netfilter: nf_tables: add netlink set API
This patch adds the new netlink API for maintaining nf_tables sets
independently of the ruleset. The API supports the following operations:
- creation of sets
- deletion of sets
- querying of specific sets
- dumping of all sets
- addition of set elements
- removal of set elements
- dumping of all set elements
Sets are identified by name, each table defines an individual namespace.
The name of a set may be allocated automatically, this is mostly useful
in combination with the NFT_SET_ANONYMOUS flag, which destroys a set
automatically once the last reference has been released.
Sets can be marked constant, meaning they're not allowed to change while
linked to a rule. This allows to perform lockless operation for set
types that would otherwise require locking.
Additionally, if the implementation supports it, sets can (as before) be
used as maps, associating a data value with each key (or range), by
specifying the NFT_SET_MAP flag and can be used for interval queries by
specifying the NFT_SET_INTERVAL flag.
Set elements are added and removed incrementally. All element operations
support batching, reducing netlink message and set lookup overhead.
The old "set" and "hash" expressions are replaced by a generic "lookup"
expression, which binds to the specified set. Userspace is not aware
of the actual set implementation used by the kernel anymore, all
configuration options are generic.
Currently the implementation selection logic is largely missing and the
kernel will simply use the first registered implementation supporting the
requested operation. Eventually, the plan is to have userspace supply a
description of the data characteristics and select the implementation
based on expected performance and memory use.
This patch includes the new 'lookup' expression to look up for element
matching in the set.
This patch includes kernel-doc descriptions for this set API and it
also includes the following fixes.
From Patrick McHardy:
* netfilter: nf_tables: fix set element data type in dumps
* netfilter: nf_tables: fix indentation of struct nft_set_elem comments
* netfilter: nf_tables: fix oops in nft_validate_data_load()
* netfilter: nf_tables: fix oops while listing sets of built-in tables
* netfilter: nf_tables: destroy anonymous sets immediately if binding fails
* netfilter: nf_tables: propagate context to set iter callback
* netfilter: nf_tables: add loop detection
From Pablo Neira Ayuso:
* netfilter: nf_tables: allow to dump all existing sets
* netfilter: nf_tables: fix wrong type for flags variable in newelem
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
new file mode 100644
index 0000000..4962d21
--- /dev/null
+++ b/net/netfilter/nft_lookup.c
@@ -0,0 +1,135 @@
+/*
+ * Copyright (c) 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/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_lookup {
+ struct nft_set *set;
+ enum nft_registers sreg:8;
+ enum nft_registers dreg:8;
+ struct nft_set_binding binding;
+};
+
+static void nft_lookup_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_lookup *priv = nft_expr_priv(expr);
+ const struct nft_set *set = priv->set;
+
+ if (set->ops->lookup(set, &data[priv->sreg], &data[priv->dreg]))
+ return;
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
+ [NFTA_LOOKUP_SET] = { .type = NLA_STRING },
+ [NFTA_LOOKUP_SREG] = { .type = NLA_U32 },
+ [NFTA_LOOKUP_DREG] = { .type = NLA_U32 },
+};
+
+static int nft_lookup_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_lookup *priv = nft_expr_priv(expr);
+ struct nft_set *set;
+ int err;
+
+ if (tb[NFTA_LOOKUP_SET] == NULL ||
+ tb[NFTA_LOOKUP_SREG] == NULL)
+ return -EINVAL;
+
+ set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]);
+ if (IS_ERR(set))
+ return PTR_ERR(set);
+
+ priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG]));
+ err = nft_validate_input_register(priv->sreg);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_LOOKUP_DREG] != NULL) {
+ if (!(set->flags & NFT_SET_MAP))
+ return -EINVAL;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+
+ if (priv->dreg == NFT_REG_VERDICT) {
+ if (set->dtype != NFT_DATA_VERDICT)
+ return -EINVAL;
+ } else if (set->dtype == NFT_DATA_VERDICT)
+ return -EINVAL;
+ } else if (set->flags & NFT_SET_MAP)
+ return -EINVAL;
+
+ err = nf_tables_bind_set(ctx, set, &priv->binding);
+ if (err < 0)
+ return err;
+
+ priv->set = set;
+ return 0;
+}
+
+static void nft_lookup_destroy(const struct nft_expr *expr)
+{
+ struct nft_lookup *priv = nft_expr_priv(expr);
+
+ nf_tables_unbind_set(NULL, priv->set, &priv->binding);
+}
+
+static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_lookup *priv = nft_expr_priv(expr);
+
+ if (nla_put_string(skb, NFTA_LOOKUP_SET, priv->set->name))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_LOOKUP_SREG, htonl(priv->sreg)))
+ goto nla_put_failure;
+ if (priv->set->flags & NFT_SET_MAP)
+ if (nla_put_be32(skb, NFTA_LOOKUP_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_lookup_ops __read_mostly = {
+ .name = "lookup",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
+ .owner = THIS_MODULE,
+ .eval = nft_lookup_eval,
+ .init = nft_lookup_init,
+ .destroy = nft_lookup_destroy,
+ .dump = nft_lookup_dump,
+ .policy = nft_lookup_policy,
+ .maxattr = NFTA_LOOKUP_MAX,
+};
+
+int __init nft_lookup_module_init(void)
+{
+ return nft_register_expr(&nft_lookup_ops);
+}
+
+void nft_lookup_module_exit(void)
+{
+ nft_unregister_expr(&nft_lookup_ops);
+}