - .head_offset = offsetof(struct nft_hash_elem, node), - .hashfn = nft_hash_key, - .obj_hashfn = nft_hash_obj, - .obj_cmpfn = nft_hash_cmp, - .automatic_shrinking = true, -}; - -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); - struct rhashtable_params params = nft_hash_params; - int err; - - params.nelem_hint = desc->size ?: NFT_HASH_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_hash_gc); - if (set->flags & NFT_SET_TIMEOUT) - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); - return 0; -} - -static void nft_hash_elem_destroy(void *ptr, void *arg) -{ - nft_set_elem_destroy((const struct nft_set *)arg, ptr); -} - -static void nft_hash_destroy(const struct nft_set *set) -{ - struct nft_hash *priv = nft_set_priv(set); - - cancel_delayed_work_sync(&priv->gc_work); - rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, - (void *)set); -} - -static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) -{ - unsigned int esize; - - esize = sizeof(struct nft_hash_elem); - if (desc->size) { - est->size = sizeof(struct nft_hash) + - roundup_pow_of_two(desc->size * 4 / 3) * - sizeof(struct nft_hash_elem *) + - desc->size * esize; - } else { - /* Resizing happens when the load drops below 30% or goes - * above 75%. The average of 52.5% load (approximated by 50%) - * is used for the size estimation of the hash buckets, - * meaning we calculate two buckets per element. - */ - est->size = esize + 2 * sizeof(struct nft_hash_elem *); - } - - est->class = NFT_SET_CLASS_O_1; - - return true; -} - -static struct nft_set_ops nft_hash_ops __read_mostly = { - .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, - .remove = nft_hash_remove, - .lookup = nft_hash_lookup, - .update = nft_hash_update, - .walk = nft_hash_walk, - .features = NFT_SET_MAP | NFT_SET_TIMEOUT, - .owner = THIS_MODULE, -}; - -static int __init nft_hash_module_init(void) -{ - return nft_register_set(&nft_hash_ops); -} - -static void __exit nft_hash_module_exit(void) -{ - nft_unregister_set(&nft_hash_ops); -} - -module_init(nft_hash_module_init); -module_exit(nft_hash_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy "); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c deleted file mode 100644 index 6473936d05c6..000000000000 --- a/net/netfilter/nft_rbtree.c +++ /dev/null @@ -1,314 +0,0 @@ -/* - * Copyright (c) 2008-2009 Patrick McHardy - * - * 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 -#include -#include -#include -#include -#include -#include -#include -#include - -static DEFINE_SPINLOCK(nft_rbtree_lock); - -struct nft_rbtree { - 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) -{ - const 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; - - spin_lock_bh(&nft_rbtree_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; - /* In case of adjacent ranges, we always see the high - * part of the range in first place, before the low one. - * So don't update interval if the keys are equal. - */ - if (interval && nft_rbtree_equal(set, this, interval)) - continue; - interval = rbe; - } else if (d > 0) - parent = parent->rb_right; - else { -found: - if (!nft_set_elem_active(&rbe->ext, genmask)) { - parent = parent->rb_left; - continue; - } - if (nft_rbtree_interval_end(rbe)) - goto out; - spin_unlock_bh(&nft_rbtree_lock); - - *ext = &rbe->ext; - return true; - } - } - - if (set->flags & NFT_SET_INTERVAL && interval != NULL) { - rbe = interval; - goto found; - } -out: - spin_unlock_bh(&nft_rbtree_lock); - return false; -} - -static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, - struct nft_rbtree_elem *new) -{ - 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_set_elem_active(&rbe->ext, genmask)) { - 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 - return -EEXIST; - } - } - } - 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_rbtree_elem *rbe = elem->priv; - int err; - - spin_lock_bh(&nft_rbtree_lock); - err = __nft_rbtree_insert(net, set, rbe); - spin_unlock_bh(&nft_rbtree_lock); - - return err; -} - -static void nft_rbtree_remove(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; - - spin_lock_bh(&nft_rbtree_lock); - rb_erase(&rbe->node, &priv->root); - spin_unlock_bh(&nft_rbtree_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 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_set_elem_change_active(net, set, &rbe->ext); - return rbe; - } - } - return NULL; -} - -static void nft_rbtree_walk(const struct nft_ctx *ctx, - const struct nft_set *set, - struct nft_set_iter *iter) -{ - const struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe; - struct nft_set_elem elem; - struct rb_node *node; - - spin_lock_bh(&nft_rbtree_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) { - spin_unlock_bh(&nft_rbtree_lock); - return; - } -cont: - iter->count++; - } - spin_unlock_bh(&nft_rbtree_lock); -} - -static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) -{ - 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); - - 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); - } -} - -static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) -{ - unsigned int nsize; - - nsize = sizeof(struct nft_rbtree_elem); - if (desc->size) - est->size = sizeof(struct nft_rbtree) + desc->size * nsize; - else - est->size = nsize; - - est->class = NFT_SET_CLASS_O_LOG_N; - - return true; -} - -static struct nft_set_ops nft_rbtree_ops __read_mostly = { - .