summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--include/linux/netfilter.h11
-rw-r--r--include/net/netfilter/nf_tables.h301
-rw-r--r--include/net/netfilter/nf_tables_core.h25
-rw-r--r--include/uapi/linux/netfilter/Kbuild1
-rw-r--r--include/uapi/linux/netfilter/nf_conntrack_common.h4
-rw-r--r--include/uapi/linux/netfilter/nf_tables.h582
-rw-r--r--include/uapi/linux/netfilter/nfnetlink.h5
-rw-r--r--net/bridge/netfilter/Kconfig3
-rw-r--r--net/bridge/netfilter/Makefile2
-rw-r--r--net/bridge/netfilter/nf_tables_bridge.c37
-rw-r--r--net/ipv4/netfilter/Kconfig16
-rw-r--r--net/ipv4/netfilter/Makefile5
-rw-r--r--net/ipv4/netfilter/nf_table_nat_ipv4.c409
-rw-r--r--net/ipv4/netfilter/nf_table_route_ipv4.c97
-rw-r--r--net/ipv4/netfilter/nf_tables_ipv4.c59
-rw-r--r--net/ipv4/netfilter/nft_reject_ipv4.c117
-rw-r--r--net/ipv6/netfilter/Kconfig8
-rw-r--r--net/ipv6/netfilter/Makefile4
-rw-r--r--net/ipv6/netfilter/nf_table_route_ipv6.c93
-rw-r--r--net/ipv6/netfilter/nf_tables_ipv6.c57
-rw-r--r--net/netfilter/Kconfig37
-rw-r--r--net/netfilter/Makefile16
-rw-r--r--net/netfilter/nf_tables_api.c1760
-rw-r--r--net/netfilter/nf_tables_core.c152
-rw-r--r--net/netfilter/nft_bitwise.c140
-rw-r--r--net/netfilter/nft_byteorder.c167
-rw-r--r--net/netfilter/nft_cmp.c146
-rw-r--r--net/netfilter/nft_counter.c107
-rw-r--r--net/netfilter/nft_ct.c252
-rw-r--r--net/netfilter/nft_expr_template.c88
-rw-r--r--net/netfilter/nft_exthdr.c127
-rw-r--r--net/netfilter/nft_hash.c348
-rw-r--r--net/netfilter/nft_immediate.c113
-rw-r--r--net/netfilter/nft_limit.c113
-rw-r--r--net/netfilter/nft_log.c140
-rw-r--r--net/netfilter/nft_meta.c222
-rw-r--r--net/netfilter/nft_meta_target.c117
-rw-r--r--net/netfilter/nft_payload.c137
-rw-r--r--net/netfilter/nft_set.c381
39 files changed, 6393 insertions, 6 deletions
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index fef7e67f7101..2077489f9887 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -53,12 +53,13 @@ struct nf_hook_ops {
struct list_head list;
/* User fills in from here down. */
- nf_hookfn *hook;
- struct module *owner;
- u_int8_t pf;
- unsigned int hooknum;
+ nf_hookfn *hook;
+ struct module *owner;
+ void *priv;
+ u_int8_t pf;
+ unsigned int hooknum;
/* Hooks are ordered in ascending priority. */
- int priority;
+ int priority;
};
struct nf_sockopt_ops {
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
new file mode 100644
index 000000000000..d26dfa345f49
--- /dev/null
+++ b/include/net/netfilter/nf_tables.h
@@ -0,0 +1,301 @@
+#ifndef _NET_NF_TABLES_H
+#define _NET_NF_TABLES_H
+
+#include <linux/list.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netlink.h>
+
+struct nft_pktinfo {
+ struct sk_buff *skb;
+ const struct net_device *in;
+ const struct net_device *out;
+ u8 hooknum;
+ u8 nhoff;
+ u8 thoff;
+};
+
+struct nft_data {
+ union {
+ u32 data[4];
+ struct {
+ u32 verdict;
+ struct nft_chain *chain;
+ };
+ };
+} __attribute__((aligned(__alignof__(u64))));
+
+static inline int nft_data_cmp(const struct nft_data *d1,
+ const struct nft_data *d2,
+ unsigned int len)
+{
+ return memcmp(d1->data, d2->data, len);
+}
+
+static inline void nft_data_copy(struct nft_data *dst,
+ const struct nft_data *src)
+{
+ BUILD_BUG_ON(__alignof__(*dst) != __alignof__(u64));
+ *(u64 *)&dst->data[0] = *(u64 *)&src->data[0];
+ *(u64 *)&dst->data[2] = *(u64 *)&src->data[2];
+}
+
+static inline void nft_data_debug(const struct nft_data *data)
+{
+ pr_debug("data[0]=%x data[1]=%x data[2]=%x data[3]=%x\n",
+ data->data[0], data->data[1],
+ data->data[2], data->data[3]);
+}
+
+/**
+ * struct nft_ctx - nf_tables rule context
+ *
+ * @afi: address family info
+ * @table: the table the chain is contained in
+ * @chain: the chain the rule is contained in
+ */
+struct nft_ctx {
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ const struct nft_chain *chain;
+};
+
+enum nft_data_types {
+ NFT_DATA_VALUE,
+ NFT_DATA_VERDICT,
+};
+
+struct nft_data_desc {
+ enum nft_data_types type;
+ unsigned int len;
+};
+
+extern int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
+ struct nft_data_desc *desc, const struct nlattr *nla);
+extern void nft_data_uninit(const struct nft_data *data,
+ enum nft_data_types type);
+extern int nft_data_dump(struct sk_buff *skb, int attr,
+ const struct nft_data *data,
+ enum nft_data_types type, unsigned int len);
+
+static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg)
+{
+ return reg == NFT_REG_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE;
+}
+
+extern int nft_validate_input_register(enum nft_registers reg);
+extern int nft_validate_output_register(enum nft_registers reg);
+extern int nft_validate_data_load(const struct nft_ctx *ctx,
+ enum nft_registers reg,
+ const struct nft_data *data,
+ enum nft_data_types type);
+
+/**
+ * struct nft_expr_ops - nf_tables expression operations
+ *
+ * @eval: Expression evaluation function
+ * @init: initialization function
+ * @destroy: destruction function
+ * @dump: function to dump parameters
+ * @list: used internally
+ * @name: Identifier
+ * @owner: module reference
+ * @policy: netlink attribute policy
+ * @maxattr: highest netlink attribute number
+ * @size: full expression size, including private data size
+ */
+struct nft_expr;
+struct nft_expr_ops {
+ void (*eval)(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt);
+ int (*init)(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[]);
+ void (*destroy)(const struct nft_expr *expr);
+ int (*dump)(struct sk_buff *skb,
+ const struct nft_expr *expr);
+
+ struct list_head list;
+ const char *name;
+ struct module *owner;
+ const struct nla_policy *policy;
+ unsigned int maxattr;
+ unsigned int size;
+};
+
+#define NFT_EXPR_SIZE(size) (sizeof(struct nft_expr) + \
+ ALIGN(size, __alignof__(struct nft_expr)))
+
+/**
+ * struct nft_expr - nf_tables expression
+ *
+ * @ops: expression ops
+ * @data: expression private data
+ */
+struct nft_expr {
+ const struct nft_expr_ops *ops;
+ unsigned char data[];
+};
+
+static inline void *nft_expr_priv(const struct nft_expr *expr)
+{
+ return (void *)expr->data;
+}
+
+/**
+ * struct nft_rule - nf_tables rule
+ *
+ * @list: used internally
+ * @rcu_head: used internally for rcu
+ * @handle: rule handle
+ * @dlen: length of expression data
+ * @data: expression data
+ */
+struct nft_rule {
+ struct list_head list;
+ struct rcu_head rcu_head;
+ u64 handle:48,
+ dlen:16;
+ unsigned char data[]
+ __attribute__((aligned(__alignof__(struct nft_expr))));
+};
+
+static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule)
+{
+ return (struct nft_expr *)&rule->data[0];
+}
+
+static inline struct nft_expr *nft_expr_next(const struct nft_expr *expr)
+{
+ return ((void *)expr) + expr->ops->size;
+}
+
+static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule)
+{
+ return (struct nft_expr *)&rule->data[rule->dlen];
+}
+
+/*
+ * The last pointer isn't really necessary, but the compiler isn't able to
+ * determine that the result of nft_expr_last() is always the same since it
+ * can't assume that the dlen value wasn't changed within calls in the loop.
+ */
+#define nft_rule_for_each_expr(expr, last, rule) \
+ for ((expr) = nft_expr_first(rule), (last) = nft_expr_last(rule); \
+ (expr) != (last); \
+ (expr) = nft_expr_next(expr))
+
+enum nft_chain_flags {
+ NFT_BASE_CHAIN = 0x1,
+ NFT_CHAIN_BUILTIN = 0x2,
+};
+
+/**
+ * struct nft_chain - nf_tables chain
+ *
+ * @rules: list of rules in the chain
+ * @list: used internally
+ * @rcu_head: used internally
+ * @handle: chain handle
+ * @flags: bitmask of enum nft_chain_flags
+ * @use: number of jump references to this chain
+ * @level: length of longest path to this chain
+ * @name: name of the chain
+ */
+struct nft_chain {
+ struct list_head rules;
+ struct list_head list;
+ struct rcu_head rcu_head;
+ u64 handle;
+ u8 flags;
+ u16 use;
+ u16 level;
+ char name[NFT_CHAIN_MAXNAMELEN];
+};
+
+/**
+ * struct nft_base_chain - nf_tables base chain
+ *
+ * @ops: netfilter hook ops
+ * @chain: the chain
+ */
+struct nft_base_chain {
+ struct nf_hook_ops ops;
+ struct nft_chain chain;
+};
+
+static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain)
+{
+ return container_of(chain, struct nft_base_chain, chain);
+}
+
+extern unsigned int nft_do_chain(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *));
+
+enum nft_table_flags {
+ NFT_TABLE_BUILTIN = 0x1,
+};
+
+/**
+ * struct nft_table - nf_tables table
+ *
+ * @list: used internally
+ * @chains: chains in the table
+ * @sets: sets in the table
+ * @hgenerator: handle generator state
+ * @use: number of chain references to this table
+ * @flags: table flag (see enum nft_table_flags)
+ * @name: name of the table
+ */
+struct nft_table {
+ struct list_head list;
+ struct list_head chains;
+ struct list_head sets;
+ u64 hgenerator;
+ u32 use;
+ u16 flags;
+ char name[];
+};
+
+/**
+ * struct nft_af_info - nf_tables address family info
+ *
+ * @list: used internally
+ * @family: address family
+ * @nhooks: number of hooks in this family
+ * @owner: module owner
+ * @tables: used internally
+ * @hooks: hookfn overrides for packet validation
+ */
+struct nft_af_info {
+ struct list_head list;
+ int family;
+ unsigned int nhooks;
+ struct module *owner;
+ struct list_head tables;
+ nf_hookfn *hooks[NF_MAX_HOOKS];
+};
+
+extern int nft_register_afinfo(struct nft_af_info *);
+extern void nft_unregister_afinfo(struct nft_af_info *);
+
+extern int nft_register_table(struct nft_table *, int family);
+extern void nft_unregister_table(struct nft_table *, int family);
+
+extern int nft_register_expr(struct nft_expr_ops *);
+extern void nft_unregister_expr(struct nft_expr_ops *);
+
+#define MODULE_ALIAS_NFT_FAMILY(family) \
+ MODULE_ALIAS("nft-afinfo-" __stringify(family))
+
+#define MODULE_ALIAS_NFT_TABLE(family, name) \
+ MODULE_ALIAS("nft-table-" __stringify(family) "-" name)
+
+#define MODULE_ALIAS_NFT_EXPR(name) \
+ MODULE_ALIAS("nft-expr-" name)
+
+#endif /* _NET_NF_TABLES_H */
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
new file mode 100644
index 000000000000..283396c916e0
--- /dev/null
+++ b/include/net/netfilter/nf_tables_core.h
@@ -0,0 +1,25 @@
+#ifndef _NET_NF_TABLES_CORE_H
+#define _NET_NF_TABLES_CORE_H
+
+extern int nf_tables_core_module_init(void);
+extern void nf_tables_core_module_exit(void);
+
+extern int nft_immediate_module_init(void);
+extern void nft_immediate_module_exit(void);
+
+extern int nft_cmp_module_init(void);
+extern void nft_cmp_module_exit(void);
+
+extern int nft_lookup_module_init(void);
+extern void nft_lookup_module_exit(void);
+
+extern int nft_bitwise_module_init(void);
+extern void nft_bitwise_module_exit(void);
+
+extern int nft_byteorder_module_init(void);
+extern void nft_byteorder_module_exit(void);
+
+extern int nft_payload_module_init(void);
+extern void nft_payload_module_exit(void);
+
+#endif /* _NET_NF_TABLES_CORE_H */
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 174915420d3f..6ce0b7f566a7 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -5,6 +5,7 @@ header-y += nf_conntrack_ftp.h
header-y += nf_conntrack_sctp.h
header-y += nf_conntrack_tcp.h
header-y += nf_conntrack_tuple_common.h
+header-y += nf_tables.h
header-y += nf_nat.h
header-y += nfnetlink.h
header-y += nfnetlink_acct.h
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 8dd803818ebe..319f47128db8 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -25,6 +25,10 @@ enum ip_conntrack_info {
IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
};
+#define NF_CT_STATE_INVALID_BIT (1 << 0)
+#define NF_CT_STATE_BIT(ctinfo) (1 << ((ctinfo) % IP_CT_IS_REPLY + 1))
+#define NF_CT_STATE_UNTRACKED_BIT (1 << (IP_CT_NUMBER + 1))
+
/* Bitset representing status of connection. */
enum ip_conntrack_status {
/* It's an expected connection: bit 0 set. This bit never changed */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
new file mode 100644
index 000000000000..ec6d84a8ed1e
--- /dev/null
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -0,0 +1,582 @@
+#ifndef _LINUX_NF_TABLES_H
+#define _LINUX_NF_TABLES_H
+
+#define NFT_CHAIN_MAXNAMELEN 32
+
+enum nft_registers {
+ NFT_REG_VERDICT,
+ NFT_REG_1,
+ NFT_REG_2,
+ NFT_REG_3,
+ NFT_REG_4,
+ __NFT_REG_MAX
+};
+#define NFT_REG_MAX (__NFT_REG_MAX - 1)
+
+/**
+ * enum nft_verdicts - nf_tables internal verdicts
+ *
+ * @NFT_CONTINUE: continue evaluation of the current rule
+ * @NFT_BREAK: terminate evaluation of the current rule
+ * @NFT_JUMP: push the current chain on the jump stack and jump to a chain
+ * @NFT_GOTO: jump to a chain without pushing the current chain on the jump stack
+ * @NFT_RETURN: return to the topmost chain on the jump stack
+ *
+ * The nf_tables verdicts share their numeric space with the netfilter verdicts.
+ */
+enum nft_verdicts {
+ NFT_CONTINUE = -1,
+ NFT_BREAK = -2,
+ NFT_JUMP = -3,
+ NFT_GOTO = -4,
+ NFT_RETURN = -5,
+};
+
+/**
+ * enum nf_tables_msg_types - nf_tables netlink message types
+ *
+ * @NFT_MSG_NEWTABLE: create a new table (enum nft_table_attributes)
+ * @NFT_MSG_GETTABLE: get a table (enum nft_table_attributes)
+ * @NFT_MSG_DELTABLE: delete a table (enum nft_table_attributes)
+ * @NFT_MSG_NEWCHAIN: create a new chain (enum nft_chain_attributes)
+ * @NFT_MSG_GETCHAIN: get a chain (enum nft_chain_attributes)
+ * @NFT_MSG_DELCHAIN: delete a chain (enum nft_chain_attributes)
+ * @NFT_MSG_NEWRULE: create a new rule (enum nft_rule_attributes)
+ * @NFT_MSG_GETRULE: get a rule (enum nft_rule_attributes)
+ * @NFT_MSG_DELRULE: delete a rule (enum nft_rule_attributes)
+ */
+enum nf_tables_msg_types {
+ NFT_MSG_NEWTABLE,
+ NFT_MSG_GETTABLE,
+ NFT_MSG_DELTABLE,
+ NFT_MSG_NEWCHAIN,
+ NFT_MSG_GETCHAIN,
+ NFT_MSG_DELCHAIN,
+ NFT_MSG_NEWRULE,
+ NFT_MSG_GETRULE,
+ NFT_MSG_DELRULE,
+ NFT_MSG_MAX,
+};
+
+enum nft_list_attributes {
+ NFTA_LIST_UNPEC,
+ NFTA_LIST_ELEM,
+ __NFTA_LIST_MAX
+};
+#define NFTA_LIST_MAX (__NFTA_LIST_MAX - 1)
+
+/**
+ * enum nft_hook_attributes - nf_tables netfilter hook netlink attributes
+ *
+ * @NFTA_HOOK_HOOKNUM: netfilter hook number (NLA_U32)
+ * @NFTA_HOOK_PRIORITY: netfilter hook priority (NLA_U32)
+ */
+enum nft_hook_attributes {
+ NFTA_HOOK_UNSPEC,
+ NFTA_HOOK_HOOKNUM,
+ NFTA_HOOK_PRIORITY,
+ __NFTA_HOOK_MAX
+};
+#define NFTA_HOOK_MAX (__NFTA_HOOK_MAX - 1)
+
+/**
+ * enum nft_table_attributes - nf_tables table netlink attributes
+ *
+ * @NFTA_TABLE_NAME: name of the table (NLA_STRING)
+ */
+enum nft_table_attributes {
+ NFTA_TABLE_UNSPEC,
+ NFTA_TABLE_NAME,
+ __NFTA_TABLE_MAX
+};
+#define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1)
+
+/**
+ * enum nft_chain_attributes - nf_tables chain netlink attributes
+ *
+ * @NFTA_CHAIN_TABLE: name of the table containing the chain (NLA_STRING)
+ * @NFTA_CHAIN_HANDLE: numeric handle of the chain (NLA_U64)
+ * @NFTA_CHAIN_NAME: name of the chain (NLA_STRING)
+ * @NFTA_CHAIN_HOOK: hook specification for basechains (NLA_NESTED: nft_hook_attributes)
+ */
+enum nft_chain_attributes {
+ NFTA_CHAIN_UNSPEC,
+ NFTA_CHAIN_TABLE,
+ NFTA_CHAIN_HANDLE,
+ NFTA_CHAIN_NAME,
+ NFTA_CHAIN_HOOK,
+ __NFTA_CHAIN_MAX
+};
+#define NFTA_CHAIN_MAX (__NFTA_CHAIN_MAX - 1)
+
+/**
+ * enum nft_rule_attributes - nf_tables rule netlink attributes
+ *
+ * @NFTA_RULE_TABLE: name of the table containing the rule (NLA_STRING)
+ * @NFTA_RULE_CHAIN: name of the chain containing the rule (NLA_STRING)
+ * @NFTA_RULE_HANDLE: numeric handle of the rule (NLA_U64)
+ * @NFTA_RULE_EXPRESSIONS: list of expressions (NLA_NESTED: nft_expr_attributes)
+ */
+enum nft_rule_attributes {
+ NFTA_RULE_UNSPEC,
+ NFTA_RULE_TABLE,
+ NFTA_RULE_CHAIN,
+ NFTA_RULE_HANDLE,
+ NFTA_RULE_EXPRESSIONS,
+ __NFTA_RULE_MAX
+};
+#define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1)
+
+enum nft_data_attributes {
+ NFTA_DATA_UNSPEC,
+ NFTA_DATA_VALUE,
+ NFTA_DATA_VERDICT,
+ __NFTA_DATA_MAX
+};
+#define NFTA_DATA_MAX (__NFTA_DATA_MAX - 1)
+
+/**
+ * enum nft_verdict_attributes - nf_tables verdict netlink attributes
+ *
+ * @NFTA_VERDICT_CODE: nf_tables verdict (NLA_U32: enum nft_verdicts)
+ * @NFTA_VERDICT_CHAIN: jump target chain name (NLA_STRING)
+ */
+enum nft_verdict_attributes {
+ NFTA_VERDICT_UNSPEC,
+ NFTA_VERDICT_CODE,
+ NFTA_VERDICT_CHAIN,
+ __NFTA_VERDICT_MAX
+};
+#define NFTA_VERDICT_MAX (__NFTA_VERDICT_MAX - 1)
+
+/**
+ * enum nft_expr_attributes - nf_tables expression netlink attributes
+ *
+ * @NFTA_EXPR_NAME: name of the expression type (NLA_STRING)
+ * @NFTA_EXPR_DATA: type specific data (NLA_NESTED)
+ */
+enum nft_expr_attributes {
+ NFTA_EXPR_UNSPEC,
+ NFTA_EXPR_NAME,
+ NFTA_EXPR_DATA,
+ __NFTA_EXPR_MAX
+};
+#define NFTA_EXPR_MAX (__NFTA_EXPR_MAX - 1)
+
+/**
+ * enum nft_immediate_attributes - nf_tables immediate expression netlink attributes
+ *
+ * @NFTA_IMMEDIATE_DREG: destination register to load data into (NLA_U32)
+ * @NFTA_IMMEDIATE_DATA: data to load (NLA_NESTED: nft_data_attributes)
+ */
+enum nft_immediate_attributes {
+ NFTA_IMMEDIATE_UNSPEC,
+ NFTA_IMMEDIATE_DREG,
+ NFTA_IMMEDIATE_DATA,
+ __NFTA_IMMEDIATE_MAX
+};
+#define NFTA_IMMEDIATE_MAX (__NFTA_IMMEDIATE_MAX - 1)
+
+/**
+ * enum nft_bitwise_attributes - nf_tables bitwise expression netlink attributes
+ *
+ * @NFTA_BITWISE_SREG: source register (NLA_U32: nft_registers)
+ * @NFTA_BITWISE_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_BITWISE_LEN: length of operands (NLA_U32)
+ * @NFTA_BITWISE_MASK: mask value (NLA_NESTED: nft_data_attributes)
+ * @NFTA_BITWISE_XOR: xor value (NLA_NESTED: nft_data_attributes)
+ *
+ * The bitwise expression performs the following operation:
+ *
+ * dreg = (sreg & mask) ^ xor
+ *
+ * which allow to express all bitwise operations:
+ *
+ * mask xor
+ * NOT: 1 1
+ * OR: 0 x
+ * XOR: 1 x
+ * AND: x 0
+ */
+enum nft_bitwise_attributes {
+ NFTA_BITWISE_UNSPEC,
+ NFTA_BITWISE_SREG,
+ NFTA_BITWISE_DREG,
+ NFTA_BITWISE_LEN,
+ NFTA_BITWISE_MASK,
+ NFTA_BITWISE_XOR,
+ __NFTA_BITWISE_MAX
+};
+#define NFTA_BITWISE_MAX (__NFTA_BITWISE_MAX - 1)
+
+/**
+ * enum nft_byteorder_ops - nf_tables byteorder operators
+ *
+ * @NFT_BYTEORDER_NTOH: network to host operator
+ * @NFT_BYTEORDER_HTON: host to network opertaor
+ */
+enum nft_byteorder_ops {
+ NFT_BYTEORDER_NTOH,
+ NFT_BYTEORDER_HTON,
+};
+
+/**
+ * enum nft_byteorder_attributes - nf_tables byteorder expression netlink attributes
+ *
+ * @NFTA_BYTEORDER_SREG: source register (NLA_U32: nft_registers)
+ * @NFTA_BYTEORDER_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_BYTEORDER_OP: operator (NLA_U32: enum nft_byteorder_ops)
+ * @NFTA_BYTEORDER_LEN: length of the data (NLA_U32)
+ * @NFTA_BYTEORDER_SIZE: data size in bytes (NLA_U32: 2 or 4)
+ */
+enum nft_byteorder_attributes {
+ NFTA_BYTEORDER_UNSPEC,
+ NFTA_BYTEORDER_SREG,
+ NFTA_BYTEORDER_DREG,
+ NFTA_BYTEORDER_OP,
+ NFTA_BYTEORDER_LEN,
+ NFTA_BYTEORDER_SIZE,
+ __NFTA_BYTEORDER_MAX
+};
+#define NFTA_BYTEORDER_MAX (__NFTA_BYTEORDER_MAX - 1)
+
+/**
+ * enum nft_cmp_ops - nf_tables relational operator
+ *
+ * @NFT_CMP_EQ: equal
+ * @NFT_CMP_NEQ: not equal
+ * @NFT_CMP_LT: less than
+ * @NFT_CMP_LTE: less than or equal to
+ * @NFT_CMP_GT: greater than
+ * @NFT_CMP_GTE: greater than or equal to
+ */
+enum nft_cmp_ops {
+ NFT_CMP_EQ,
+ NFT_CMP_NEQ,
+ NFT_CMP_LT,
+ NFT_CMP_LTE,
+ NFT_CMP_GT,
+ NFT_CMP_GTE,
+};
+
+/**
+ * enum nft_cmp_attributes - nf_tables cmp expression netlink attributes
+ *
+ * @NFTA_CMP_SREG: source register of data to compare (NLA_U32: nft_registers)
+ * @NFTA_CMP_OP: cmp operation (NLA_U32: nft_cmp_ops)
+ * @NFTA_CMP_DATA: data to compare against (NLA_NESTED: nft_data_attributes)
+ */
+enum nft_cmp_attributes {
+ NFTA_CMP_UNSPEC,
+ NFTA_CMP_SREG,
+ NFTA_CMP_OP,
+ NFTA_CMP_DATA,
+ __NFTA_CMP_MAX
+};
+#define NFTA_CMP_MAX (__NFTA_CMP_MAX - 1)
+
+enum nft_set_elem_flags {
+ NFT_SE_INTERVAL_END = 0x1,
+};
+
+enum nft_set_elem_attributes {
+ NFTA_SE_UNSPEC,
+ NFTA_SE_KEY,
+ NFTA_SE_DATA,
+ NFTA_SE_FLAGS,
+ __NFTA_SE_MAX
+};
+#define NFTA_SE_MAX (__NFTA_SE_MAX - 1)
+
+enum nft_set_flags {
+ NFT_SET_INTERVAL = 0x1,
+ NFT_SET_MAP = 0x2,
+};
+
+enum nft_set_attributes {
+ NFTA_SET_UNSPEC,
+ NFTA_SET_FLAGS,
+ NFTA_SET_SREG,
+ NFTA_SET_DREG,
+ NFTA_SET_KLEN,
+ NFTA_SET_DLEN,
+ NFTA_SET_ELEMENTS,
+ __NFTA_SET_MAX
+};
+#define NFTA_SET_MAX (__NFTA_SET_MAX - 1)
+
+enum nft_hash_flags {
+ NFT_HASH_MAP = 0x1,
+};
+
+enum nft_hash_elem_attributes {
+ NFTA_HE_UNSPEC,
+ NFTA_HE_KEY,
+ NFTA_HE_DATA,
+ __NFTA_HE_MAX
+};
+#define NFTA_HE_MAX (__NFTA_HE_MAX - 1)
+
+enum nft_hash_attributes {
+ NFTA_HASH_UNSPEC,
+ NFTA_HASH_FLAGS,
+ NFTA_HASH_SREG,
+ NFTA_HASH_DREG,
+ NFTA_HASH_KLEN,
+ NFTA_HASH_ELEMENTS,
+ __NFTA_HASH_MAX
+};
+#define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1)
+
+/**
+ * enum nft_payload_bases - nf_tables payload expression offset bases
+ *
+ * @NFT_PAYLOAD_LL_HEADER: link layer header
+ * @NFT_PAYLOAD_NETWORK_HEADER: network header
+ * @NFT_PAYLOAD_TRANSPORT_HEADER: transport header
+ */
+enum nft_payload_bases {
+ NFT_PAYLOAD_LL_HEADER,
+ NFT_PAYLOAD_NETWORK_HEADER,
+ NFT_PAYLOAD_TRANSPORT_HEADER,
+};
+
+/**
+ * enum nft_payload_attributes - nf_tables payload expression netlink attributes
+ *
+ * @NFTA_PAYLOAD_DREG: destination register to load data into (NLA_U32: nft_registers)
+ * @NFTA_PAYLOAD_BASE: payload base (NLA_U32: nft_payload_bases)
+ * @NFTA_PAYLOAD_OFFSET: payload offset relative to base (NLA_U32)
+ * @NFTA_PAYLOAD_LEN: payload length (NLA_U32)
+ */
+enum nft_payload_attributes {
+ NFTA_PAYLOAD_UNSPEC,
+ NFTA_PAYLOAD_DREG,
+ NFTA_PAYLOAD_BASE,
+ NFTA_PAYLOAD_OFFSET,
+ NFTA_PAYLOAD_LEN,
+ __NFTA_PAYLOAD_MAX
+};
+#define NFTA_PAYLOAD_MAX (__NFTA_PAYLOAD_MAX - 1)
+
+/**
+ * enum nft_exthdr_attributes - nf_tables IPv6 extension header expression netlink attributes
+ *
+ * @NFTA_EXTHDR_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_EXTHDR_TYPE: extension header type (NLA_U8)
+ * @NFTA_EXTHDR_OFFSET: extension header offset (NLA_U32)
+ * @NFTA_EXTHDR_LEN: extension header length (NLA_U32)
+ */
+enum nft_exthdr_attributes {
+ NFTA_EXTHDR_UNSPEC,
+ NFTA_EXTHDR_DREG,
+ NFTA_EXTHDR_TYPE,
+ NFTA_EXTHDR_OFFSET,
+ NFTA_EXTHDR_LEN,
+ __NFTA_EXTHDR_MAX
+};
+#define NFTA_EXTHDR_MAX (__NFTA_EXTHDR_MAX - 1)
+
+/**
+ * enum nft_meta_keys - nf_tables meta expression keys
+ *
+ * @NFT_META_LEN: packet length (skb->len)
+ * @NFT_META_PROTOCOL: packet ethertype protocol (skb->protocol), invalid in OUTPUT
+ * @NFT_META_PRIORITY: packet priority (skb->priority)
+ * @NFT_META_MARK: packet mark (skb->mark)
+ * @NFT_META_IIF: packet input interface index (dev->ifindex)
+ * @NFT_META_OIF: packet output interface index (dev->ifindex)
+ * @NFT_META_IIFNAME: packet input interface name (dev->name)
+ * @NFT_META_OIFNAME: packet output interface name (dev->name)
+ * @NFT_META_IIFTYPE: packet input interface type (dev->type)
+ * @NFT_META_OIFTYPE: packet output interface type (dev->type)
+ * @NFT_META_SKUID: originating socket UID (fsuid)
+ * @NFT_META_SKGID: originating socket GID (fsgid)
+ * @NFT_META_NFTRACE: packet nftrace bit
+ * @NFT_META_RTCLASSID: realm value of packet's route (skb->dst->tclassid)
+ * @NFT_META_SECMARK: packet secmark (skb->secmark)
+ */
+enum nft_meta_keys {
+ NFT_META_LEN,
+ NFT_META_PROTOCOL,
+ NFT_META_PRIORITY,
+ NFT_META_MARK,
+ NFT_META_IIF,
+ NFT_META_OIF,
+ NFT_META_IIFNAME,
+ NFT_META_OIFNAME,
+ NFT_META_IIFTYPE,
+ NFT_META_OIFTYPE,
+ NFT_META_SKUID,
+ NFT_META_SKGID,
+ NFT_META_NFTRACE,
+ NFT_META_RTCLASSID,
+ NFT_META_SECMARK,
+};
+
+/**
+ * enum nft_meta_attributes - nf_tables meta expression netlink attributes
+ *
+ * @NFTA_META_DREG: destination register (NLA_U32)
+ * @NFTA_META_KEY: meta data item to load (NLA_U32: nft_meta_keys)
+ */
+enum nft_meta_attributes {
+ NFTA_META_UNSPEC,
+ NFTA_META_DREG,
+ NFTA_META_KEY,
+ __NFTA_META_MAX
+};
+#define NFTA_META_MAX (__NFTA_META_MAX - 1)
+
+/**
+ * enum nft_ct_keys - nf_tables ct expression keys
+ *
+ * @NFT_CT_STATE: conntrack state (bitmask of enum ip_conntrack_info)
+ * @NFT_CT_DIRECTION: conntrack direction (enum ip_conntrack_dir)
+ * @NFT_CT_STATUS: conntrack status (bitmask of enum ip_conntrack_status)
+ * @NFT_CT_MARK: conntrack mark value
+ * @NFT_CT_SECMARK: conntrack secmark value
+ * @NFT_CT_EXPIRATION: relative conntrack expiration time in ms
+ * @NFT_CT_HELPER: connection tracking helper assigned to conntrack
+ * @NFT_CT_L3PROTOCOL: conntrack layer 3 protocol
+ * @NFT_CT_SRC: conntrack layer 3 protocol source (IPv4/IPv6 address)
+ * @NFT_CT_DST: conntrack layer 3 protocol destination (IPv4/IPv6 address)
+ * @NFT_CT_PROTOCOL: conntrack layer 4 protocol
+ * @NFT_CT_PROTO_SRC: conntrack layer 4 protocol source
+ * @NFT_CT_PROTO_DST: conntrack layer 4 protocol destination
+ */
+enum nft_ct_keys {
+ NFT_CT_STATE,
+ NFT_CT_DIRECTION,
+ NFT_CT_STATUS,
+ NFT_CT_MARK,
+ NFT_CT_SECMARK,
+ NFT_CT_EXPIRATION,
+ NFT_CT_HELPER,
+ NFT_CT_L3PROTOCOL,
+ NFT_CT_SRC,
+ NFT_CT_DST,
+ NFT_CT_PROTOCOL,
+ NFT_CT_PROTO_SRC,
+ NFT_CT_PROTO_DST,
+};
+
+/**
+ * enum nft_ct_attributes - nf_tables ct expression netlink attributes
+ *
+ * @NFTA_CT_DREG: destination register (NLA_U32)
+ * @NFTA_CT_KEY: conntrack data item to load (NLA_U32: nft_ct_keys)
+ * @NFTA_CT_DIRECTION: direction in case of directional keys (NLA_U8)
+ */
+enum nft_ct_attributes {
+ NFTA_CT_UNSPEC,
+ NFTA_CT_DREG,
+ NFTA_CT_KEY,
+ NFTA_CT_DIRECTION,
+ __NFTA_CT_MAX
+};
+#define NFTA_CT_MAX (__NFTA_CT_MAX - 1)
+
+/**
+ * enum nft_limit_attributes - nf_tables limit expression netlink attributes
+ *
+ * @NFTA_LIMIT_RATE: refill rate (NLA_U64)
+ * @NFTA_LIMIT_UNIT: refill unit (NLA_U64)
+ */
+enum nft_limit_attributes {
+ NFTA_LIMIT_UNSPEC,
+ NFTA_LIMIT_RATE,
+ NFTA_LIMIT_UNIT,
+ __NFTA_LIMIT_MAX
+};
+#define NFTA_LIMIT_MAX (__NFTA_LIMIT_MAX - 1)
+
+/**
+ * enum nft_counter_attributes - nf_tables counter expression netlink attributes
+ *
+ * @NFTA_COUNTER_BYTES: number of bytes (NLA_U64)
+ * @NFTA_COUNTER_PACKETS: number of packets (NLA_U64)
+ */
+enum nft_counter_attributes {
+ NFTA_COUNTER_UNSPEC,
+ NFTA_COUNTER_BYTES,
+ NFTA_COUNTER_PACKETS,
+ __NFTA_COUNTER_MAX
+};
+#define NFTA_COUNTER_MAX (__NFTA_COUNTER_MAX - 1)
+
+/**
+ * enum nft_log_attributes - nf_tables log expression netlink attributes
+ *
+ * @NFTA_LOG_GROUP: netlink group to send messages to (NLA_U32)
+ * @NFTA_LOG_PREFIX: prefix to prepend to log messages (NLA_STRING)
+ * @NFTA_LOG_SNAPLEN: length of payload to include in netlink message (NLA_U32)
+ * @NFTA_LOG_QTHRESHOLD: queue threshold (NLA_U32)
+ */
+enum nft_log_attributes {
+ NFTA_LOG_UNSPEC,
+ NFTA_LOG_GROUP,
+ NFTA_LOG_PREFIX,
+ NFTA_LOG_SNAPLEN,
+ NFTA_LOG_QTHRESHOLD,
+ __NFTA_LOG_MAX
+};
+#define NFTA_LOG_MAX (__NFTA_LOG_MAX - 1)
+
+/**
+ * enum nft_reject_types - nf_tables reject expression reject types
+ *
+ * @NFT_REJECT_ICMP_UNREACH: reject using ICMP unreachable
+ * @NFT_REJECT_TCP_RST: reject using TCP RST
+ */
+enum nft_reject_types {
+ NFT_REJECT_ICMP_UNREACH,
+ NFT_REJECT_TCP_RST,
+};
+
+/**
+ * enum nft_reject_attributes - nf_tables reject expression netlink attributes
+ *
+ * @NFTA_REJECT_TYPE: packet type to use (NLA_U32: nft_reject_types)
+ * @NFTA_REJECT_ICMP_CODE: ICMP code to use (NLA_U8)
+ */
+enum nft_reject_attributes {
+ NFTA_REJECT_UNSPEC,
+ NFTA_REJECT_TYPE,
+ NFTA_REJECT_ICMP_CODE,
+ __NFTA_REJECT_MAX
+};
+#define NFTA_REJECT_MAX (__NFTA_REJECT_MAX - 1)
+
+/**
+ * enum nft_nat_types - nf_tables nat expression NAT types
+ *
+ * @NFT_NAT_SNAT: source NAT
+ * @NFT_NAT_DNAT: destination NAT
+ */
+enum nft_nat_types {
+ NFT_NAT_SNAT,
+ NFT_NAT_DNAT,
+};
+
+/**
+ * enum nft_nat_attributes - nf_tables nat expression netlink attributes
+ *
+ * @NFTA_NAT_TYPE: NAT type (NLA_U32: nft_nat_types)
+ * @NFTA_NAT_ADDR_MIN: source register of address range start (NLA_U32: nft_registers)
+ * @NFTA_NAT_ADDR_MAX: source register of address range end (NLA_U32: nft_registers)
+ * @NFTA_NAT_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_NAT_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
+ */
+enum nft_nat_attributes {
+ NFTA_NAT_UNSPEC,
+ NFTA_NAT_TYPE,
+ NFTA_NAT_ADDR_MIN,
+ NFTA_NAT_ADDR_MAX,
+ NFTA_NAT_PROTO_MIN,
+ NFTA_NAT_PROTO_MAX,
+ __NFTA_NAT_MAX
+};
+#define NFTA_NAT_MAX (__NFTA_NAT_MAX - 1)
+
+#endif /* _LINUX_NF_TABLES_H */
diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h
index 4a4efafad5f4..d276c3bd55b8 100644
--- a/include/uapi/linux/netfilter/nfnetlink.h
+++ b/include/uapi/linux/netfilter/nfnetlink.h
@@ -18,6 +18,8 @@ enum nfnetlink_groups {
#define NFNLGRP_CONNTRACK_EXP_UPDATE NFNLGRP_CONNTRACK_EXP_UPDATE
NFNLGRP_CONNTRACK_EXP_DESTROY,
#define NFNLGRP_CONNTRACK_EXP_DESTROY NFNLGRP_CONNTRACK_EXP_DESTROY
+ NFNLGRP_NFTABLES,
+#define NFNLGRP_NFTABLES NFNLGRP_NFTABLES
__NFNLGRP_MAX,
};
#define NFNLGRP_MAX (__NFNLGRP_MAX - 1)
@@ -51,6 +53,7 @@ struct nfgenmsg {
#define NFNL_SUBSYS_ACCT 7
#define NFNL_SUBSYS_CTNETLINK_TIMEOUT 8
#define NFNL_SUBSYS_CTHELPER 9
-#define NFNL_SUBSYS_COUNT 10
+#define NFNL_SUBSYS_NFTABLES 10
+#define NFNL_SUBSYS_COUNT 11
#endif /* _UAPI_NFNETLINK_H */
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index a9aff9c7d027..68f8128147be 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -1,6 +1,9 @@
#
# Bridge netfilter configuration
#
+#
+config NF_TABLES_BRIDGE
+ tristate "Ethernet Bridge nf_tables support"
menuconfig BRIDGE_NF_EBTABLES
tristate "Ethernet Bridge tables (ebtables) support"
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index 0718699540b0..ea7629f58b3d 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -2,6 +2,8 @@
# Makefile for the netfilter modules for Link Layer filtering on a bridge.
#
+obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o
+
obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o
# tables
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
new file mode 100644
index 000000000000..bc5c21c911c0
--- /dev/null
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright (c) 2008 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/init.h>
+#include <linux/module.h>
+#include <linux/netfilter_bridge.h>
+#include <net/netfilter/nf_tables.h>
+
+static struct nft_af_info nft_af_bridge __read_mostly = {
+ .family = NFPROTO_BRIDGE,
+ .nhooks = NF_BR_NUMHOOKS,
+ .owner = THIS_MODULE,
+};
+
+static int __init nf_tables_bridge_init(void)
+{
+ return nft_register_afinfo(&nft_af_bridge);
+}
+
+static void __exit nf_tables_bridge_exit(void)
+{
+ nft_unregister_afinfo(&nft_af_bridge);
+}
+
+module_init(nf_tables_bridge_init);
+module_exit(nf_tables_bridge_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(AF_BRIDGE);
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 1657e39b291f..eb1d56ece361 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -36,6 +36,22 @@ config NF_CONNTRACK_PROC_COMPAT
If unsure, say Y.