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, - .activate = nft_rbtree_activate, - .lookup = nft_rbtree_lookup, - .walk = nft_rbtree_walk, - .features = NFT_SET_INTERVAL | NFT_SET_MAP, - .owner = THIS_MODULE, -}; - -static int __init nft_rbtree_module_init(void) -{ - return nft_register_set(&nft_rbtree_ops); -} - -static void __exit nft_rbtree_module_exit(void) -{ - nft_unregister_set(&nft_rbtree_ops); -} - -module_init(nft_rbtree_module_init); -module_exit(nft_rbtree_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy "); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c new file mode 100644 index 000000000000..564fa7929ed5 --- /dev/null +++ b/net/netfilter/nft_set_hash.c @@ -0,0 +1,395 @@ +/* + * Copyright (c) 2008-2014 Patrick McHardy + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* We target a hash table size of 4, element hint is 75% of final size */ +#define NFT_HASH_ELEMENT_HINT 3 + +struct nft_hash { + struct rhashtable ht; + struct delayed_work gc_work; +}; + +struct nft_hash_elem { + struct rhash_head node; + struct nft_set_ext ext; +}; + +struct nft_hash_cmp_arg { + const struct nft_set *set; + const u32 *key; + u8 genmask; +}; + +static const struct rhashtable_params nft_hash_params; + +static inline u32 nft_hash_key(const void *data, u32 len, u32 seed) +{ + const struct nft_hash_cmp_arg *arg = data; + + return jhash(arg->key, len, seed); +} + +static inline u32 nft_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct nft_hash_elem *he = data; + + return jhash(nft_set_ext_key(&he->ext), len, seed); +} + +static inline int nft_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nft_hash_cmp_arg *x = arg->key; + const struct nft_hash_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 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); + const struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_cur(net), + .set = set, + .key = key, + }; + + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + *ext = &he->ext; + + return !!he; +} + +static bool nft_hash_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_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct nft_hash_cmp_arg arg = { + .genmask = NFT_GENMASK_ANY, + .set = set, + .key = key, + }; + + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_hash_params); + if (he != NULL) + goto out; + + he = new(set, expr, regs); + if (he == NULL) + goto err1; + if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params)) + goto err2; +out: + *ext = &he->ext; + return true; + +err2: + nft_set_elem_destroy(set, he); +err1: + return false; +} + +static int nft_hash_insert(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 *he = elem->priv; + struct nft_hash_cmp_arg arg = { + .genmask = nft_genmask_next(net), + .set = set, + .key = elem->key.val.data, + }; + + return rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); +} + +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); + nft_set_elem_clear_busy(&he->ext); +} + +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 *he; + struct nft_hash_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_hash_params); + if (he != NULL) { + if (!nft_set_elem_mark_busy(&he->ext) || + !nft_is_active(net, &he->ext)) + nft_set_elem_change_active(net, set, &he->ext); + else + he = NULL; + } + rcu_read_unlock(); + + return he; +} + +static void nft_hash_remove(const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he = elem->priv; + + rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params); +} + +static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, + struct nft_set_iter *iter) +{ + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_elem *he; + struct rhashtable_iter hti; + struct nft_set_elem elem; + int err; + + err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); + iter->err = err; + if (err) + return; + + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) { + iter->err = err; + goto out; + } + + 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_hash_gc(struct work_struct *work) +{ + struct nft_set *set; + struct nft_hash_elem *he; + struct nft_hash *priv; + struct nft_set_gc_batch *gcb = NULL; + struct rhashtable_iter hti; + int err; + + priv = container_of(work, struct nft_hash, gc_work.work); + set = nft_set_container_of(priv); + + err = rhashtable_walk_init(&priv->ht, &hti, GFP_KERNEL); + if (err) + goto schedule; + + err = rhashtable_walk_start(&hti); + if (err && err != -EAGAIN) + goto out; + + while ((he = rhashtable_walk_next(&hti))) { + if (IS_ERR(he)) { + if (PTR_ERR(he) != -EAGAIN) + goto out; + continue; + } + + if (!nft_set_elem_expired(&he->ext)) + continue; + 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_hash_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 unsigned int nft_hash_privsize(const struct nlattr * const nla[]) +{ + return sizeof(struct nft_hash); +} + +static const struct rhashtable_params nft_hash_params = { + .head_offset = offsetof(struct nft_hash_elem, node), + .hashfn = nft_hash_key, + .obj_hashfn = nft_hash_obj, + .obj_cmpfn = nft_hash_cmp, + .automatic_shrinking = true, +}; + +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); + struct rhashtable_params params = nft_hash_params; + int err; + + params.nelem_hint = desc->size ?: NFT_HASH_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_hash_gc); + if (set->flags & NFT_SET_TIMEOUT) + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); + return 0; +} + +static void nft_hash_elem_destroy(void *ptr, void *arg) +{ + nft_set_elem_destroy((const struct nft_set *)arg, ptr); +} + +static void nft_hash_destroy(const struct nft_set *set) +{ + struct nft_hash *priv = nft_set_priv(set); + + cancel_delayed_work_sync(&priv->gc_work); + rhashtable_free_and_destroy(&priv->ht, nft_hash_elem_destroy, + (void *)set); +} + +static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + unsigned int esize; + + esize = sizeof(struct nft_hash_elem); + if (desc->size) { + est->size = sizeof(struct nft_hash) + + roundup_pow_of_two(desc->size * 4 / 3) * + sizeof(struct nft_hash_elem *) + + desc->size * esize; + } else { + /* Resizing happens when the load drops below 30% or goes + * above 75%. The average of 52.5% load (approximated by 50%) + * is used for the size estimation of the hash buckets, + * meaning we calculate two buckets per element. + */ + est->size = esize + 2 * sizeof(struct nft_hash_elem *); + } + + est->class = NFT_SET_CLASS_O_1; + + return true; +} + +static struct nft_set_ops nft_hash_ops __read_mostly = { + .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, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup, + .update = nft_hash_update, + .walk = nft_hash_walk, + .features = NFT_SET_MAP | NFT_SET_TIMEOUT, + .owner = THIS_MODULE, +}; + +static int __init nft_hash_module_init(void) +{ + return nft_register_set(&nft_hash_ops); +} + +static void __exit nft_hash_module_exit(void) +{ + nft_unregister_set(&nft_hash_ops); +} + +module_init(nft_hash_module_init); +module_exit(nft_hash_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy "); +MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c new file mode 100644 index 000000000000..6473936d05c6 --- /dev/null +++ b/net/netfilter/nft_set_rbtree.c @@ -0,0 +1,314 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy + * + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(nft_rbtree_lock); + +struct nft_rbtree { + 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) +{ + const 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; + + spin_lock_bh(&nft_rbtree_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; + /* In case of adjacent ranges, we always see the high + * part of the range in first place, before the low one. + * So don't update interval if the keys are equal. + */ + if (interval && nft_rbtree_equal(set, this, interval)) + continue; + interval = rbe; + } else if (d > 0) + parent = parent->rb_right; + else { +found: + if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; + } + if (nft_rbtree_interval_end(rbe)) + goto out; + spin_unlock_bh(&nft_rbtree_lock); + + *ext = &rbe->ext; + return true; + } + } + + if (set->flags & NFT_SET_INTERVAL && interval != NULL) { + rbe = interval; + goto found; + } +out: + spin_unlock_bh(&nft_rbtree_lock); + return false; +} + +static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, + struct nft_rbtree_elem *new) +{ + 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_set_elem_active(&rbe->ext, genmask)) { + 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 + return -EEXIST; + } + } + } + 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_rbtree_elem *rbe = elem->priv; + int err; + + spin_lock_bh(&nft_rbtree_lock); + err = __nft_rbtree_insert(net, set, rbe); + spin_unlock_bh(&nft_rbtree_lock); + + return err; +} + +static void nft_rbtree_remove(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; + + spin_lock_bh(&nft_rbtree_lock); + rb_erase(&rbe->node, &priv->root); + spin_unlock_bh(&nft_rbtree_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 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_set_elem_change_active(net, set, &rbe->ext); + return rbe; + } + } + return NULL; +} + +static void nft_rbtree_walk(const struct nft_ctx *ctx, + const struct nft_set *set, + struct nft_set_iter *iter) +{ + const struct nft_rbtree *priv = nft_set_priv(set); + struct nft_rbtree_elem *rbe; + struct nft_set_elem elem; + struct rb_node *node; + + spin_lock_bh(&nft_rbtree_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) { + spin_unlock_bh(&nft_rbtree_lock); + return; + } +cont: + iter->count++; + } + spin_unlock_bh(&nft_rbtree_lock); +} + +static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) +{ + 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); + + 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); + } +} + +static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + unsigned int nsize; + + nsize = sizeof(struct nft_rbtree_elem); + if (desc->size) + est->size = sizeof(struct nft_rbtree) + desc->size * nsize; + else + est->size = nsize; + + est->class = NFT_SET_CLASS_O_LOG_N; + + return true; +} + +static struct nft_set_ops nft_rbtree_ops __read_mostly = { + .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, + .activate = nft_rbtree_activate, + .lookup = nft_rbtree_lookup, + .walk = nft_rbtree_walk, + .features = NFT_SET_INTERVAL | NFT_SET_MAP, + .owner = THIS_MODULE, +}; + +static int __init nft_rbtree_module_init(void) +{ + return nft_register_set(&nft_rbtree_ops); +} + +static void __exit nft_rbtree_module_exit(void) +{ + nft_unregister_set(&nft_rbtree_ops); +} + +module_init(nft_rbtree_module_init); +module_exit(nft_rbtree_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy "); +MODULE_ALIAS_NFT_SET();