+config NF_TABLES_IPV4
+ depends on NF_TABLES
+ tristate "IPv4 nf_tables support"
+
+config NFT_REJECT_IPV4
+ depends on NF_TABLES_IPV4
+ tristate "nf_tables IPv4 reject support"
+
+config NF_TABLE_ROUTE_IPV4
+ depends on NF_TABLES_IPV4
+ tristate "IPv4 nf_tables route table support"
+
+config NF_TABLE_NAT_IPV4
+ depends on NF_TABLES_IPV4
+ tristate "IPv4 nf_tables nat table support"
+
config IP_NF_IPTABLES
tristate "IP tables support (required for filtering/masq/NAT)"
default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 3622b248b6dd..b2f01cd2cd65 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -27,6 +27,11 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
# NAT protocols (nf_nat)
obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
+obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
+obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NF_TABLE_ROUTE_IPV4) += nf_table_route_ipv4.o
+obj-$(CONFIG_NF_TABLE_NAT_IPV4) += nf_table_nat_ipv4.o
+
# generic IP tables
obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
diff --git a/net/ipv4/netfilter/nf_table_nat_ipv4.c b/net/ipv4/netfilter/nf_table_nat_ipv4.c
new file mode 100644
index 000000000000..2a6f184c10bd
--- /dev/null
+++ b/net/ipv4/netfilter/nf_table_nat_ipv4.c
@@ -0,0 +1,409 @@
+/*
+ * Copyright (c) 2008 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/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/ip.h>
+
+struct nft_nat {
+ enum nft_registers sreg_addr_min:8;
+ enum nft_registers sreg_addr_max:8;
+ enum nft_registers sreg_proto_min:8;
+ enum nft_registers sreg_proto_max:8;
+ enum nf_nat_manip_type type;
+};
+
+static void nft_nat_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_nat *priv = nft_expr_priv(expr);
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
+ struct nf_nat_range range;
+
+ memset(&range, 0, sizeof(range));
+ if (priv->sreg_addr_min) {
+ range.min_addr.ip = data[priv->sreg_addr_min].data[0];
+ range.max_addr.ip = data[priv->sreg_addr_max].data[0];
+ range.flags |= NF_NAT_RANGE_MAP_IPS;
+ }
+
+ if (priv->sreg_proto_min) {
+ range.min_proto.all = data[priv->sreg_proto_min].data[0];
+ range.max_proto.all = data[priv->sreg_proto_max].data[0];
+ range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+ }
+
+ data[NFT_REG_VERDICT].verdict =
+ nf_nat_setup_info(ct, &range, priv->type);
+}
+
+static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
+ [NFTA_NAT_ADDR_MIN] = { .type = NLA_U32 },
+ [NFTA_NAT_ADDR_MAX] = { .type = NLA_U32 },
+ [NFTA_NAT_PROTO_MIN] = { .type = NLA_U32 },
+ [NFTA_NAT_PROTO_MAX] = { .type = NLA_U32 },
+ [NFTA_NAT_TYPE] = { .type = NLA_U32 },
+};
+
+static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_nat *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_NAT_TYPE] == NULL)
+ return -EINVAL;
+
+ switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) {
+ case NFT_NAT_SNAT:
+ priv->type = NF_NAT_MANIP_SRC;
+ break;
+ case NFT_NAT_DNAT:
+ priv->type = NF_NAT_MANIP_DST;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (tb[NFTA_NAT_ADDR_MIN]) {
+ priv->sreg_addr_min = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MIN]));
+ err = nft_validate_input_register(priv->sreg_addr_min);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[NFTA_NAT_ADDR_MAX]) {
+ priv->sreg_addr_max = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MAX]));
+ err = nft_validate_input_register(priv->sreg_addr_max);
+ if (err < 0)
+ return err;
+ } else
+ priv->sreg_addr_max = priv->sreg_addr_min;
+
+ if (tb[NFTA_NAT_PROTO_MIN]) {
+ priv->sreg_proto_min = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MIN]));
+ err = nft_validate_input_register(priv->sreg_proto_min);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[NFTA_NAT_PROTO_MAX]) {
+ priv->sreg_proto_max = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MAX]));
+ err = nft_validate_input_register(priv->sreg_proto_max);
+ if (err < 0)
+ return err;
+ } else
+ priv->sreg_proto_max = priv->sreg_proto_min;
+
+ return 0;
+}
+
+static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_nat *priv = nft_expr_priv(expr);
+
+ switch (priv->type) {
+ case NF_NAT_MANIP_SRC:
+ if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT)))
+ goto nla_put_failure;
+ break;
+ case NF_NAT_MANIP_DST:
+ if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT)))
+ goto nla_put_failure;
+ break;
+ }
+
+ if (nla_put_be32(skb, NFTA_NAT_ADDR_MIN, htonl(priv->sreg_addr_min)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_NAT_ADDR_MAX, htonl(priv->sreg_addr_max)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_NAT_PROTO_MIN, htonl(priv->sreg_proto_min)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_NAT_PROTO_MAX, htonl(priv->sreg_proto_max)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_nat_ops __read_mostly = {
+ .name = "nat",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+ .owner = THIS_MODULE,
+ .eval = nft_nat_eval,
+ .init = nft_nat_init,
+ .dump = nft_nat_dump,
+ .policy = nft_nat_policy,
+ .maxattr = NFTA_NAT_MAX,
+};
+
+/*
+ * NAT table
+ */
+
+static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+ struct nf_conn_nat *nat;
+ enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+ unsigned int ret;
+
+ if (ct == NULL || nf_ct_is_untracked(ct))
+ return NF_ACCEPT;
+
+ NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
+
+ nat = nfct_nat(ct);
+ if (nat == NULL) {
+ /* Conntrack module was loaded late, can't add extension. */
+ if (nf_ct_is_confirmed(ct))
+ return NF_ACCEPT;
+ nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+ if (nat == NULL)
+ return NF_ACCEPT;
+ }
+
+ switch (ctinfo) {
+ case IP_CT_RELATED:
+ case IP_CT_RELATED + IP_CT_IS_REPLY:
+ if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+ if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+ ops->hooknum))
+ return NF_DROP;
+ else
+ return NF_ACCEPT;
+ }
+ /* Fall through */
+ case IP_CT_NEW:
+ if (nf_nat_initialized(ct, maniptype))
+ break;
+
+ ret = nft_do_chain(ops, skb, in, out, okfn);
+ if (ret != NF_ACCEPT)
+ return ret;
+ if (!nf_nat_initialized(ct, maniptype)) {
+ ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+ if (ret != NF_ACCEPT)
+ return ret;
+ }
+ default:
+ break;
+ }
+
+ return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+}
+
+static unsigned int nf_nat_prerouting(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ __be32 daddr = ip_hdr(skb)->daddr;
+ unsigned int ret;
+
+ ret = nf_nat_fn(ops, skb, in, out, okfn);
+ if (ret != NF_DROP && ret != NF_STOLEN &&
+ ip_hdr(skb)->daddr != daddr) {
+ skb_dst_drop(skb);
+ }
+ return ret;
+}
+
+static unsigned int nf_nat_postrouting(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ enum ip_conntrack_info ctinfo __maybe_unused;
+ const struct nf_conn *ct __maybe_unused;
+ unsigned int ret;
+
+ ret = nf_nat_fn(ops, skb, in, out, okfn);
+#ifdef CONFIG_XFRM
+ if (ret != NF_DROP && ret != NF_STOLEN &&
+ (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+ enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+ if (ct->tuplehash[dir].tuple.src.u3.ip !=
+ ct->tuplehash[!dir].tuple.dst.u3.ip ||
+ ct->tuplehash[dir].tuple.src.u.all !=
+ ct->tuplehash[!dir].tuple.dst.u.all)
+ return nf_xfrm_me_harder(skb, AF_INET) == 0 ?
+ ret : NF_DROP;
+ }
+#endif
+ return ret;
+}
+
+static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ enum ip_conntrack_info ctinfo;
+ const struct nf_conn *ct;
+ unsigned int ret;
+
+ ret = nf_nat_fn(ops, skb, in, out, okfn);
+ if (ret != NF_DROP && ret != NF_STOLEN &&
+ (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+ enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+ if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+ ct->tuplehash[!dir].tuple.src.u3.ip) {
+ if (ip_route_me_harder(skb, RTN_UNSPEC))
+ ret = NF_DROP;
+ }
+#ifdef CONFIG_XFRM
+ else if (ct->tuplehash[dir].tuple.dst.u.all !=
+ ct->tuplehash[!dir].tuple.src.u.all)
+ if (nf_xfrm_me_harder(skb, AF_INET))
+ ret = NF_DROP;
+#endif
+ }
+ return ret;
+}
+
+static struct nft_base_chain nf_chain_nat_prerouting __read_mostly = {
+ .chain = {
+ .name = "PREROUTING",
+ .rules = LIST_HEAD_INIT(nf_chain_nat_prerouting.chain.rules),
+ .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+ },
+ .ops = {
+ .hook = nf_nat_prerouting,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_PRE_ROUTING,
+ .priority = NF_IP_PRI_NAT_DST,
+ .priv = &nf_chain_nat_prerouting.chain,
+ },
+};
+
+static struct nft_base_chain nf_chain_nat_postrouting __read_mostly = {
+ .chain = {
+ .name = "POSTROUTING",
+ .rules = LIST_HEAD_INIT(nf_chain_nat_postrouting.chain.rules),
+ .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+ },
+ .ops = {
+ .hook = nf_nat_postrouting,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_POST_ROUTING,
+ .priority = NF_IP_PRI_NAT_SRC,
+ .priv = &nf_chain_nat_postrouting.chain,
+ },
+};
+
+static struct nft_base_chain nf_chain_nat_output __read_mostly = {
+ .chain = {
+ .name = "OUTPUT",
+ .rules = LIST_HEAD_INIT(nf_chain_nat_output.chain.rules),
+ .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+ },
+ .ops = {
+ .hook = nf_nat_output,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = NF_IP_PRI_NAT_DST,
+ .priv = &nf_chain_nat_output.chain,
+ },
+};
+
+static struct nft_base_chain nf_chain_nat_input __read_mostly = {
+ .chain = {
+ .name = "INPUT",
+ .rules = LIST_HEAD_INIT(nf_chain_nat_input.chain.rules),
+ .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+ },
+ .ops = {
+ .hook = nf_nat_fn,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = NF_IP_PRI_NAT_SRC,
+ .priv = &nf_chain_nat_input.chain,
+ },
+};
+
+
+static struct nft_table nf_table_nat_ipv4 __read_mostly = {
+ .name = "nat",
+ .chains = LIST_HEAD_INIT(nf_table_nat_ipv4.chains),
+};
+
+static int __init nf_table_nat_init(void)
+{
+ int err;
+
+ list_add_tail(&nf_chain_nat_prerouting.chain.list,
+ &nf_table_nat_ipv4.chains);
+ list_add_tail(&nf_chain_nat_postrouting.chain.list,
+ &nf_table_nat_ipv4.chains);
+ list_add_tail(&nf_chain_nat_output.chain.list,
+ &nf_table_nat_ipv4.chains);
+ list_add_tail(&nf_chain_nat_input.chain.list,
+ &nf_table_nat_ipv4.chains);
+
+ err = nft_register_table(&nf_table_nat_ipv4, NFPROTO_IPV4);
+ if (err < 0)
+ goto err1;
+
+ err = nft_register_expr(&nft_nat_ops);
+ if (err < 0)
+ goto err2;
+
+ return 0;
+
+err2:
+ nft_unregister_table(&nf_table_nat_ipv4, NFPROTO_IPV4);
+err1:
+ return err;
+}
+
+static void __exit nf_table_nat_exit(void)
+{
+ nft_unregister_expr(&nft_nat_ops);
+ nft_unregister_table(&nf_table_nat_ipv4, AF_INET);
+}
+
+module_init(nf_table_nat_init);
+module_exit(nf_table_nat_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_TABLE(AF_INET, "nat");
+MODULE_ALIAS_NFT_EXPR("nat");
diff --git a/net/ipv4/netfilter/nf_table_route_ipv4.c b/net/ipv4/netfilter/nf_table_route_ipv4.c
new file mode 100644
index 000000000000..4f257a1ed661
--- /dev/null
+++ b/net/ipv4/netfilter/nf_table_route_ipv4.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2008 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.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ unsigned int ret;
+ u32 mark;
+ __be32 saddr, daddr;
+ u_int8_t tos;
+ const struct iphdr *iph;
+
+ /* root is playing with raw sockets. */
+ if (skb->len < sizeof(struct iphdr) ||
+ ip_hdrlen(skb) < sizeof(struct iphdr))
+ return NF_ACCEPT;
+
+ mark = skb->mark;
+ iph = ip_hdr(skb);
+ saddr = iph->saddr;
+ daddr = iph->daddr;
+ tos = iph->tos;
+
+ ret = nft_do_chain(ops, skb, in, out, okfn);
+ if (ret != NF_DROP && ret != NF_QUEUE) {
+ iph = ip_hdr(skb);
+
+ if (iph->saddr != saddr ||
+ iph->daddr != daddr ||
+ skb->mark != mark ||
+ iph->tos != tos)
+ if (ip_route_me_harder(skb, RTN_UNSPEC))
+ ret = NF_DROP;
+ }
+ return ret;
+}
+
+static struct nft_base_chain nf_chain_route_output __read_mostly = {
+ .chain = {
+ .name = "OUTPUT",
+ .rules = LIST_HEAD_INIT(nf_chain_route_output.chain.rules),
+ .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+ },
+ .ops = {
+ .hook = nf_route_table_hook,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = NF_IP_PRI_MANGLE,
+ .priv = &nf_chain_route_output.chain,
+ },
+};
+
+static struct nft_table nf_table_route_ipv4 __read_mostly = {
+ .name = "route",
+ .chains = LIST_HEAD_INIT(nf_table_route_ipv4.chains),
+};
+
+static int __init nf_table_route_init(void)
+{
+ list_add_tail(&nf_chain_route_output.chain.list,
+ &nf_table_route_ipv4.chains);
+ return nft_register_table(&nf_table_route_ipv4, NFPROTO_IPV4);
+}
+
+static void __exit nf_table_route_exit(void)
+{
+ nft_unregister_table(&nf_table_route_ipv4, NFPROTO_IPV4);
+}
+
+module_init(nf_table_route_init);
+module_exit(nf_table_route_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_TABLE(AF_INET, "route");
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
new file mode 100644
index 000000000000..63d0a3bf53d3
--- /dev/null
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2008 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/init.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/netfilter_ipv4.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/ip.h>
+
+static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ if (unlikely(skb->len < sizeof(struct iphdr) ||
+ ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) {
+ if (net_ratelimit())
+ pr_info("nf_tables_ipv4: ignoring short SOCK_RAW "
+ "packet\n");
+ return NF_ACCEPT;
+ }
+
+ return nft_do_chain(ops, skb, in, out, okfn);
+}
+
+static struct nft_af_info nft_af_ipv4 __read_mostly = {
+ .family = NFPROTO_IPV4,
+ .nhooks = NF_INET_NUMHOOKS,
+ .owner = THIS_MODULE,
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nft_ipv4_output,
+ },
+};
+
+static int __init nf_tables_ipv4_init(void)
+{
+ return nft_register_afinfo(&nft_af_ipv4);
+}
+
+static void __exit nf_tables_ipv4_exit(void)
+{
+ nft_unregister_afinfo(&nft_af_ipv4);
+}
+
+module_init(nf_tables_ipv4_init);
+module_exit(nf_tables_ipv4_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(AF_INET);
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
new file mode 100644
index 000000000000..b4ee8d3bb1e4
--- /dev/null
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/icmp.h>
+
+struct nft_reject {
+ enum nft_reject_types type:8;
+ u8 icmp_code;
+};
+
+static void nft_reject_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_reject *priv = nft_expr_priv(expr);
+
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ icmp_send(pkt->skb, ICMP_DEST_UNREACH, priv->icmp_code, 0);
+ break;
+ case NFT_REJECT_TCP_RST:
+ break;
+ }
+
+ data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+
+static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
+ [NFTA_REJECT_TYPE] = { .type = NLA_U32 },
+ [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 },
+};
+
+static int nft_reject_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_reject *priv = nft_expr_priv(expr);
+
+ if (tb[NFTA_REJECT_TYPE] == NULL)
+ return -EINVAL;
+
+ priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+ return -EINVAL;
+ priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+ case NFT_REJECT_TCP_RST:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_reject *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type))
+ goto nla_put_failure;
+
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+ goto nla_put_failure;
+ break;
+ }
+
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops reject_ops __read_mostly = {
+ .name = "reject",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+ .owner = THIS_MODULE,
+ .eval = nft_reject_eval,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+ .policy = nft_reject_policy,
+ .maxattr = NFTA_REJECT_MAX,
+};
+
+static int __init nft_reject_module_init(void)
+{
+ return nft_register_expr(&reject_ops);
+}
+
+static void __exit nft_reject_module_exit(void)
+{
+ nft_unregister_expr(&reject_ops);
+}
+
+module_init(nft_reject_module_init);
+module_exit(nft_reject_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("reject");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index a7f842b29b67..5677e38eeca3 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -25,6 +25,14 @@ config NF_CONNTRACK_IPV6
To compile it as a module, choose M here. If unsure, say N.
+config NF_TABLES_IPV6
+ depends on NF_TABLES
+ tristate "IPv6 nf_tables support"
+
+config NF_TABLE_ROUTE_IPV6
+ depends on NF_TABLES_IPV6
+ tristate "IPv6 nf_tables route table support"
+
config IP6_NF_IPTABLES
tristate "IP6 tables support (required for filtering)"
depends on INET && IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 2b53738f798c..956af4492d10 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -23,6 +23,10 @@ obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
+# nf_tables
+obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
+obj-$(CONFIG_NF_TABLE_ROUTE_IPV6) += nf_table_route_ipv6.o
+
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
diff --git a/net/ipv6/netfilter/nf_table_route_ipv6.c b/net/ipv6/netfilter/nf_table_route_ipv6.c
new file mode 100644
index 000000000000..48ac65c7b398
--- /dev/null
+++ b/net/ipv6/netfilter/nf_table_route_ipv6.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright (c) 2008 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/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/route.h>
+
+static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ unsigned int ret;
+ struct in6_addr saddr, daddr;
+ u_int8_t hop_limit;
+ u32 mark, flowlabel;
+
+ /* save source/dest address, mark, hoplimit, flowlabel, priority */
+ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+ memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+ mark = skb->mark;
+ hop_limit = ipv6_hdr(skb)->hop_limit;
+
+ /* flowlabel and prio (includes version, which shouldn't change either */
+ flowlabel = *((u32 *)ipv6_hdr(skb));
+
+ ret = nft_do_chain(ops, skb, in, out, okfn);
+ if (ret != NF_DROP && ret != NF_QUEUE &&
+ (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
+ memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
+ skb->mark != mark ||
+ ipv6_hdr(skb)->hop_limit != hop_limit ||
+ flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
+ return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP;
+
+ return ret;
+}
+
+static struct nft_base_chain nf_chain_route_output __read_mostly = {
+ .chain = {
+ .name = "OUTPUT",
+ .rules = LIST_HEAD_INIT(nf_chain_route_output.chain.rules),
+ .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+ },
+ .ops = {
+ .hook = nf_route_table_hook,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV6,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = NF_IP6_PRI_MANGLE,
+ .priv = &nf_chain_route_output.chain,
+ },
+};
+
+static struct nft_table nf_table_route_ipv6 __read_mostly = {
+ .name = "route",
+ .chains = LIST_HEAD_INIT(nf_table_route_ipv6.chains),
+};
+
+static int __init nf_table_route_init(void)
+{
+ list_add_tail(&nf_chain_route_output.chain.list,
+ &nf_table_route_ipv6.chains);
+ return nft_register_table(&nf_table_route_ipv6, NFPROTO_IPV6);
+}
+
+static void __exit nf_table_route_exit(void)
+{
+ nft_unregister_table(&nf_table_route_ipv6, NFPROTO_IPV6);
+}
+
+module_init(nf_table_route_init);
+module_exit(nf_table_route_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_TABLE(AF_INET6, "route");
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
new file mode 100644
index 000000000000..e0717cea4913
--- /dev/null
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2008 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/init.h>
+#include <linux/module.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_tables.h>
+
+static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ if (unlikely(skb->len < sizeof(struct ipv6hdr))) {
+ if (net_ratelimit())
+ pr_info("nf_tables_ipv6: ignoring short SOCK_RAW "
+ "packet\n");
+ return NF_ACCEPT;
+ }
+
+ return nft_do_chain(ops, skb, in, out, okfn);
+}
+
+static struct nft_af_info nft_af_ipv6 __read_mostly = {
+ .family = NFPROTO_IPV6,
+ .nhooks = NF_INET_NUMHOOKS,
+ .owner = THIS_MODULE,
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nft_ipv6_output,
+ },
+};
+
+static int __init nf_tables_ipv6_init(void)
+{
+ return nft_register_afinfo(&nft_af_ipv6);
+}
+
+static void __exit nf_tables_ipv6_exit(void)
+{
+ nft_unregister_afinfo(&nft_af_ipv6);
+}
+
+module_init(nf_tables_ipv6_init);
+module_exit(nf_tables_ipv6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(AF_INET6);
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6e839b6dff2b..c271e1af93b5 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -413,6 +413,43 @@ config NETFILTER_SYNPROXY
endif # NF_CONNTRACK
+config NF_TABLES
+ depends on NETFILTER_NETLINK
+ tristate "Netfilter nf_tables support"
+
+config NFT_EXTHDR
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables IPv6 exthdr module"
+
+config NFT_META
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables meta module"
+
+config NFT_CT
+ depends on NF_TABLES
+ depends on NF_CONNTRACK
+ tristate "Netfilter nf_tables conntrack module"
+
+config NFT_SET
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables set module"
+
+config NFT_HASH
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables hash module"
+
+config NFT_COUNTER
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables counter module"
+
+config NFT_LOG
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables log module"
+
+config NFT_LIMIT
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables limit module"
+
config NETFILTER_XTABLES
tristate "Netfilter Xtables support (required for ip_tables)"
default m if NETFILTER_ADVANCED=n
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index c3a0a12907f6..1ca3f3932826 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -64,6 +64,22 @@ obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
# SYNPROXY
obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
+# nf_tables
+nf_tables-objs += nf_tables_core.o nf_tables_api.o
+nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
+nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
+
+obj-$(CONFIG_NF_TABLES) += nf_tables.o
+obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o
+obj-$(CONFIG_NFT_META) += nft_meta.o
+obj-$(CONFIG_NFT_CT) += nft_ct.o
+obj-$(CONFIG_NFT_LIMIT) += nft_limit.o
+#nf_tables-objs += nft_meta_target.o
+obj-$(CONFIG_NFT_SET) += nft_set.o
+obj-$(CONFIG_NFT_HASH) += nft_hash.o
+obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
+obj-$(CONFIG_NFT_LOG) += nft_log.o
+
# generic X tables
obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
new file mode 100644
index 000000000000..7d59c89c6c75
--- /dev/null
+++ b/net/netfilter/nf_tables_api.c
@@ -0,0 +1,1760 @@
+/*
+ * Copyright (c) 2007, 2008 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/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/sock.h>
+
+static LIST_HEAD(nf_tables_afinfo);
+static LIST_HEAD(nf_tables_expressions);
+
+/**
+ * nft_register_afinfo - register nf_tables address family info
+ *
+ * @afi: address family info to register
+ *
+ * Register the address family for use with nf_tables. Returns zero on
+ * success or a negative errno code otherwise.
+ */
+int nft_register_afinfo(struct nft_af_info *afi)
+{
+ INIT_LIST_HEAD(&afi->tables);
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_add_tail(&afi->list, &nf_tables_afinfo);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nft_register_afinfo);
+
+/**
+ * nft_unregister_afinfo - unregister nf_tables address family info
+ *
+ * @afi: address family info to unregister
+ *
+ * Unregister the address family for use with nf_tables.
+ */
+void nft_unregister_afinfo(struct nft_af_info *afi)
+{
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_del(&afi->list);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
+
+static struct nft_af_info *nft_afinfo_lookup(int family)
+{
+ struct nft_af_info *afi;
+
+ list_for_each_entry(afi, &nf_tables_afinfo, list) {
+ if (afi->family == family)
+ return afi;
+ }
+ return NULL;
+}
+
+static struct nft_af_info *nf_tables_afinfo_lookup(int family, bool autoload)
+{
+ struct nft_af_info *afi;
+
+ afi = nft_afinfo_lookup(family);
+ if (afi != NULL)
+ return afi;
+#ifdef CONFIG_MODULES
+ if (autoload) {
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ request_module("nft-afinfo-%u", family);
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ afi = nft_afinfo_lookup(family);
+ if (afi != NULL)
+ return ERR_PTR(-EAGAIN);
+ }
+#endif
+ return ERR_PTR(-EAFNOSUPPORT);
+}
+
+/*
+ * Tables
+ */
+
+static struct nft_table *nft_table_lookup(const struct nft_af_info *afi,
+ const struct nlattr *nla)
+{
+ struct nft_table *table;
+
+ list_for_each_entry(table, &afi->tables, list) {
+ if (!nla_strcmp(nla, table->name))
+ return table;
+ }
+ return NULL;
+}
+
+static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi,
+ const struct nlattr *nla,
+ bool autoload)
+{
+ struct nft_table *table;
+
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
+ table = nft_table_lookup(afi, nla);
+ if (table != NULL)
+ return table;
+
+#ifdef CONFIG_MODULES
+ if (autoload) {
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ request_module("nft-table-%u-%*.s", afi->family,
+ nla_len(nla)-1, (const char *)nla_data(nla));
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ if (nft_table_lookup(afi, nla))
+ return ERR_PTR(-EAGAIN);
+ }
+#endif
+ return ERR_PTR(-ENOENT);
+}
+
+static inline u64 nf_tables_alloc_handle(struct nft_table *table)
+{
+ return ++table->hgenerator;
+}
+
+static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
+ [NFTA_TABLE_NAME] = { .type = NLA_STRING },
+};
+
+static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
+ int event, u32 flags, int family,
+ const struct nft_table *table)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+
+ event |= NFNL_SUBSYS_NFTABLES << 8;
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
+ if (nlh == NULL)
+ goto nla_put_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = family;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ if (nla_put_string(skb, NFTA_TABLE_NAME, table->name))
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_trim(skb, nlh);
+ return -1;
+}
+
+static int nf_tables_table_notify(const struct sk_buff *oskb,
+ const struct nlmsghdr *nlh,
+ const struct nft_table *table,
+ int event, int family)
+{
+ struct sk_buff *skb;
+ u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+ u32 seq = nlh ? nlh->nlmsg_seq : 0;
+ struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
+ bool report;
+ int err;
+
+ report = nlh ? nlmsg_report(nlh) : false;
+ if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+ return 0;
+
+ err = -ENOBUFS;
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (skb == NULL)
+ goto err;
+
+ err = nf_tables_fill_table_info(skb, portid, seq, event, 0,
+ family, table);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto err;
+ }
+
+ err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+ GFP_KERNEL);
+err:
+ if (err < 0)
+ nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+ return err;
+}
+
+static int nf_tables_dump_tables(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ unsigned int idx = 0, s_idx = cb->args[0];
+ int family = nfmsg->nfgen_family;
+
+ list_for_each_entry(afi, &nf_tables_afinfo, list) {
+ if (family != NFPROTO_UNSPEC && family != afi->family)
+ continue;
+
+ list_for_each_entry(table, &afi->tables, list) {
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (nf_tables_fill_table_info(skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWTABLE,
+ NLM_F_MULTI,
+ afi->family, table) < 0)
+ goto done;
+cont:
+ idx++;
+ }
+ }
+done:
+ cb->args[0] = idx;
+ return skb->len;
+}
+
+static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ struct sk_buff *skb2;
+ int family = nfmsg->nfgen_family;
+ int err;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .dump = nf_tables_dump_tables,
+ };
+ return netlink_dump_start(nlsk, skb, nlh, &c);
+ }
+
+ afi = nf_tables_afinfo_lookup(family, false);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], false);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb2)
+ return -ENOMEM;
+
+ err = nf_tables_fill_table_info(skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0,
+ family, table);
+ if (err < 0)
+ goto err;
+
+ return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+ kfree_skb(skb2);
+ return err;
+}
+
+static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nlattr *name;
+ struct nft_af_info *afi;
+ struct nft_table *table;
+ int family = nfmsg->nfgen_family;
+
+ afi = nf_tables_afinfo_lookup(family, true);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ name = nla[NFTA_TABLE_NAME];
+ table = nf_tables_table_lookup(afi, name, false);
+ if (IS_ERR(table)) {
+ if (PTR_ERR(table) != -ENOENT)
+ return PTR_ERR(table);
+ table = NULL;
+ }
+
+ if (table != NULL) {
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+ if (nlh->nlmsg_flags & NLM_F_REPLACE)
+ return -EOPNOTSUPP;
+ return 0;
+ }
+
+ table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL);
+ if (table == NULL)
+ return -ENOMEM;
+
+ nla_strlcpy(table->name, name, nla_len(name));
+ INIT_LIST_HEAD(&table->chains);
+
+ list_add_tail(&table->list, &afi->tables);
+ nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+ return 0;
+}
+
+static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ struct nft_af_info *afi;
+ struct nft_table *table;
+ int family = nfmsg->nfgen_family;
+
+ afi = nf_tables_afinfo_lookup(family, false);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], false);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ if (table->flags & NFT_TABLE_BUILTIN)
+ return -EOPNOTSUPP;
+
+ if (table->use)
+ return -EBUSY;
+
+ list_del(&table->list);
+ nf_tables_table_notify(skb, nlh, table, NFT_MSG_DELTABLE, family);
+ kfree(table);
+ return 0;
+}
+
+static struct nft_table *__nf_tables_table_lookup(const struct nft_af_info *afi,
+ const char *name)
+{
+ struct nft_table *table;
+
+ list_for_each_entry(table, &afi->tables, list) {
+ if (!strcmp(name, table->name))
+ return table;
+ }
+
+ return ERR_PTR(-ENOENT);
+}
+
+static int nf_tables_chain_notify(const struct sk_buff *oskb,
+ const struct nlmsghdr *nlh,
+ const struct nft_table *table,
+ const struct nft_chain *chain,
+ int event, int family);
+
+/**
+ * nft_register_table - register a built-in table
+ *
+ * @table: the table to register
+ * @family: protocol family to register table with
+ *
+ * Register a built-in table for use with nf_tables. Returns zero on
+ * success or a negative errno code otherwise.
+ */
+int nft_register_table(struct nft_table *table, int family)
+{
+ struct nft_af_info *afi;
+ struct nft_table *t;
+ struct nft_chain *chain;
+ int err;
+
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+again:
+ afi = nf_tables_afinfo_lookup(family, true);
+ if (IS_ERR(afi)) {
+ err = PTR_ERR(afi);
+ if (err == -EAGAIN)
+ goto again;
+ goto err;
+ }
+
+ t = __nf_tables_table_lookup(afi, table->name);
+ if (IS_ERR(t)) {
+ err = PTR_ERR(t);
+ if (err != -ENOENT)
+ goto err;
+ t = NULL;
+ }
+
+ if (t != NULL) {
+ err = -EEXIST;
+ goto err;
+ }
+
+ table->flags |= NFT_TABLE_BUILTIN;
+ list_add_tail(&table->list, &afi->tables);
+ nf_tables_table_notify(NULL, NULL, table, NFT_MSG_NEWTABLE, family);
+ list_for_each_entry(chain, &table->chains, list)
+ nf_tables_chain_notify(NULL, NULL, table, chain,
+ NFT_MSG_NEWCHAIN, family);
+ err = 0;
+err:
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ return err;
+}
+EXPORT_SYMBOL_GPL(nft_register_table);
+
+/**
+ * nft_unregister_table - unregister a built-in table
+ *
+ * @table: the table to unregister
+ * @family: protocol family to unregister table with
+ *
+ * Unregister a built-in table for use with nf_tables.
+ */
+void nft_unregister_table(struct nft_table *table, int family)
+{
+ struct nft_chain *chain;
+
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_del(&table->list);
+ list_for_each_entry(chain, &table->chains, list)
+ nf_tables_chain_notify(NULL, NULL, table, chain,
+ NFT_MSG_DELCHAIN, family);
+ nf_tables_table_notify(NULL, NULL, table, NFT_MSG_DELTABLE, family);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_table);
+
+/*
+ * Chains
+ */
+
+static struct nft_chain *
+nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle)
+{
+ struct nft_chain *chain;
+
+ list_for_each_entry(chain, &table->chains, list) {
+ if (chain->handle == handle)
+ return chain;
+ }
+
+ return ERR_PTR(-ENOENT);
+}
+
+static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table,
+ const struct nlattr *nla)
+{
+ struct nft_chain *chain;
+
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
+ list_for_each_entry(chain, &table->chains, list) {
+ if (!nla_strcmp(nla, chain->name))
+ return chain;
+ }
+
+ return ERR_PTR(-ENOENT);
+}
+
+static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
+ [NFTA_CHAIN_TABLE] = { .type = NLA_STRING },
+ [NFTA_CHAIN_HANDLE] = { .type = NLA_U64 },
+ [NFTA_CHAIN_NAME] = { .type = NLA_STRING,
+ .len = NFT_CHAIN_MAXNAMELEN - 1 },
+ [NFTA_CHAIN_HOOK] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
+ [NFTA_HOOK_HOOKNUM] = { .type = NLA_U32 },
+ [NFTA_HOOK_PRIORITY] = { .type = NLA_U32 },
+};
+
+static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
+ int event, u32 flags, int family,
+ const struct nft_table *table,
+ const struct nft_chain *chain)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+
+ event |= NFNL_SUBSYS_NFTABLES << 8;
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
+ if (nlh == NULL)
+ goto nla_put_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = family;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name))
+ goto nla_put_failure;
+ if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle)))
+ goto nla_put_failure;
+ if (nla_put_string(skb, NFTA_CHAIN_NAME, chain->name))
+ goto nla_put_failure;
+
+ if (chain->flags & NFT_BASE_CHAIN) {
+ const struct nf_hook_ops *ops = &nft_base_chain(chain)->ops;
+ struct nlattr *nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
+ if (nest == NULL)
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
+ goto nla_put_failure;
+ nla_nest_end(skb, nest);
+ }
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_trim(skb, nlh);
+ return -1;
+}
+
+static int nf_tables_chain_notify(const struct sk_buff *oskb,
+ const struct nlmsghdr *nlh,
+ const struct nft_table *table,
+ const struct nft_chain *chain,
+ int event, int family)
+{
+ struct sk_buff *skb;
+ u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+ struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
+ u32 seq = nlh ? nlh->nlmsg_seq : 0;
+ bool report;
+ int err;
+
+ report = nlh ? nlmsg_report(nlh) : false;
+ if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+ return 0;
+
+ err = -ENOBUFS;
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (skb == NULL)
+ goto err;
+
+ err = nf_tables_fill_chain_info(skb, portid, seq, event, 0, family,
+ table, chain);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto err;
+ }
+
+ err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+ GFP_KERNEL);
+err:
+ if (err < 0)
+ nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+ return err;
+}
+
+static int nf_tables_dump_chains(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ const struct nft_chain *chain;
+ unsigned int idx = 0, s_idx = cb->args[0];
+ int family = nfmsg->nfgen_family;
+
+ list_for_each_entry(afi, &nf_tables_afinfo, list) {
+ if (family != NFPROTO_UNSPEC && family != afi->family)
+ continue;
+
+ list_for_each_entry(table, &afi->tables, list) {
+ list_for_each_entry(chain, &table->chains, list) {
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (nf_tables_fill_chain_info(skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWCHAIN,
+ NLM_F_MULTI,
+ afi->family, table, chain) < 0)
+ goto done;
+cont:
+ idx++;
+ }
+ }
+ }
+done:
+ cb->args[0] = idx;
+ return skb->len;
+}
+
+
+static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ const struct nft_chain *chain;
+ struct sk_buff *skb2;
+ int family = nfmsg->nfgen_family;
+ int err;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .dump = nf_tables_dump_chains,
+ };
+ return netlink_dump_start(nlsk, skb, nlh, &c);
+ }
+
+ afi = nf_tables_afinfo_lookup(family, false);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], false);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+
+ skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb2)
+ return -ENOMEM;
+
+ err = nf_tables_fill_chain_info(skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0,
+ family, table, chain);
+ if (err < 0)
+ goto err;
+
+ return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+ kfree_skb(skb2);
+ return err;
+}
+
+static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nlattr * uninitialized_var(name);
+ const struct nft_af_info *afi;
+ struct nft_table *table;
+ struct nft_chain *chain;
+ struct nft_base_chain *basechain;
+ struct nlattr *ha[NFTA_HOOK_MAX + 1];
+ int family = nfmsg->nfgen_family;
+ u64 handle = 0;
+ int err;
+ bool create;
+
+ create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
+
+ afi = nf_tables_afinfo_lookup(family, true);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], create);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ if (table->use == UINT_MAX)
+ return -EOVERFLOW;
+
+ chain = NULL;
+ name = nla[NFTA_CHAIN_NAME];
+
+ if (nla[NFTA_CHAIN_HANDLE]) {
+ handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
+ chain = nf_tables_chain_lookup_byhandle(table, handle);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+ } else {
+ chain = nf_tables_chain_lookup(table, name);
+ if (IS_ERR(chain)) {
+ if (PTR_ERR(chain) != -ENOENT)
+ return PTR_ERR(chain);
+ chain = NULL;
+ }
+ }
+
+ if (chain != NULL) {
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+ if (nlh->nlmsg_flags & NLM_F_REPLACE)
+ return -EOPNOTSUPP;
+
+ if (nla[NFTA_CHAIN_HANDLE] && name &&
+ !IS_ERR(nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME])))
+ return -EEXIST;
+
+ if (nla[NFTA_CHAIN_HANDLE] && name)
+ nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
+
+ goto notify;
+ }
+
+ if (nla[NFTA_CHAIN_HOOK]) {
+ struct nf_hook_ops *ops;
+
+ err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
+ nft_hook_policy);
+ if (err < 0)
+ return err;
+ if (ha[NFTA_HOOK_HOOKNUM] == NULL ||
+ ha[NFTA_HOOK_PRIORITY] == NULL)
+ return -EINVAL;
+ if (ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])) >= afi->nhooks)
+ return -EINVAL;
+
+ basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
+ if (basechain == NULL)
+ return -ENOMEM;
+ chain = &basechain->chain;
+
+ ops = &basechain->ops;
+ ops->pf = family;
+ ops->owner = afi->owner;
+ ops->hooknum = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
+ ops->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
+ ops->priv = chain;
+ ops->hook = nft_do_chain;
+ if (afi->hooks[ops->hooknum])
+ ops->hook = afi->hooks[ops->hooknum];
+
+ chain->flags |= NFT_BASE_CHAIN;
+ } else {
+ chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+ if (chain == NULL)
+ return -ENOMEM;
+ }
+
+ INIT_LIST_HEAD(&chain->rules);
+ chain->handle = nf_tables_alloc_handle(table);
+ nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
+
+ list_add_tail(&chain->list, &table->chains);
+ table->use++;
+notify:
+ nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN,
+ family);
+ return 0;
+}
+
+static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
+{
+ struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
+
+ BUG_ON(chain->use > 0);
+
+ if (chain->flags & NFT_BASE_CHAIN)
+ kfree(nft_base_chain(chain));
+ else
+ kfree(chain);
+}
+
+static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nft_af_info *afi;
+ struct nft_table *table;
+ struct nft_chain *chain;
+ int family = nfmsg->nfgen_family;
+
+ afi = nf_tables_afinfo_lookup(family, false);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], false);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+
+ if (chain->flags & NFT_CHAIN_BUILTIN)
+ return -EOPNOTSUPP;
+
+ if (!list_empty(&chain->rules))
+ return -EBUSY;
+
+ list_del(&chain->list);
+ table->use--;
+
+ if (chain->flags & NFT_BASE_CHAIN)
+ nf_unregister_hook(&nft_base_chain(chain)->ops);
+
+ nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN,
+ family);
+
+ /* Make sure all rule references are gone before this is released */
+ call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy);
+ return 0;
+}
+
+static void nft_ctx_init(struct nft_ctx *ctx,
+ const struct nft_af_info *afi,
+ const struct nft_table *table,
+ const struct nft_chain *chain)
+{
+ ctx->afi = afi;
+ ctx->table = table;
+ ctx->chain = chain;
+}
+
+/*
+ * Expressions
+ */
+
+/**
+ * nft_register_expr - register nf_tables expr operations
+ * @ops: expr operations
+ *
+ * Registers the expr operations for use with nf_tables. Returns zero on
+ * success or a negative errno code otherwise.
+ */
+int nft_register_expr(struct nft_expr_ops *ops)
+{
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_add_tail(&ops->list, &nf_tables_expressions);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nft_register_expr);
+
+/**
+ * nft_unregister_expr - unregister nf_tables expr operations
+ * @ops: expr operations
+ *
+ * Unregisters the expr operations for use with nf_tables.
+ */
+void nft_unregister_expr(struct nft_expr_ops *ops)
+{
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_del(&ops->list);
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_expr);
+
+static const struct nft_expr_ops *__nft_expr_ops_get(struct nlattr *nla)
+{
+ const struct nft_expr_ops *ops;
+
+ list_for_each_entry(ops, &nf_tables_expressions, list) {
+ if (!nla_strcmp(nla, ops->name))
+ return ops;
+ }
+ return NULL;
+}
+
+static const struct nft_expr_ops *nft_expr_ops_get(struct nlattr *nla)
+{
+ const struct nft_expr_ops *ops;
+
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
+ ops = __nft_expr_ops_get(nla);
+ if (ops != NULL && try_module_get(ops->owner))
+ return ops;
+
+#ifdef CONFIG_MODULES
+ if (ops == NULL) {
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ request_module("nft-expr-%.*s",
+ nla_len(nla), (char *)nla_data(nla));
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ if (__nft_expr_ops_get(nla))
+ return ERR_PTR(-EAGAIN);
+ }
+#endif
+ return ERR_PTR(-ENOENT);
+}
+
+static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = {
+ [NFTA_EXPR_NAME] = { .type = NLA_STRING },
+ [NFTA_EXPR_DATA] = { .type = NLA_NESTED },
+};
+
+static int nf_tables_fill_expr_info(struct sk_buff *skb,
+ const struct nft_expr *expr)
+{
+ if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->name))
+ goto nla_put_failure;
+
+ if (expr->ops->dump) {
+ struct nlattr *data = nla_nest_start(skb, NFTA_EXPR_DATA);
+ if (data == NULL)
+ goto nla_put_failure;
+ if (expr->ops->dump(skb, expr) < 0)
+ goto nla_put_failure;
+ nla_nest_end(skb, data);
+ }
+
+ return skb->len;
+
+nla_put_failure:
+ return -1;
+};
+
+struct nft_expr_info {
+ const struct nft_expr_ops *ops;
+ struct nlattr *tb[NFTA_EXPR_MAX + 1];
+};
+
+static int nf_tables_expr_parse(const struct nlattr *nla,
+ struct nft_expr_info *info)
+{
+ const struct nft_expr_ops *ops;
+ int err;
+
+ err = nla_parse_nested(info->tb, NFTA_EXPR_MAX, nla, nft_expr_policy);
+ if (err < 0)
+ return err;
+
+ ops = nft_expr_ops_get(info->tb[NFTA_EXPR_NAME]);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+ info->ops = ops;
+ return 0;
+}
+
+static int nf_tables_newexpr(const struct nft_ctx *ctx,
+ struct nft_expr_info *info,
+ struct nft_expr *expr)
+{
+ const struct nft_expr_ops *ops = info->ops;
+ int err;
+
+ expr->ops = ops;
+ if (ops->init) {
+ struct nlattr *ma[ops->maxattr + 1];
+
+ if (info->tb[NFTA_EXPR_DATA]) {
+ err = nla_parse_nested(ma, ops->maxattr,
+ info->tb[NFTA_EXPR_DATA],
+ ops->policy);
+ if (err < 0)
+ goto err1;
+ } else
+ memset(ma, 0, sizeof(ma[0]) * (ops->maxattr + 1));
+
+ err = ops->init(ctx, expr, (const struct nlattr **)ma);
+ if (err < 0)
+ goto err1;
+ }
+
+ info->ops = NULL;
+ return 0;
+
+err1:
+ expr->ops = NULL;
+ return err;
+}
+
+static void nf_tables_expr_destroy(struct nft_expr *expr)
+{
+ if (expr->ops->destroy)
+ expr->ops->destroy(expr);
+ module_put(expr->ops->owner);
+}
+
+/*
+ * Rules
+ */
+
+static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain,
+ u64 handle)
+{
+ struct nft_rule *rule;
+
+ // FIXME: this sucks
+ list_for_each_entry(rule, &chain->rules, list) {
+ if (handle == rule->handle)
+ return rule;
+ }
+
+ return ERR_PTR(-ENOENT);
+}
+
+static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain,
+ const struct nlattr *nla)
+{
+ if (nla == NULL)
+ return ERR_PTR(-EINVAL);
+
+ return __nf_tables_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla)));
+}
+
+static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
+ [NFTA_RULE_TABLE] = { .type = NLA_STRING },
+ [NFTA_RULE_CHAIN] = { .type = NLA_STRING,
+ .len = NFT_CHAIN_MAXNAMELEN - 1 },
+ [NFTA_RULE_HANDLE] = { .type = NLA_U64 },
+ [NFTA_RULE_EXPRESSIONS] = { .type = NLA_NESTED },
+};
+
+static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
+ int event, u32 flags, int family,
+ const struct nft_table *table,
+ const struct nft_chain *chain,
+ const struct nft_rule *rule)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+ const struct nft_expr *expr, *next;
+ struct nlattr *list;
+
+ event |= NFNL_SUBSYS_NFTABLES << 8;
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+ flags);
+ if (nlh == NULL)
+ goto nla_put_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = family;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ if (nla_put_string(skb, NFTA_RULE_TABLE, table->name))
+ goto nla_put_failure;
+ if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name))
+ goto nla_put_failure;
+ if (nla_put_be64(skb, NFTA_RULE_HANDLE, cpu_to_be64(rule->handle)))
+ goto nla_put_failure;
+
+ list = nla_nest_start(skb, NFTA_RULE_EXPRESSIONS);
+ if (list == NULL)
+ goto nla_put_failure;
+ nft_rule_for_each_expr(expr, next, rule) {
+ struct nlattr *elem = nla_nest_start(skb, NFTA_LIST_ELEM);
+ if (elem == NULL)
+ goto nla_put_failure;
+ if (nf_tables_fill_expr_info(skb, expr) < 0)
+ goto nla_put_failure;
+ nla_nest_end(skb, elem);
+ }
+ nla_nest_end(skb, list);
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_trim(skb, nlh);
+ return -1;
+}
+
+static int nf_tables_rule_notify(const struct sk_buff *oskb,
+ const struct nlmsghdr *nlh,
+ const struct nft_table *table,
+ const struct nft_chain *chain,
+ const struct nft_rule *rule,
+ int event, u32 flags, int family)
+{
+ struct sk_buff *skb;
+ u32 portid = NETLINK_CB(oskb).portid;
+ struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
+ u32 seq = nlh->nlmsg_seq;
+ bool report;
+ int err;
+
+ report = nlmsg_report(nlh);
+ if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+ return 0;
+
+ err = -ENOBUFS;
+ skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (skb == NULL)
+ goto err;
+
+ err = nf_tables_fill_rule_info(skb, portid, seq, event, flags,
+ family, table, chain, rule);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto err;
+ }
+
+ err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+ GFP_KERNEL);
+err:
+ if (err < 0)
+ nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+ return err;
+}
+
+static int nf_tables_dump_rules(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ const struct nft_chain *chain;
+ const struct nft_rule *rule;
+ unsigned int idx = 0, s_idx = cb->args[0];
+ int family = nfmsg->nfgen_family;
+
+ list_for_each_entry(afi, &nf_tables_afinfo, list) {
+ if (family != NFPROTO_UNSPEC && family != afi->family)
+ continue;
+
+ list_for_each_entry(table, &afi->tables, list) {
+ list_for_each_entry(chain, &table->chains, list) {
+ list_for_each_entry(rule, &chain->rules, list) {
+ if (idx < s_idx)
+ goto cont;
+ if (idx > s_idx)
+ memset(&cb->args[1], 0,
+ sizeof(cb->args) - sizeof(cb->args[0]));
+ if (nf_tables_fill_rule_info(skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWRULE,
+ NLM_F_MULTI | NLM_F_APPEND,
+ afi->family, table, chain, rule) < 0)
+ goto done;
+cont:
+ idx++;
+ }
+ }
+ }
+ }
+done:
+ cb->args[0] = idx;
+ return skb->len;
+}
+
+static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ const struct nft_chain *chain;
+ const struct nft_rule *rule;
+ struct sk_buff *skb2;
+ int family = nfmsg->nfgen_family;
+ int err;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .dump = nf_tables_dump_rules,
+ };
+ return netlink_dump_start(nlsk, skb, nlh, &c);
+ }
+
+ afi = nf_tables_afinfo_lookup(family, false);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], false);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+
+ rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
+ if (IS_ERR(rule))
+ return PTR_ERR(rule);
+
+ skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb2)
+ return -ENOMEM;
+
+ err = nf_tables_fill_rule_info(skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0,
+ family, table, chain, rule);
+ if (err < 0)
+ goto err;
+
+ return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+ kfree_skb(skb2);
+ return err;
+}
+
+static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
+{
+ struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head);
+ struct nft_expr *expr;
+
+ /*
+ * Careful: some expressions might not be initialized in case this
+ * is called on error from nf_tables_newrule().
+ */
+ expr = nft_expr_first(rule);
+ while (expr->ops && expr != nft_expr_last(rule)) {
+ nf_tables_expr_destroy(expr);
+ expr = nft_expr_next(expr);
+ }
+ kfree(rule);
+}
+
+static void nf_tables_rule_destroy(struct nft_rule *rule)
+{
+ call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy);
+}
+
+#define NFT_RULE_MAXEXPRS 128
+
+static struct nft_expr_info *info;
+
+static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nft_af_info *afi;
+ struct nft_table *table;
+ struct nft_chain *chain;
+ struct nft_rule *rule, *old_rule = NULL;
+ struct nft_expr *expr;
+ struct nft_ctx ctx;
+ struct nlattr *tmp;
+ unsigned int size, i, n;
+ int err, rem;
+ bool create;
+ u64 handle;
+
+ create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
+
+ afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, create);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], create);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+
+ if (nla[NFTA_RULE_HANDLE]) {
+ handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE]));
+ rule = __nf_tables_rule_lookup(chain, handle);
+ if (IS_ERR(rule))
+ return PTR_ERR(rule);
+
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+ if (nlh->nlmsg_flags & NLM_F_REPLACE)
+ old_rule = rule;
+ else
+ return -EOPNOTSUPP;
+ } else {
+ if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
+ return -EINVAL;
+ handle = nf_tables_alloc_handle(table);
+ }
+
+ n = 0;
+ size = 0;
+ if (nla[NFTA_RULE_EXPRESSIONS]) {
+ nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) {
+ err = -EINVAL;
+ if (nla_type(tmp) != NFTA_LIST_ELEM)
+ goto err1;
+ if (n == NFT_RULE_MAXEXPRS)
+ goto err1;
+ err = nf_tables_expr_parse(tmp, &info[n]);
+ if (err < 0)
+ goto err1;
+ size += info[n].ops->size;
+ n++;
+ }
+ }
+
+ err = -ENOMEM;
+ rule = kzalloc(sizeof(*rule) + size, GFP_KERNEL);
+ if (rule == NULL)
+ goto err1;
+
+ rule->handle = handle;
+ rule->dlen = size;
+
+ nft_ctx_init(&ctx, afi, table, chain);
+ expr = nft_expr_first(rule);
+ for (i = 0; i < n; i++) {
+ err = nf_tables_newexpr(&ctx, &info[i], expr);
+ if (err < 0)
+ goto err2;
+ expr = nft_expr_next(expr);
+ }
+
+ /* Register hook when first rule is inserted into a base chain */
+ if (list_empty(&chain->rules) && chain->flags & NFT_BASE_CHAIN) {
+ err = nf_register_hook(&nft_base_chain(chain)->ops);
+ if (err < 0)
+ goto err2;
+ }
+
+ if (nlh->nlmsg_flags & NLM_F_REPLACE) {
+ list_replace_rcu(&old_rule->list, &rule->list);
+ nf_tables_rule_destroy(old_rule);
+ } else if (nlh->nlmsg_flags & NLM_F_APPEND)
+ list_add_tail_rcu(&rule->list, &chain->rules);
+ else
+ list_add_rcu(&rule->list, &chain->rules);
+
+ nf_tables_rule_notify(skb, nlh, table, chain, rule, NFT_MSG_NEWRULE,
+ nlh->nlmsg_flags & (NLM_F_APPEND | NLM_F_REPLACE),
+ nfmsg->nfgen_family);
+ return 0;
+
+err2:
+ nf_tables_rule_destroy(rule);
+err1:
+ for (i = 0; i < n; i++) {
+ if (info[i].ops != NULL)
+ module_put(info[i].ops->owner);
+ }
+ return err;
+}
+
+static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const nla[])
+{
+ const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+ const struct nft_af_info *afi;
+ const struct nft_table *table;
+ struct nft_chain *chain;
+ struct nft_rule *rule, *tmp;
+ int family = nfmsg->nfgen_family;
+
+ afi = nf_tables_afinfo_lookup(family, false);
+ if (IS_ERR(afi))
+ return PTR_ERR(afi);
+
+ table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], false);
+ if (IS_ERR(table))
+ return PTR_ERR(table);
+
+ chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+
+ if (nla[NFTA_RULE_HANDLE]) {
+ rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
+ if (IS_ERR(rule))
+ return PTR_ERR(rule);
+
+ /* List removal must be visible before destroying expressions */
+ list_del_rcu(&rule->list);
+
+ nf_tables_rule_notify(skb, nlh, table, chain, rule,
+ NFT_MSG_DELRULE, 0, family);
+ nf_tables_rule_destroy(rule);
+ } else {
+ /* Remove all rules in this chain */
+ list_for_each_entry_safe(rule, tmp, &chain->rules, list) {
+ list_del_rcu(&rule->list);
+
+ nf_tables_rule_notify(skb, nlh, table, chain, rule,
+ NFT_MSG_DELRULE, 0, family);
+ nf_tables_rule_destroy(rule);
+ }
+ }
+
+ /* Unregister hook when last rule from base chain is deleted */
+ if (list_empty(&chain->rules) && chain->flags & NFT_BASE_CHAIN)
+ nf_unregister_hook(&nft_base_chain(chain)->ops);
+
+ return 0;
+}
+
+static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
+ [NFT_MSG_NEWTABLE] = {
+ .call = nf_tables_newtable,
+ .attr_count = NFTA_TABLE_MAX,
+ .policy = nft_table_policy,
+ },
+ [NFT_MSG_GETTABLE] = {
+ .call = nf_tables_gettable,
+ .attr_count = NFTA_TABLE_MAX,
+ .policy = nft_table_policy,
+ },
+ [NFT_MSG_DELTABLE] = {
+ .call = nf_tables_deltable,
+ .attr_count = NFTA_TABLE_MAX,
+ .policy = nft_table_policy,
+ },
+ [NFT_MSG_NEWCHAIN] = {
+ .call = nf_tables_newchain,
+ .attr_count = NFTA_CHAIN_MAX,
+ .policy = nft_chain_policy,
+ },
+ [NFT_MSG_GETCHAIN] = {
+ .call = nf_tables_getchain,
+ .attr_count = NFTA_CHAIN_MAX,
+ .policy = nft_chain_policy,
+ },
+ [NFT_MSG_DELCHAIN] = {
+ .call = nf_tables_delchain,
+ .attr_count = NFTA_CHAIN_MAX,
+ .policy = nft_chain_policy,
+ },
+ [NFT_MSG_NEWRULE] = {
+ .call = nf_tables_newrule,
+ .attr_count = NFTA_RULE_MAX,
+ .policy = nft_rule_policy,
+ },
+ [NFT_MSG_GETRULE] = {
+ .call = nf_tables_getrule,
+ .attr_count = NFTA_RULE_MAX,
+ .policy = nft_rule_policy,
+ },
+ [NFT_MSG_DELRULE] = {
+ .call = nf_tables_delrule,
+ .attr_count = NFTA_RULE_MAX,
+ .policy = nft_rule_policy,
+ },
+};
+
+static const struct nfnetlink_subsystem nf_tables_subsys = {
+ .name = "nf_tables",
+ .subsys_id = NFNL_SUBSYS_NFTABLES,
+ .cb_count = NFT_MSG_MAX,
+ .cb = nf_tables_cb,
+};
+
+/**
+ * nft_validate_input_register - validate an expressions' input register
+ *
+ * @reg: the register number
+ *
+ * Validate that the input register is one of the general purpose
+ * registers.
+ */
+int nft_validate_input_register(enum nft_registers reg)
+{
+ if (reg <= NFT_REG_VERDICT)
+ return -EINVAL;
+ if (reg > NFT_REG_MAX)
+ return -ERANGE;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nft_validate_input_register);
+
+/**
+ * nft_validate_output_register - validate an expressions' output register
+ *
+ * @reg: the register number
+ *
+ * Validate that the output register is one of the general purpose
+ * registers or the verdict register.
+ */
+int nft_validate_output_register(enum nft_registers reg)
+{
+ if (reg < NFT_REG_VERDICT)
+ return -EINVAL;
+ if (reg > NFT_REG_MAX)
+ return -ERANGE;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nft_validate_output_register);
+
+/**
+ * nft_validate_data_load - validate an expressions' data load
+ *
+ * @ctx: context of the expression performing the load
+ * @reg: the destination register number
+ * @data: the data to load
+ * @type: the data type
+ *
+ * Validate that a data load uses the appropriate data type for
+ * the destination register. A value of NULL for the data means
+ * that its runtime gathered data, which is always of type
+ * NFT_DATA_VALUE.
+ */
+int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg,
+ const struct nft_data *data,
+ enum nft_data_types type)
+{
+ switch (reg) {
+ case NFT_REG_VERDICT:
+ if (data == NULL || type != NFT_DATA_VERDICT)
+ return -EINVAL;
+ // FIXME: do loop detection
+ return 0;
+ default:
+ if (data != NULL && type != NFT_DATA_VALUE)
+ return -EINVAL;
+ return 0;
+ }
+}
+EXPORT_SYMBOL_GPL(nft_validate_data_load);
+
+static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = {
+ [NFTA_VERDICT_CODE] = { .type = NLA_U32 },
+ [NFTA_VERDICT_CHAIN] = { .type = NLA_STRING,
+ .len = NFT_CHAIN_MAXNAMELEN - 1 },
+};
+
+static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
+ struct nft_data_desc *desc, const struct nlattr *nla)
+{
+ struct nlattr *tb[NFTA_VERDICT_MAX + 1];
+ struct nft_chain *chain;
+ int err;
+
+ err = nla_parse_nested(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFTA_VERDICT_CODE])
+ return -EINVAL;
+ data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
+
+ switch (data->verdict) {
+ case NF_ACCEPT:
+ case NF_DROP:
+ case NF_QUEUE:
+ case NFT_CONTINUE:
+ case NFT_BREAK:
+ case NFT_RETURN:
+ desc->len = sizeof(data->verdict);
+ break;
+ case NFT_JUMP:
+ case NFT_GOTO:
+ if (!tb[NFTA_VERDICT_CHAIN])
+ return -EINVAL;
+ chain = nf_tables_chain_lookup(ctx->table,
+ tb[NFTA_VERDICT_CHAIN]);
+ if (IS_ERR(chain))
+ return PTR_ERR(chain);
+ if (chain->flags & NFT_BASE_CHAIN)
+ return -EOPNOTSUPP;
+
+ if (ctx->chain->level + 1 > chain->level) {
+ if (ctx->chain->level + 1 == 16)
+ return -EMLINK;
+ chain->level = ctx->chain->level + 1;
+ }
+ chain->use++;
+ data->chain = chain;
+ desc->len = sizeof(data);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ desc->type = NFT_DATA_VERDICT;
+ return 0;
+}
+
+static void nft_verdict_uninit(const struct nft_data *data)
+{
+ switch (data->verdict) {
+ case NFT_JUMP:
+ case NFT_GOTO:
+ data->chain->use--;
+ break;
+ }
+}
+
+static int nft_verdict_dump(struct sk_buff *skb, const struct nft_data *data)
+{
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, NFTA_DATA_VERDICT);
+ if (!nest)
+ goto nla_put_failure;
+
+ if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict)))
+ goto nla_put_failure;
+
+ switch (data->verdict) {
+ case NFT_JUMP:
+ case NFT_GOTO:
+ if (nla_put_string(skb, NFTA_VERDICT_CHAIN, data->chain->name))
+ goto nla_put_failure;
+ }
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data,
+ struct nft_data_desc *desc, const struct nlattr *nla)
+{
+ unsigned int len;
+
+ len = nla_len(nla);
+ if (len == 0)
+ return -EINVAL;
+ if (len > sizeof(data->data))
+ return -EOVERFLOW;
+
+ nla_memcpy(data->data, nla, sizeof(data->data));
+ desc->type = NFT_DATA_VALUE;
+ desc->len = len;
+ return 0;
+}
+
+static int nft_value_dump(struct sk_buff *skb, const struct nft_data *data,
+ unsigned int len)
+{
+ return nla_put(skb, NFTA_DATA_VALUE, len, data->data);
+}
+
+static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
+ [NFTA_DATA_VALUE] = { .type = NLA_BINARY,
+ .len = FIELD_SIZEOF(struct nft_data, data) },
+ [NFTA_DATA_VERDICT] = { .type = NLA_NESTED },
+};
+
+/**
+ * nft_data_init - parse nf_tables data netlink attributes
+ *
+ * @ctx: context of the expression using the data
+ * @data: destination struct nft_data
+ * @desc: data description
+ * @nla: netlink attribute containing data
+ *
+ * Parse the netlink data attributes and initialize a struct nft_data.
+ * The type and length of data are returned in the data description.
+ *
+ * The caller can indicate that it only wants to accept data of type
+ * NFT_DATA_VALUE by passing NULL for the ctx argument.
+ */
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
+ struct nft_data_desc *desc, const struct nlattr *nla)
+{
+ struct nlattr *tb[NFTA_DATA_MAX + 1];
+ int err;
+
+ err = nla_parse_nested(tb, NFTA_DATA_MAX, nla, nft_data_policy);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_DATA_VALUE])
+ return nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]);
+ if (tb[NFTA_DATA_VERDICT] && ctx != NULL)
+ return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
+ return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(nft_data_init);
+
+/**
+ * nft_data_uninit - release a nft_data item
+ *
+ * @data: struct nft_data to release
+ * @type: type of data
+ *
+ * Release a nft_data item. NFT_DATA_VALUE types can be silently discarded,
+ * all others need to be released by calling this function.
+ */
+void nft_data_uninit(const struct nft_data *data, enum nft_data_types type)
+{
+ switch (type) {
+ case NFT_DATA_VALUE:
+ return;
+ case NFT_DATA_VERDICT:
+ return nft_verdict_uninit(data);
+ default:
+ WARN_ON(1);
+ }
+}
+EXPORT_SYMBOL_GPL(nft_data_uninit);
+
+int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
+ enum nft_data_types type, unsigned int len)
+{
+ struct nlattr *nest;
+ int err;
+
+ nest = nla_nest_start(skb, attr);
+ if (nest == NULL)
+ return -1;
+
+ switch (type) {
+ case NFT_DATA_VALUE:
+ err = nft_value_dump(skb, data, len);
+ break;
+ case NFT_DATA_VERDICT:
+ err = nft_verdict_dump(skb, data);
+ break;
+ default:
+ err = -EINVAL;
+ WARN_ON(1);
+ }
+
+ nla_nest_end(skb, nest);
+ return err;
+}
+EXPORT_SYMBOL_GPL(nft_data_dump);
+
+static int __init nf_tables_module_init(void)
+{
+ int err;
+
+ info = kmalloc(sizeof(struct nft_expr_info) * NFT_RULE_MAXEXPRS,
+ GFP_KERNEL);
+ if (info == NULL) {
+ err = -ENOMEM;
+ goto err1;
+ }
+
+ err = nf_tables_core_module_init();
+ if (err < 0)
+ goto err2;
+
+ err = nfnetlink_subsys_register(&nf_tables_subsys);
+ if (err < 0)
+ goto err3;
+
+ pr_info("nf_tables: (c) 2007-2009 Patrick McHardy <kaber@trash.net>\n");
+ return 0;
+err3:
+ nf_tables_core_module_exit();
+err2:
+ kfree(info);
+err1:
+ return err;
+}
+
+static void __exit nf_tables_module_exit(void)
+{
+ nfnetlink_subsys_unregister(&nf_tables_subsys);
+ nf_tables_core_module_exit();
+ kfree(info);
+}
+
+module_init(nf_tables_module_init);
+module_exit(nf_tables_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFTABLES);
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
new file mode 100644
index 000000000000..bc7fb85d4002
--- /dev/null
+++ b/net/netfilter/nf_tables_core.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (c) 2008 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/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+#define NFT_JUMP_STACK_SIZE 16
+
+unsigned int nft_do_chain(const struct nf_hook_ops *ops,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ const struct nft_chain *chain = ops->priv;
+ const struct nft_rule *rule;
+ const struct nft_expr *expr, *last;
+ struct nft_data data[NFT_REG_MAX + 1];
+ const struct nft_pktinfo pkt = {
+ .skb = skb,
+ .in = in,
+ .out = out,
+ .hooknum = ops->hooknum,
+ };
+ unsigned int stackptr = 0;
+ struct {
+ const struct nft_chain *chain;
+ const struct nft_rule *rule;
+ } jumpstack[NFT_JUMP_STACK_SIZE];
+
+do_chain:
+ rule = list_entry(&chain->rules, struct nft_rule, list);
+next_rule:
+ data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+ list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
+ nft_rule_for_each_expr(expr, last, rule) {
+ expr->ops->eval(expr, data, &pkt);
+ if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE)
+ break;
+ }
+
+ switch (data[NFT_REG_VERDICT].verdict) {
+ case NFT_BREAK:
+ data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+ /* fall through */
+ case NFT_CONTINUE:
+ continue;
+ }
+ break;
+ }
+
+ switch (data[NFT_REG_VERDICT].verdict) {
+ case NF_ACCEPT:
+ case NF_DROP:
+ case NF_QUEUE:
+ return data[NFT_REG_VERDICT].verdict;
+ case NFT_JUMP:
+ BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE);
+ jumpstack[stackptr].chain = chain;
+ jumpstack[stackptr].rule = rule;
+ stackptr++;
+ /* fall through */
+ case NFT_GOTO:
+ chain = data[NFT_REG_VERDICT].chain;
+ goto do_chain;
+ case NFT_RETURN:
+ case NFT_CONTINUE:
+ break;
+ default:
+ WARN_ON(1);
+ }
+
+ if (stackptr > 0) {
+ stackptr--;
+ chain = jumpstack[stackptr].chain;
+ rule = jumpstack[stackptr].rule;
+ goto next_rule;
+ }
+
+ return NF_ACCEPT;
+}
+EXPORT_SYMBOL_GPL(nft_do_chain);
+
+int __init nf_tables_core_module_init(void)
+{
+ int err;
+
+ err = nft_immediate_module_init();
+ if (err < 0)
+ goto err1;
+
+ err = nft_cmp_module_init();
+ if (err < 0)
+ goto err2;
+
+ err = nft_lookup_module_init();
+ if (err < 0)
+ goto err3;
+
+ err = nft_bitwise_module_init();
+ if (err < 0)
+ goto err4;
+
+ err = nft_byteorder_module_init();
+ if (err < 0)
+ goto err5;
+
+ err = nft_payload_module_init();
+ if (err < 0)
+ goto err6;
+
+ return 0;
+
+err6:
+ nft_byteorder_module_exit();
+err5:
+ nft_bitwise_module_exit();
+err4:
+ nft_lookup_module_exit();
+err3:
+ nft_cmp_module_exit();
+err2:
+ nft_immediate_module_exit();
+err1:
+ return err;
+}
+
+void nf_tables_core_module_exit(void)
+{
+ nft_payload_module_exit();
+ nft_byteorder_module_exit();
+ nft_bitwise_module_exit();
+ nft_lookup_module_exit();
+ nft_cmp_module_exit();
+ nft_immediate_module_exit();
+}
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
new file mode 100644
index 000000000000..0f7501506367
--- /dev/null
+++ b/net/netfilter/nft_bitwise.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_bitwise {
+ enum nft_registers sreg:8;
+ enum nft_registers dreg:8;
+ u8 len;
+ struct nft_data mask;
+ struct nft_data xor;
+};
+
+static void nft_bitwise_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_bitwise *priv = nft_expr_priv(expr);
+ const struct nft_data *src = &data[priv->sreg];
+ struct nft_data *dst = &data[priv->dreg];
+ unsigned int i;
+
+ for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) {
+ dst->data[i] = (src->data[i] & priv->mask.data[i]) ^
+ priv->xor.data[i];
+ }
+}
+
+static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
+ [NFTA_BITWISE_SREG] = { .type = NLA_U32 },
+ [NFTA_BITWISE_DREG] = { .type = NLA_U32 },
+ [NFTA_BITWISE_LEN] = { .type = NLA_U32 },
+ [NFTA_BITWISE_MASK] = { .type = NLA_NESTED },
+ [NFTA_BITWISE_XOR] = { .type = NLA_NESTED },
+};
+
+static int nft_bitwise_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_bitwise *priv = nft_expr_priv(expr);
+ struct nft_data_desc d1, d2;
+ int err;
+
+ if (tb[NFTA_BITWISE_SREG] == NULL ||
+ tb[NFTA_BITWISE_DREG] == NULL ||
+ tb[NFTA_BITWISE_LEN] == NULL ||
+ tb[NFTA_BITWISE_MASK] == NULL ||
+ tb[NFTA_BITWISE_XOR] == NULL)
+ return -EINVAL;
+
+ priv->sreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_SREG]));
+ err = nft_validate_input_register(priv->sreg);
+ if (err < 0)
+ return err;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+ err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+ if (err < 0)
+ return err;
+
+ priv->len = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN]));
+
+ err = nft_data_init(NULL, &priv->mask, &d1, tb[NFTA_BITWISE_MASK]);
+ if (err < 0)
+ return err;
+ if (d1.len != priv->len)
+ return -EINVAL;
+
+ err = nft_data_init(NULL, &priv->xor, &d2, tb[NFTA_BITWISE_XOR]);
+ if (err < 0)
+ return err;
+ if (d2.len != priv->len)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_bitwise *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_BITWISE_SREG, htonl(priv->sreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_BITWISE_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len)))
+ goto nla_put_failure;
+
+ if (nft_data_dump(skb, NFTA_BITWISE_MASK, &priv->mask,
+ NFT_DATA_VALUE, priv->len) < 0)
+ goto nla_put_failure;
+
+ if (nft_data_dump(skb, NFTA_BITWISE_XOR, &priv->xor,
+ NFT_DATA_VALUE, priv->len) < 0)
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_bitwise_ops __read_mostly = {
+ .name = "bitwise",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_bitwise)),
+ .owner = THIS_MODULE,
+ .eval = nft_bitwise_eval,
+ .init = nft_bitwise_init,
+ .dump = nft_bitwise_dump,
+ .policy = nft_bitwise_policy,
+ .maxattr = NFTA_BITWISE_MAX,
+};
+
+int __init nft_bitwise_module_init(void)
+{
+ return nft_register_expr(&nft_bitwise_ops);
+}
+
+void nft_bitwise_module_exit(void)
+{
+ nft_unregister_expr(&nft_bitwise_ops);
+}
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
new file mode 100644
index 000000000000..8b0657a4d17b
--- /dev/null
+++ b/net/netfilter/nft_byteorder.c
@@ -0,0 +1,167 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_byteorder {
+ enum nft_registers sreg:8;
+ enum nft_registers dreg:8;
+ enum nft_byteorder_ops op:8;
+ u8 len;
+ u8 size;
+};
+
+static void nft_byteorder_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_byteorder *priv = nft_expr_priv(expr);
+ struct nft_data *src = &data[priv->sreg], *dst = &data[priv->dreg];
+ union { u32 u32; u16 u16; } *s, *d;
+ unsigned int i;
+
+ s = (void *)src->data;
+ d = (void *)dst->data;
+
+ switch (priv->size) {
+ case 4:
+ switch (priv->op) {
+ case NFT_BYTEORDER_NTOH:
+ for (i = 0; i < priv->len / 4; i++)
+ d[i].u32 = ntohl((__force __be32)s[i].u32);
+ break;
+ case NFT_BYTEORDER_HTON:
+ for (i = 0; i < priv->len / 4; i++)
+ d[i].u32 = (__force __u32)htonl(s[i].u32);
+ break;
+ }
+ break;
+ case 2:
+ switch (priv->op) {
+ case NFT_BYTEORDER_NTOH:
+ for (i = 0; i < priv->len / 2; i++)
+ d[i].u16 = ntohs((__force __be16)s[i].u16);
+ break;
+ case NFT_BYTEORDER_HTON:
+ for (i = 0; i < priv->len / 2; i++)
+ d[i].u16 = (__force __u16)htons(s[i].u16);
+ break;
+ }
+ break;
+ }
+}
+
+static const struct nla_policy nft_byteorder_policy[NFTA_BYTEORDER_MAX + 1] = {
+ [NFTA_BYTEORDER_SREG] = { .type = NLA_U32 },
+ [NFTA_BYTEORDER_DREG] = { .type = NLA_U32 },
+ [NFTA_BYTEORDER_OP] = { .type = NLA_U32 },
+ [NFTA_BYTEORDER_LEN] = { .type = NLA_U32 },
+ [NFTA_BYTEORDER_SIZE] = { .type = NLA_U32 },
+};
+
+static int nft_byteorder_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_byteorder *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_BYTEORDER_SREG] == NULL ||
+ tb[NFTA_BYTEORDER_DREG] == NULL ||
+ tb[NFTA_BYTEORDER_LEN] == NULL ||
+ tb[NFTA_BYTEORDER_SIZE] == NULL ||
+ tb[NFTA_BYTEORDER_OP] == NULL)
+ return -EINVAL;
+
+ priv->sreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SREG]));
+ err = nft_validate_input_register(priv->sreg);
+ if (err < 0)
+ return err;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+ err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+ if (err < 0)
+ return err;
+
+ priv->op = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_OP]));
+ switch (priv->op) {
+ case NFT_BYTEORDER_NTOH:
+ case NFT_BYTEORDER_HTON:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ priv->len = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN]));
+ if (priv->len == 0 || priv->len > FIELD_SIZEOF(struct nft_data, data))
+ return -EINVAL;
+
+ priv->size = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SIZE]));
+ switch (priv->size) {
+ case 2:
+ case 4:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_byteorder *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_BYTEORDER_SREG, htonl(priv->sreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_BYTEORDER_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_BYTEORDER_OP, htonl(priv->op)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_BYTEORDER_LEN, htonl(priv->len)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_BYTEORDER_SIZE, htonl(priv->size)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_byteorder_ops __read_mostly = {
+ .name = "byteorder",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
+ .owner = THIS_MODULE,
+ .eval = nft_byteorder_eval,
+ .init = nft_byteorder_init,
+ .dump = nft_byteorder_dump,
+ .policy = nft_byteorder_policy,
+ .maxattr = NFTA_BYTEORDER_MAX,
+};
+
+int __init nft_byteorder_module_init(void)
+{
+ return nft_register_expr(&nft_byteorder_ops);
+}
+
+void nft_byteorder_module_exit(void)
+{
+ nft_unregister_expr(&nft_byteorder_ops);
+}
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
new file mode 100644
index 000000000000..e734d670120a
--- /dev/null
+++ b/net/netfilter/nft_cmp.c
@@ -0,0 +1,146 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_cmp_expr {
+ struct nft_data data;
+ enum nft_registers sreg:8;
+ u8 len;
+ enum nft_cmp_ops op:8;
+};
+
+static void nft_cmp_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+ int d;
+
+ d = nft_data_cmp(&data[priv->sreg], &priv->data, priv->len);
+ switch (priv->op) {
+ case NFT_CMP_EQ:
+ if (d != 0)
+ goto mismatch;
+ break;
+ case NFT_CMP_NEQ:
+ if (d == 0)
+ goto mismatch;
+ break;
+ case NFT_CMP_LT:
+ if (d == 0)
+ goto mismatch;
+ case NFT_CMP_LTE:
+ if (d > 0)
+ goto mismatch;
+ break;
+ case NFT_CMP_GT:
+ if (d == 0)
+ goto mismatch;
+ case NFT_CMP_GTE:
+ if (d < 0)
+ goto mismatch;
+ break;
+ }
+ return;
+
+mismatch:
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_cmp_policy[NFTA_CMP_MAX + 1] = {
+ [NFTA_CMP_SREG] = { .type = NLA_U32 },
+ [NFTA_CMP_OP] = { .type = NLA_U32 },
+ [NFTA_CMP_DATA] = { .type = NLA_NESTED },
+};
+
+static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_cmp_expr *priv = nft_expr_priv(expr);
+ struct nft_data_desc desc;
+ int err;
+
+ if (tb[NFTA_CMP_SREG] == NULL ||
+ tb[NFTA_CMP_OP] == NULL ||
+ tb[NFTA_CMP_DATA] == NULL)
+ return -EINVAL;
+
+ priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
+ err = nft_validate_input_register(priv->sreg);
+ if (err < 0)
+ return err;
+
+ priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
+ switch (priv->op) {
+ case NFT_CMP_EQ:
+ case NFT_CMP_NEQ:
+ case NFT_CMP_LT:
+ case NFT_CMP_LTE:
+ case NFT_CMP_GT:
+ case NFT_CMP_GTE:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
+ if (err < 0)
+ return err;
+
+ priv->len = desc.len;
+ return 0;
+}
+
+static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_CMP_OP, htonl(priv->op)))
+ goto nla_put_failure;
+
+ if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data,
+ NFT_DATA_VALUE, priv->len) < 0)
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_cmp_ops __read_mostly = {
+ .name = "cmp",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_cmp_expr)),
+ .owner = THIS_MODULE,
+ .eval = nft_cmp_eval,
+ .init = nft_cmp_init,
+ .dump = nft_cmp_dump,
+ .policy = nft_cmp_policy,
+ .maxattr = NFTA_CMP_MAX,
+};
+
+int __init nft_cmp_module_init(void)
+{
+ return nft_register_expr(&nft_cmp_ops);
+}
+
+void nft_cmp_module_exit(void)
+{
+ nft_unregister_expr(&nft_cmp_ops);
+}
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
new file mode 100644
index 000000000000..33c5d36819bb
--- /dev/null
+++ b/net/netfilter/nft_counter.c
@@ -0,0 +1,107 @@
+/*
+ * Copyright (c) 2008 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/seqlock.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_counter {
+ seqlock_t lock;
+ u64 bytes;
+ u64 packets;
+};
+
+static void nft_counter_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_counter *priv = nft_expr_priv(expr);
+
+ write_seqlock_bh(&priv->lock);
+ priv->bytes += pkt->skb->len;
+ priv->packets++;
+ write_sequnlock_bh(&priv->lock);
+}
+
+static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ struct nft_counter *priv = nft_expr_priv(expr);
+ unsigned int seq;
+ u64 bytes;
+ u64 packets;
+
+ do {
+ seq = read_seqbegin(&priv->lock);
+ bytes = priv->bytes;
+ packets = priv->packets;
+ } while (read_seqretry(&priv->lock, seq));
+
+ if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(bytes)))
+ goto nla_put_failure;
+ if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(packets)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = {
+ [NFTA_COUNTER_PACKETS] = { .type = NLA_U64 },
+ [NFTA_COUNTER_BYTES] = { .type = NLA_U64 },
+};
+
+static int nft_counter_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_counter *priv = nft_expr_priv(expr);
+
+ if (tb[NFTA_COUNTER_PACKETS])
+ priv->packets = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+ if (tb[NFTA_COUNTER_BYTES])
+ priv->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
+
+ seqlock_init(&priv->lock);
+ return 0;
+}
+
+static struct nft_expr_ops nft_counter_ops __read_mostly = {
+ .name = "counter",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_counter)),
+ .policy = nft_counter_policy,
+ .maxattr = NFTA_COUNTER_MAX,
+ .owner = THIS_MODULE,
+ .eval = nft_counter_eval,
+ .init = nft_counter_init,
+ .dump = nft_counter_dump,
+};
+
+static int __init nft_counter_module_init(void)
+{
+ return nft_register_expr(&nft_counter_ops);
+}
+
+static void __exit nft_counter_module_exit(void)
+{
+ nft_unregister_expr(&nft_counter_ops);
+}
+
+module_init(nft_counter_module_init);
+module_exit(nft_counter_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("counter");
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
new file mode 100644
index 000000000000..a1756d678226
--- /dev/null
+++ b/net/netfilter/nft_ct.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+
+struct nft_ct {
+ enum nft_ct_keys key:8;
+ enum ip_conntrack_dir dir:8;
+ enum nft_registers dreg:8;
+ uint8_t family;
+};
+
+static void nft_ct_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_ct *priv = nft_expr_priv(expr);
+ struct nft_data *dest = &data[priv->dreg];
+ enum ip_conntrack_info ctinfo;
+ const struct nf_conn *ct;
+ const struct nf_conn_help *help;
+ const struct nf_conntrack_tuple *tuple;
+ const struct nf_conntrack_helper *helper;
+ long diff;
+ unsigned int state;
+
+ ct = nf_ct_get(pkt->skb, &ctinfo);
+
+ switch (priv->key) {
+ case NFT_CT_STATE:
+ if (ct == NULL)
+ state = NF_CT_STATE_INVALID_BIT;
+ else if (nf_ct_is_untracked(ct))
+ state = NF_CT_STATE_UNTRACKED_BIT;
+ else
+ state = NF_CT_STATE_BIT(ctinfo);
+ dest->data[0] = state;
+ return;
+ }
+
+ if (ct == NULL)
+ goto err;
+
+ switch (priv->key) {
+ case NFT_CT_DIRECTION:
+ dest->data[0] = CTINFO2DIR(ctinfo);
+ return;
+ case NFT_CT_STATUS:
+ dest->data[0] = ct->status;
+ return;
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ case NFT_CT_MARK:
+ dest->data[0] = ct->mark;
+ return;
+#endif
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+ case NFT_CT_SECMARK:
+ dest->data[0] = ct->secmark;
+ return;
+#endif
+ case NFT_CT_EXPIRATION:
+ diff = (long)jiffies - (long)ct->timeout.expires;
+ if (diff < 0)
+ diff = 0;
+ dest->data[0] = jiffies_to_msecs(diff);
+ return;
+ case NFT_CT_HELPER:
+ if (ct->master == NULL)
+ goto err;
+ help = nfct_help(ct->master);
+ if (help == NULL)
+ goto err;
+ helper = rcu_dereference(help->helper);
+ if (helper == NULL)
+ goto err;
+ if (strlen(helper->name) >= sizeof(dest->data))
+ goto err;
+ strncpy((char *)dest->data, helper->name, sizeof(dest->data));
+ return;
+ }
+
+ tuple = &ct->tuplehash[priv->dir].tuple;
+ switch (priv->key) {
+ case NFT_CT_L3PROTOCOL:
+ dest->data[0] = nf_ct_l3num(ct);
+ return;
+ case NFT_CT_SRC:
+ memcpy(dest->data, tuple->src.u3.all,
+ nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
+ return;
+ case NFT_CT_DST:
+ memcpy(dest->data, tuple->dst.u3.all,
+ nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
+ return;
+ case NFT_CT_PROTOCOL:
+ dest->data[0] = nf_ct_protonum(ct);
+ return;
+ case NFT_CT_PROTO_SRC:
+ dest->data[0] = (__force __u16)tuple->src.u.all;
+ return;
+ case NFT_CT_PROTO_DST:
+ dest->data[0] = (__force __u16)tuple->dst.u.all;
+ return;
+ }
+ return;
+err:
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = {
+ [NFTA_CT_DREG] = { .type = NLA_U32 },
+ [NFTA_CT_KEY] = { .type = NLA_U32 },
+ [NFTA_CT_DIRECTION] = { .type = NLA_U8 },
+};
+
+static int nft_ct_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_ct *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_CT_DREG] == NULL ||
+ tb[NFTA_CT_KEY] == NULL)
+ return -EINVAL;
+
+ priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
+ if (tb[NFTA_CT_DIRECTION] != NULL) {
+ priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
+ switch (priv->dir) {
+ case IP_CT_DIR_ORIGINAL:
+ case IP_CT_DIR_REPLY:
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ switch (priv->key) {
+ case NFT_CT_STATE:
+ case NFT_CT_DIRECTION:
+ case NFT_CT_STATUS:
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ case NFT_CT_MARK:
+#endif
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+ case NFT_CT_SECMARK:
+#endif
+ case NFT_CT_EXPIRATION:
+ case NFT_CT_HELPER:
+ if (tb[NFTA_CT_DIRECTION] != NULL)
+ return -EINVAL;
+ break;
+ case NFT_CT_PROTOCOL:
+ case NFT_CT_SRC:
+ case NFT_CT_DST:
+ case NFT_CT_PROTO_SRC:
+ case NFT_CT_PROTO_DST:
+ if (tb[NFTA_CT_DIRECTION] == NULL)
+ return -EINVAL;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ err = nf_ct_l3proto_try_module_get(ctx->afi->family);
+ if (err < 0)
+ return err;
+ priv->family = ctx->afi->family;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ goto err1;
+
+ err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+ if (err < 0)
+ goto err1;
+ return 0;
+
+err1:
+ nf_ct_l3proto_module_put(ctx->afi->family);
+ return err;
+}
+
+static void nft_ct_destroy(const struct nft_expr *expr)
+{
+ struct nft_ct *priv = nft_expr_priv(expr);
+
+ nf_ct_l3proto_module_put(priv->family);
+}
+
+static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_ct *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_CT_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
+ goto nla_put_failure;
+ if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_ct_ops __read_mostly = {
+ .name = "ct",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)),
+ .owner = THIS_MODULE,
+ .eval = nft_ct_eval,
+ .init = nft_ct_init,
+ .destroy = nft_ct_destroy,
+ .dump = nft_ct_dump,
+ .policy = nft_ct_policy,
+ .maxattr = NFTA_CT_MAX,
+};
+
+static int __init nft_ct_module_init(void)
+{
+ return nft_register_expr(&nft_ct_ops);
+}
+
+static void __exit nft_ct_module_exit(void)
+{
+ nft_unregister_expr(&nft_ct_ops);
+}
+
+module_init(nft_ct_module_init);
+module_exit(nft_ct_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("ct");
diff --git a/net/netfilter/nft_expr_template.c b/net/netfilter/nft_expr_template.c
new file mode 100644
index 000000000000..9fc8eb308193
--- /dev/null
+++ b/net/netfilter/nft_expr_template.c
@@ -0,0 +1,88 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_template {
+
+};
+
+static void nft_template_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_template *priv = nft_expr_priv(expr);
+
+}
+
+static const struct nla_policy nft_template_policy[NFTA_TEMPLATE_MAX + 1] = {
+ [NFTA_TEMPLATE_ATTR] = { .type = NLA_U32 },
+};
+
+static int nft_template_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr *tb[])
+{
+ struct nft_template *priv = nft_expr_priv(expr);
+
+ return 0;
+}
+
+static void nft_template_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_template *priv = nft_expr_priv(expr);
+
+}
+
+static int nft_template_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_template *priv = nft_expr_priv(expr);
+
+ NLA_PUT_BE32(skb, NFTA_TEMPLATE_ATTR, priv->field);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops template_ops __read_mostly = {
+ .name = "template",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_template)),
+ .owner = THIS_MODULE,
+ .eval = nft_template_eval,
+ .init = nft_template_init,
+ .destroy = nft_template_destroy,
+ .dump = nft_template_dump,
+ .policy = nft_template_policy,
+ .maxattr = NFTA_TEMPLATE_MAX,
+};
+
+static int __init nft_template_module_init(void)
+{
+ return nft_register_expr(&template_ops);
+}
+
+static void __exit nft_template_module_exit(void)
+{
+ nft_unregister_expr(&template_ops);
+}
+
+module_init(nft_template_module_init);
+module_exit(nft_template_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("template");
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
new file mode 100644
index 000000000000..21c6a6b7b662
--- /dev/null
+++ b/net/netfilter/nft_exthdr.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+// FIXME:
+#include <net/ipv6.h>
+
+struct nft_exthdr {
+ u8 type;
+ u8 offset;
+ u8 len;
+ enum nft_registers dreg:8;
+};
+
+static void nft_exthdr_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_exthdr *priv = nft_expr_priv(expr);
+ struct nft_data *dest = &data[priv->dreg];
+ unsigned int offset;
+ int err;
+
+ err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
+ if (err < 0)
+ goto err;
+ offset += priv->offset;
+
+ if (skb_copy_bits(pkt->skb, offset, dest->data, priv->len) < 0)
+ goto err;
+ return;
+err:
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
+ [NFTA_EXTHDR_DREG] = { .type = NLA_U32 },
+ [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 },
+ [NFTA_EXTHDR_OFFSET] = { .type = NLA_U32 },
+ [NFTA_EXTHDR_LEN] = { .type = NLA_U32 },
+};
+
+static int nft_exthdr_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_exthdr *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_EXTHDR_DREG] == NULL ||
+ tb[NFTA_EXTHDR_TYPE] == NULL ||
+ tb[NFTA_EXTHDR_OFFSET] == NULL ||
+ tb[NFTA_EXTHDR_LEN] == NULL)
+ return -EINVAL;
+
+ priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
+ priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET]));
+ priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN]));
+ if (priv->len == 0 ||
+ priv->len > FIELD_SIZEOF(struct nft_data, data))
+ return -EINVAL;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_EXTHDR_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+ return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+}
+
+static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_exthdr *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_EXTHDR_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_EXTHDR_OFFSET, htonl(priv->offset)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_EXTHDR_LEN, htonl(priv->len)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops exthdr_ops __read_mostly = {
+ .name = "exthdr",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+ .owner = THIS_MODULE,
+ .eval = nft_exthdr_eval,
+ .init = nft_exthdr_init,
+ .dump = nft_exthdr_dump,
+ .policy = nft_exthdr_policy,
+ .maxattr = NFTA_EXTHDR_MAX,
+};
+
+static int __init nft_exthdr_module_init(void)
+{
+ return nft_register_expr(&exthdr_ops);
+}
+
+static void __exit nft_exthdr_module_exit(void)
+{
+ nft_unregister_expr(&exthdr_ops);
+}
+
+module_init(nft_exthdr_module_init);
+module_exit(nft_exthdr_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("exthdr");
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
new file mode 100644
index 000000000000..67cc502881f1
--- /dev/null
+++ b/net/netfilter/nft_hash.c
@@ -0,0 +1,348 @@
+/*
+ * Copyright (c) 2008 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/jhash.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_hash {
+ struct hlist_head *hash;
+ unsigned int hsize;
+ enum nft_registers sreg:8;
+ enum nft_registers dreg:8;
+ u8 klen;
+ u8 dlen;
+ u16 flags;
+};
+
+struct nft_hash_elem {
+ struct hlist_node hnode;
+ struct nft_data key;
+ struct nft_data data[];
+};
+
+static u32 nft_hash_rnd __read_mostly;
+static bool nft_hash_rnd_initted __read_mostly;
+
+static unsigned int nft_hash_data(const struct nft_data *data,
+ unsigned int hsize, unsigned int len)
+{
+ unsigned int h;
+
+ // FIXME: can we reasonably guarantee the upper bits are fixed?
+ h = jhash2(data->data, len >> 2, nft_hash_rnd);
+ return ((u64)h * hsize) >> 32;
+}
+
+static void nft_hash_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_hash *priv = nft_expr_priv(expr);
+ const struct nft_hash_elem *elem;
+ const struct nft_data *key = &data[priv->sreg];
+ unsigned int h;
+
+ h = nft_hash_data(key, priv->hsize, priv->klen);
+ hlist_for_each_entry(elem, &priv->hash[h], hnode) {
+ if (nft_data_cmp(&elem->key, key, priv->klen))
+ continue;
+ if (priv->flags & NFT_HASH_MAP)
+ nft_data_copy(&data[priv->dreg], elem->data);
+ return;
+ }
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static void nft_hash_elem_destroy(const struct nft_expr *expr,
+ struct nft_hash_elem *elem)
+{
+ const struct nft_hash *priv = nft_expr_priv(expr);
+
+ nft_data_uninit(&elem->key, NFT_DATA_VALUE);
+ if (priv->flags & NFT_HASH_MAP)
+ nft_data_uninit(elem->data, nft_dreg_to_type(priv->dreg));
+ kfree(elem);
+}
+
+static const struct nla_policy nft_he_policy[NFTA_HE_MAX + 1] = {
+ [NFTA_HE_KEY] = { .type = NLA_NESTED },
+ [NFTA_HE_DATA] = { .type = NLA_NESTED },
+};
+
+static int nft_hash_elem_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr *nla,
+ struct nft_hash_elem **new)
+{
+ struct nft_hash *priv = nft_expr_priv(expr);
+ struct nlattr *tb[NFTA_HE_MAX + 1];
+ struct nft_hash_elem *elem;
+ struct nft_data_desc d1, d2;
+ unsigned int size;
+ int err;
+
+ err = nla_parse_nested(tb, NFTA_HE_MAX, nla, nft_he_policy);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_HE_KEY] == NULL)
+ return -EINVAL;
+ size = sizeof(*elem);
+
+ if (priv->flags & NFT_HASH_MAP) {
+ if (tb[NFTA_HE_DATA] == NULL)
+ return -EINVAL;
+ size += sizeof(elem->data[0]);
+ } else {
+ if (tb[NFTA_HE_DATA] != NULL)
+ return -EINVAL;
+ }
+
+ elem = kzalloc(size, GFP_KERNEL);
+ if (elem == NULL)
+ return -ENOMEM;
+
+ err = nft_data_init(ctx, &elem->key, &d1, tb[NFTA_HE_KEY]);
+ if (err < 0)
+ goto err1;
+ err = -EINVAL;
+ if (d1.type != NFT_DATA_VALUE || d1.len != priv->klen)
+ goto err2;
+
+ if (tb[NFTA_HE_DATA] != NULL) {
+ err = nft_data_init(ctx, elem->data, &d2, tb[NFTA_HE_DATA]);
+ if (err < 0)
+ goto err2;
+ err = nft_validate_data_load(ctx, priv->dreg, elem->data, d2.type);
+ if (err < 0)
+ goto err3;
+ }
+
+ *new = elem;
+ return 0;
+
+err3:
+ nft_data_uninit(elem->data, d2.type);
+err2:
+ nft_data_uninit(&elem->key, d1.type);
+err1:
+ kfree(elem);
+ return err;
+}
+
+static int nft_hash_elem_dump(struct sk_buff *skb, const struct nft_expr *expr,
+ const struct nft_hash_elem *elem)
+
+{
+ const struct nft_hash *priv = nft_expr_priv(expr);
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, NFTA_LIST_ELEM);
+ if (nest == NULL)
+ goto nla_put_failure;
+
+ if (nft_data_dump(skb, NFTA_HE_KEY, &elem->key,
+ NFT_DATA_VALUE, priv->klen) < 0)
+ goto nla_put_failure;
+
+ if (priv->flags & NFT_HASH_MAP) {
+ if (nft_data_dump(skb, NFTA_HE_DATA, elem->data,
+ NFT_DATA_VALUE, priv->dlen) < 0)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static void nft_hash_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ const struct nft_hash *priv = nft_expr_priv(expr);
+ const struct hlist_node *next;
+ struct nft_hash_elem *elem;
+ unsigned int i;
+
+ for (i = 0; i < priv->hsize; i++) {
+ hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) {
+ hlist_del(&elem->hnode);
+ nft_hash_elem_destroy(expr, elem);
+ }
+ }
+ kfree(priv->hash);
+}
+
+static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
+ [NFTA_HASH_FLAGS] = { .type = NLA_U32 },
+ [NFTA_HASH_SREG] = { .type = NLA_U32 },
+ [NFTA_HASH_DREG] = { .type = NLA_U32 },
+ [NFTA_HASH_KLEN] = { .type = NLA_U32 },
+ [NFTA_HASH_ELEMENTS] = { .type = NLA_NESTED },
+};
+
+static int nft_hash_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_hash *priv = nft_expr_priv(expr);
+ struct nft_hash_elem *elem, *uninitialized_var(new);
+ const struct nlattr *nla;
+ unsigned int cnt, i;
+ unsigned int h;
+ int err, rem;
+
+ if (unlikely(!nft_hash_rnd_initted)) {
+ get_random_bytes(&nft_hash_rnd, 4);
+ nft_hash_rnd_initted = true;
+ }
+
+ if (tb[NFTA_HASH_SREG] == NULL ||
+ tb[NFTA_HASH_KLEN] == NULL ||
+ tb[NFTA_HASH_ELEMENTS] == NULL)
+ return -EINVAL;
+
+ if (tb[NFTA_HASH_FLAGS] != NULL) {
+ priv->flags = ntohl(nla_get_be32(tb[NFTA_HASH_FLAGS]));
+ if (priv->flags & ~NFT_HASH_MAP)
+ return -EINVAL;
+ }
+
+ priv->sreg = ntohl(nla_get_be32(tb[NFTA_HASH_SREG]));
+ err = nft_validate_input_register(priv->sreg);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_HASH_DREG] != NULL) {
+ if (!(priv->flags & NFT_HASH_MAP))
+ return -EINVAL;
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_HASH_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+ }
+
+ priv->klen = ntohl(nla_get_be32(tb[NFTA_HASH_KLEN]));
+ if (priv->klen == 0)
+ return -EINVAL;
+
+ cnt = 0;
+ nla_for_each_nested(nla, tb[NFTA_HASH_ELEMENTS], rem) {
+ if (nla_type(nla) != NFTA_LIST_ELEM)
+ return -EINVAL;
+ cnt++;
+ }
+
+ /* Aim for a load factor of 0.75 */
+ cnt = cnt * 4 / 3;
+
+ priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL);
+ if (priv->hash == NULL)
+ return -ENOMEM;
+ priv->hsize = cnt;
+
+ for (i = 0; i < cnt; i++)
+ INIT_HLIST_HEAD(&priv->hash[i]);
+
+ err = -ENOMEM;
+ nla_for_each_nested(nla, tb[NFTA_HASH_ELEMENTS], rem) {
+ err = nft_hash_elem_init(ctx, expr, nla, &new);
+ if (err < 0)
+ goto err1;
+
+ h = nft_hash_data(&new->key, priv->hsize, priv->klen);
+ hlist_for_each_entry(elem, &priv->hash[h], hnode) {
+ if (nft_data_cmp(&elem->key, &new->key, priv->klen))
+ continue;
+ nft_hash_elem_destroy(expr, new);
+ err = -EEXIST;
+ goto err1;
+ }
+ hlist_add_head(&new->hnode, &priv->hash[h]);
+ }
+ return 0;
+
+err1:
+ nft_hash_destroy(ctx, expr);
+ return err;
+}
+
+static int nft_hash_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_hash *priv = nft_expr_priv(expr);
+ const struct nft_hash_elem *elem;
+ struct nlattr *list;
+ unsigned int i;
+
+ if (priv->flags)
+ if (nla_put_be32(skb, NFTA_HASH_FLAGS, htonl(priv->flags)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_SREG, htonl(priv->sreg)))
+ goto nla_put_failure;
+ if (priv->flags & NFT_HASH_MAP)
+ if (nla_put_be32(skb, NFTA_HASH_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HASH_KLEN, htonl(priv->klen)))
+ goto nla_put_failure;
+
+ list = nla_nest_start(skb, NFTA_HASH_ELEMENTS);
+ if (list == NULL)
+ goto nla_put_failure;
+
+ for (i = 0; i < priv->hsize; i++) {
+ hlist_for_each_entry(elem, &priv->hash[i], hnode) {
+ if (nft_hash_elem_dump(skb, expr, elem) < 0)
+ goto nla_put_failure;
+ }
+ }
+
+ nla_nest_end(skb, list);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_hash_ops __read_mostly = {
+ .name = "hash",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_hash)),
+ .owner = THIS_MODULE,
+ .eval = nft_hash_eval,
+ .init = nft_hash_init,
+ .destroy = nft_hash_destroy,
+ .dump = nft_hash_dump,
+ .policy = nft_hash_policy,
+ .maxattr = NFTA_HASH_MAX,
+};
+
+static int __init nft_hash_module_init(void)
+{
+ return nft_register_expr(&nft_hash_ops);
+}
+
+static void __exit nft_hash_module_exit(void)
+{
+ nft_unregister_expr(&nft_hash_ops);
+}
+
+module_init(nft_hash_module_init);
+module_exit(nft_hash_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("hash");
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
new file mode 100644
index 000000000000..3bf42c3cc49a
--- /dev/null
+++ b/net/netfilter/nft_immediate.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_immediate_expr {
+ struct nft_data data;
+ enum nft_registers dreg:8;
+ u8 dlen;
+};
+
+static void nft_immediate_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+ nft_data_copy(&data[priv->dreg], &priv->data);
+}
+
+static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = {
+ [NFTA_IMMEDIATE_DREG] = { .type = NLA_U32 },
+ [NFTA_IMMEDIATE_DATA] = { .type = NLA_NESTED },
+};
+
+static int nft_immediate_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ struct nft_data_desc desc;
+ int err;
+
+ if (tb[NFTA_IMMEDIATE_DREG] == NULL ||
+ tb[NFTA_IMMEDIATE_DATA] == NULL)
+ return -EINVAL;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_IMMEDIATE_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+
+ err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]);
+ if (err < 0)
+ return err;
+ priv->dlen = desc.len;
+
+ err = nft_validate_data_load(ctx, priv->dreg, &priv->data, desc.type);
+ if (err < 0)
+ goto err1;
+
+ return 0;
+
+err1:
+ nft_data_uninit(&priv->data, desc.type);
+ return err;
+}
+
+static void nft_immediate_destroy(const struct nft_expr *expr)
+{
+ const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+ return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg));
+}
+
+static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_IMMEDIATE_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+
+ return nft_data_dump(skb, NFTA_IMMEDIATE_DATA, &priv->data,
+ nft_dreg_to_type(priv->dreg), priv->dlen);
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_imm_ops __read_mostly = {
+ .name = "immediate",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
+ .owner = THIS_MODULE,
+ .eval = nft_immediate_eval,
+ .init = nft_immediate_init,
+ .destroy = nft_immediate_destroy,
+ .dump = nft_immediate_dump,
+ .policy = nft_immediate_policy,
+ .maxattr = NFTA_IMMEDIATE_MAX,
+};
+
+int __init nft_immediate_module_init(void)
+{
+ return nft_register_expr(&nft_imm_ops);
+}
+
+void nft_immediate_module_exit(void)
+{
+ nft_unregister_expr(&nft_imm_ops);
+}
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
new file mode 100644
index 000000000000..e0e3fc8aebc3
--- /dev/null
+++ b/net/netfilter/nft_limit.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright (c) 2008 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/spinlock.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+static DEFINE_SPINLOCK(limit_lock);
+
+struct nft_limit {
+ u64 tokens;
+ u64 rate;
+ u64 unit;
+ unsigned long stamp;
+};
+
+static void nft_limit_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_limit *priv = nft_expr_priv(expr);
+
+ spin_lock_bh(&limit_lock);
+ if (time_after_eq(jiffies, priv->stamp)) {
+ priv->tokens = priv->rate;
+ priv->stamp = jiffies + priv->unit * HZ;
+ }
+
+ if (priv->tokens >= 1) {
+ priv->tokens--;
+ spin_unlock_bh(&limit_lock);
+ return;
+ }
+ spin_unlock_bh(&limit_lock);
+
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_limit_policy[NFTA_LIMIT_MAX + 1] = {
+ [NFTA_LIMIT_RATE] = { .type = NLA_U64 },
+ [NFTA_LIMIT_UNIT] = { .type = NLA_U64 },
+};
+
+static int nft_limit_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_limit *priv = nft_expr_priv(expr);
+
+ if (tb[NFTA_LIMIT_RATE] == NULL ||
+ tb[NFTA_LIMIT_UNIT] == NULL)
+ return -EINVAL;
+
+ priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE]));
+ priv->unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT]));
+ priv->stamp = jiffies + priv->unit * HZ;
+ priv->tokens = priv->rate;
+ return 0;
+}
+
+static int nft_limit_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_limit *priv = nft_expr_priv(expr);
+
+ if (nla_put_be64(skb, NFTA_LIMIT_RATE, cpu_to_be64(priv->rate)))
+ goto nla_put_failure;
+ if (nla_put_be64(skb, NFTA_LIMIT_UNIT, cpu_to_be64(priv->unit)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_limit_ops __read_mostly = {
+ .name = "limit",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_limit)),
+ .owner = THIS_MODULE,
+ .eval = nft_limit_eval,
+ .init = nft_limit_init,
+ .dump = nft_limit_dump,
+ .policy = nft_limit_policy,
+ .maxattr = NFTA_LIMIT_MAX,
+};
+
+static int __init nft_limit_module_init(void)
+{
+ return nft_register_expr(&nft_limit_ops);
+}
+
+static void __exit nft_limit_module_exit(void)
+{
+ nft_unregister_expr(&nft_limit_ops);
+}
+
+module_init(nft_limit_module_init);
+module_exit(nft_limit_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("limit");
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
new file mode 100644
index 000000000000..da495c3b1e7e
--- /dev/null
+++ b/net/netfilter/nft_log.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_log.h>
+#include <linux/netdevice.h>
+
+static const char *nft_log_null_prefix = "";
+
+struct nft_log {
+ struct nf_loginfo loginfo;
+ char *prefix;
+ int family;
+};
+
+static void nft_log_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_log *priv = nft_expr_priv(expr);
+ struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
+
+ nf_log_packet(net, priv->family, pkt->hooknum, pkt->skb, pkt->in,
+ pkt->out, &priv->loginfo, "%s", priv->prefix);
+}
+
+static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
+ [NFTA_LOG_GROUP] = { .type = NLA_U16 },
+ [NFTA_LOG_PREFIX] = { .type = NLA_STRING },
+ [NFTA_LOG_SNAPLEN] = { .type = NLA_U32 },
+ [NFTA_LOG_QTHRESHOLD] = { .type = NLA_U16 },
+};
+
+static int nft_log_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_log *priv = nft_expr_priv(expr);
+ struct nf_loginfo *li = &priv->loginfo;
+ const struct nlattr *nla;
+
+ priv->family = ctx->afi->family;
+
+ nla = tb[NFTA_LOG_PREFIX];
+ if (nla != NULL) {
+ priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
+ if (priv->prefix == NULL)
+ return -ENOMEM;
+ nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1);
+ } else
+ priv->prefix = (char *)nft_log_null_prefix;
+
+ li->type = NF_LOG_TYPE_ULOG;
+ if (tb[NFTA_LOG_GROUP] != NULL)
+ li->u.ulog.group = ntohs(nla_get_be16(tb[NFTA_LOG_GROUP]));
+
+ if (tb[NFTA_LOG_SNAPLEN] != NULL)
+ li->u.ulog.copy_len = ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN]));
+ if (tb[NFTA_LOG_QTHRESHOLD] != NULL) {
+ li->u.ulog.qthreshold =
+ ntohs(nla_get_be16(tb[NFTA_LOG_QTHRESHOLD]));
+ }
+
+ return 0;
+}
+
+static void nft_log_destroy(const struct nft_expr *expr)
+{
+ struct nft_log *priv = nft_expr_priv(expr);
+
+ if (priv->prefix != nft_log_null_prefix)
+ kfree(priv->prefix);
+}
+
+static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_log *priv = nft_expr_priv(expr);
+ const struct nf_loginfo *li = &priv->loginfo;
+
+ if (priv->prefix != nft_log_null_prefix)
+ if (nla_put_string(skb, NFTA_LOG_PREFIX, priv->prefix))
+ goto nla_put_failure;
+ if (li->u.ulog.group)
+ if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group)))
+ goto nla_put_failure;
+ if (li->u.ulog.copy_len)
+ if (nla_put_be32(skb, NFTA_LOG_SNAPLEN,
+ htonl(li->u.ulog.copy_len)))
+ goto nla_put_failure;
+ if (li->u.ulog.qthreshold)
+ if (nla_put_be16(skb, NFTA_LOG_QTHRESHOLD,
+ htons(li->u.ulog.qthreshold)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_log_ops __read_mostly = {
+ .name = "log",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_log)),
+ .owner = THIS_MODULE,
+ .eval = nft_log_eval,
+ .init = nft_log_init,
+ .destroy = nft_log_destroy,
+ .dump = nft_log_dump,
+ .policy = nft_log_policy,
+ .maxattr = NFTA_LOG_MAX,
+};
+
+static int __init nft_log_module_init(void)
+{
+ return nft_register_expr(&nft_log_ops);
+}
+
+static void __exit nft_log_module_exit(void)
+{
+ nft_unregister_expr(&nft_log_ops);
+}
+
+module_init(nft_log_module_init);
+module_exit(nft_log_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("log");
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
new file mode 100644
index 000000000000..96735aa2f039
--- /dev/null
+++ b/net/netfilter/nft_meta.c
@@ -0,0 +1,222 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/tcp_states.h> /* for TCP_TIME_WAIT */
+#include <net/netfilter/nf_tables.h>
+
+struct nft_meta {
+ enum nft_meta_keys key:8;
+ enum nft_registers dreg:8;
+};
+
+static void nft_meta_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_meta *priv = nft_expr_priv(expr);
+ const struct sk_buff *skb = pkt->skb;
+ const struct net_device *in = pkt->in, *out = pkt->out;
+ struct nft_data *dest = &data[priv->dreg];
+
+ switch (priv->key) {
+ case NFT_META_LEN:
+ dest->data[0] = skb->len;
+ break;
+ case NFT_META_PROTOCOL:
+ *(__be16 *)dest->data = skb->protocol;
+ break;
+ case NFT_META_PRIORITY:
+ dest->data[0] = skb->priority;
+ break;
+ case NFT_META_MARK:
+ dest->data[0] = skb->mark;
+ break;
+ case NFT_META_IIF:
+ if (in == NULL)
+ goto err;
+ dest->data[0] = in->ifindex;
+ break;
+ case NFT_META_OIF:
+ if (out == NULL)
+ goto err;
+ dest->data[0] = out->ifindex;
+ break;
+ case NFT_META_IIFNAME:
+ if (in == NULL)
+ goto err;
+ strncpy((char *)dest->data, in->name, sizeof(dest->data));
+ break;
+ case NFT_META_OIFNAME:
+ if (out == NULL)
+ goto err;
+ strncpy((char *)dest->data, out->name, sizeof(dest->data));
+ break;
+ case NFT_META_IIFTYPE:
+ if (in == NULL)
+ goto err;
+ *(u16 *)dest->data = in->type;
+ break;
+ case NFT_META_OIFTYPE:
+ if (out == NULL)
+ goto err;
+ *(u16 *)dest->data = out->type;
+ break;
+ case NFT_META_SKUID:
+ if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT)
+ goto err;
+
+ read_lock_bh(&skb->sk->sk_callback_lock);
+ if (skb->sk->sk_socket == NULL ||
+ skb->sk->sk_socket->file == NULL) {
+ read_unlock_bh(&skb->sk->sk_callback_lock);
+ goto err;
+ }
+
+ dest->data[0] =
+ from_kuid_munged(&init_user_ns,
+ skb->sk->sk_socket->file->f_cred->fsuid);
+ read_unlock_bh(&skb->sk->sk_callback_lock);
+ break;
+ case NFT_META_SKGID:
+ if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT)
+ goto err;
+
+ read_lock_bh(&skb->sk->sk_callback_lock);
+ if (skb->sk->sk_socket == NULL ||
+ skb->sk->sk_socket->file == NULL) {
+ read_unlock_bh(&skb->sk->sk_callback_lock);
+ goto err;
+ }
+ dest->data[0] =
+ from_kgid_munged(&init_user_ns,
+ skb->sk->sk_socket->file->f_cred->fsgid);
+ read_unlock_bh(&skb->sk->sk_callback_lock);
+ break;
+#ifdef CONFIG_NET_CLS_ROUTE
+ case NFT_META_RTCLASSID: {
+ const struct dst_entry *dst = skb_dst(skb);
+
+ if (dst == NULL)
+ goto err;
+ dest->data[0] = dst->tclassid;
+ break;
+ }
+#endif
+#ifdef CONFIG_NETWORK_SECMARK
+ case NFT_META_SECMARK:
+ dest->data[0] = skb->secmark;
+ break;
+#endif
+ default:
+ WARN_ON(1);
+ goto err;
+ }
+ return;
+
+err:
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+ [NFTA_META_DREG] = { .type = NLA_U32 },
+ [NFTA_META_KEY] = { .type = NLA_U32 },
+};
+
+static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_meta *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_META_DREG] == NULL ||
+ tb[NFTA_META_KEY] == NULL)
+ return -EINVAL;
+
+ priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+ switch (priv->key) {
+ case NFT_META_LEN:
+ case NFT_META_PROTOCOL:
+ case NFT_META_PRIORITY:
+ case NFT_META_MARK:
+ case NFT_META_IIF:
+ case NFT_META_OIF:
+ case NFT_META_IIFNAME:
+ case NFT_META_OIFNAME:
+ case NFT_META_IIFTYPE:
+ case NFT_META_OIFTYPE:
+ case NFT_META_SKUID:
+ case NFT_META_SKGID:
+#ifdef CONFIG_NET_CLS_ROUTE
+ case NFT_META_RTCLASSID:
+#endif
+#ifdef CONFIG_NETWORK_SECMARK
+ case NFT_META_SECMARK:
+#endif
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+ return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+}
+
+static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_meta *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_META_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_meta_ops __read_mostly = {
+ .name = "meta",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+ .owner = THIS_MODULE,
+ .eval = nft_meta_eval,
+ .init = nft_meta_init,
+ .dump = nft_meta_dump,
+ .policy = nft_meta_policy,
+ .maxattr = NFTA_META_MAX,
+};
+
+static int __init nft_meta_module_init(void)
+{
+ return nft_register_expr(&nft_meta_ops);
+}
+
+static void __exit nft_meta_module_exit(void)
+{
+ nft_unregister_expr(&nft_meta_ops);
+}
+
+module_init(nft_meta_module_init);
+module_exit(nft_meta_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("meta");
diff --git a/net/netfilter/nft_meta_target.c b/net/netfilter/nft_meta_target.c
new file mode 100644
index 000000000000..71177df75ffb
--- /dev/null
+++ b/net/netfilter/nft_meta_target.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2008 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_meta {
+ enum nft_meta_keys key;
+};
+
+static void nft_meta_eval(const struct nft_expr *expr,
+ struct nft_data *nfres,
+ struct nft_data *data,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_meta *meta = nft_expr_priv(expr);
+ struct sk_buff *skb = pkt->skb;
+ u32 val = data->data[0];
+
+ switch (meta->key) {
+ case NFT_META_MARK:
+ skb->mark = val;
+ break;
+ case NFT_META_PRIORITY:
+ skb->priority = val;
+ break;
+ case NFT_META_NFTRACE:
+ skb->nf_trace = val;
+ break;
+#ifdef CONFIG_NETWORK_SECMARK
+ case NFT_META_SECMARK:
+ skb->secmark = val;
+ break;
+#endif
+ default:
+ WARN_ON(1);
+ }
+}
+
+static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+ [NFTA_META_KEY] = { .type = NLA_U32 },
+};
+
+static int nft_meta_init(const struct nft_expr *expr, struct nlattr *tb[])
+{
+ struct nft_meta *meta = nft_expr_priv(expr);
+
+ if (tb[NFTA_META_KEY] == NULL)
+ return -EINVAL;
+
+ meta->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+ switch (meta->key) {
+ case NFT_META_MARK:
+ case NFT_META_PRIORITY:
+ case NFT_META_NFTRACE:
+#ifdef CONFIG_NETWORK_SECMARK
+ case NFT_META_SECMARK:
+#endif
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ struct nft_meta *meta = nft_expr_priv(expr);
+
+ NLA_PUT_BE32(skb, NFTA_META_KEY, htonl(meta->key));
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops meta_target __read_mostly = {
+ .name = "meta",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+ .owner = THIS_MODULE,
+ .eval = nft_meta_eval,
+ .init = nft_meta_init,
+ .dump = nft_meta_dump,
+ .policy = nft_meta_policy,
+ .maxattr = NFTA_META_MAX,
+};
+
+static int __init nft_meta_target_init(void)
+{
+ return nft_register_expr(&meta_target);
+}
+
+static void __exit nft_meta_target_exit(void)
+{
+ nft_unregister_expr(&meta_target);
+}
+
+module_init(nft_meta_target_init);
+module_exit(nft_meta_target_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("meta");
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
new file mode 100644
index 000000000000..329f134b3f89
--- /dev/null
+++ b/net/netfilter/nft_payload.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright (c) 2008 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/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_payload {
+ enum nft_payload_bases base:8;
+ u8 offset;
+ u8 len;
+ enum nft_registers dreg:8;
+};
+
+static void nft_payload_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_payload *priv = nft_expr_priv(expr);
+ const struct sk_buff *skb = pkt->skb;
+ struct nft_data *dest = &data[priv->dreg];
+ int offset;
+
+ switch (priv->base) {
+ case NFT_PAYLOAD_LL_HEADER:
+ if (!skb_mac_header_was_set(skb))
+ goto err;
+ offset = skb_mac_header(skb) - skb->data;
+ break;
+ case NFT_PAYLOAD_NETWORK_HEADER:
+ offset = skb_network_offset(skb);
+ break;
+ case NFT_PAYLOAD_TRANSPORT_HEADER:
+ offset = skb_transport_offset(skb);
+ break;
+ default:
+ BUG();
+ }
+ offset += priv->offset;
+
+ if (skb_copy_bits(skb, offset, dest->data, priv->len) < 0)
+ goto err;
+ return;
+err:
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = {
+ [NFTA_PAYLOAD_DREG] = { .type = NLA_U32 },
+ [NFTA_PAYLOAD_BASE] = { .type = NLA_U32 },
+ [NFTA_PAYLOAD_OFFSET] = { .type = NLA_U32 },
+ [NFTA_PAYLOAD_LEN] = { .type = NLA_U32 },
+};
+
+static int nft_payload_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_payload *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_PAYLOAD_DREG] == NULL ||
+ tb[NFTA_PAYLOAD_BASE] == NULL ||
+ tb[NFTA_PAYLOAD_OFFSET] == NULL ||
+ tb[NFTA_PAYLOAD_LEN] == NULL)
+ return -EINVAL;
+
+ priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
+ switch (priv->base) {
+ case NFT_PAYLOAD_LL_HEADER:
+ case NFT_PAYLOAD_NETWORK_HEADER:
+ case NFT_PAYLOAD_TRANSPORT_HEADER:
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
+ priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+ if (priv->len == 0 ||
+ priv->len > FIELD_SIZEOF(struct nft_data, data))
+ return -EINVAL;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+ return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+}
+
+static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_payload *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_PAYLOAD_DREG, htonl(priv->dreg)) ||
+ nla_put_be32(skb, NFTA_PAYLOAD_BASE, htonl(priv->base)) ||
+ nla_put_be32(skb, NFTA_PAYLOAD_OFFSET, htonl(priv->offset)) ||
+ nla_put_be32(skb, NFTA_PAYLOAD_LEN, htonl(priv->len)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_payload_ops __read_mostly = {
+ .name = "payload",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_payload)),
+ .owner = THIS_MODULE,
+ .eval = nft_payload_eval,
+ .init = nft_payload_init,
+ .dump = nft_payload_dump,
+ .policy = nft_payload_policy,
+ .maxattr = NFTA_PAYLOAD_MAX,
+};
+
+int __init nft_payload_module_init(void)
+{
+ return nft_register_expr(&nft_payload_ops);
+}
+
+void nft_payload_module_exit(void)
+{
+ nft_unregister_expr(&nft_payload_ops);
+}
diff --git a/net/netfilter/nft_set.c b/net/netfilter/nft_set.c
new file mode 100644
index 000000000000..7b7c8354c327
--- /dev/null
+++ b/net/netfilter/nft_set.c
@@ -0,0 +1,381 @@
+/*
+ * Copyright (c) 2008 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/module.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_set {
+ struct rb_root root;
+ enum nft_registers sreg:8;
+ enum nft_registers dreg:8;
+ u8 klen;
+ u8 dlen;
+ u16 flags;
+};
+
+struct nft_set_elem {
+ struct rb_node node;
+ enum nft_set_elem_flags flags;
+ struct nft_data key;
+ struct nft_data data[];
+};
+
+static void nft_set_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_set *priv = nft_expr_priv(expr);
+ const struct rb_node *parent = priv->root.rb_node;
+ const struct nft_set_elem *elem, *interval = NULL;
+ const struct nft_data *key = &data[priv->sreg];
+ int d;
+
+ while (parent != NULL) {
+ elem = rb_entry(parent, struct nft_set_elem, node);
+
+ d = nft_data_cmp(&elem->key, key, priv->klen);
+ if (d < 0) {
+ parent = parent->rb_left;
+ interval = elem;
+ } else if (d > 0)
+ parent = parent->rb_right;
+ else {
+found:
+ if (elem->flags & NFT_SE_INTERVAL_END)
+ goto out;
+ if (priv->flags & NFT_SET_MAP)
+ nft_data_copy(&data[priv->dreg], elem->data);
+ return;
+ }
+ }
+
+ if (priv->flags & NFT_SET_INTERVAL && interval != NULL) {
+ elem = interval;
+ goto found;
+ }
+out:
+ data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static void nft_set_elem_destroy(const struct nft_expr *expr,
+ struct nft_set_elem *elem)
+{
+ const struct nft_set *priv = nft_expr_priv(expr);
+
+ nft_data_uninit(&elem->key, NFT_DATA_VALUE);
+ if (priv->flags & NFT_SET_MAP)
+ nft_data_uninit(elem->data, nft_dreg_to_type(priv->dreg));
+ kfree(elem);
+}
+
+static const struct nla_policy nft_se_policy[NFTA_SE_MAX + 1] = {
+ [NFTA_SE_KEY] = { .type = NLA_NESTED },
+ [NFTA_SE_DATA] = { .type = NLA_NESTED },
+ [NFTA_SE_FLAGS] = { .type = NLA_U32 },
+};
+
+static int nft_set_elem_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr *nla,
+ struct nft_set_elem **new)
+{
+ struct nft_set *priv = nft_expr_priv(expr);
+ struct nlattr *tb[NFTA_SE_MAX + 1];
+ struct nft_set_elem *elem;
+ struct nft_data_desc d1, d2;
+ enum nft_set_elem_flags flags = 0;
+ unsigned int size;
+ int err;
+
+ err = nla_parse_nested(tb, NFTA_SE_MAX, nla, nft_se_policy);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_SE_KEY] == NULL)
+ return -EINVAL;
+
+ if (tb[NFTA_SE_FLAGS] != NULL) {
+ flags = ntohl(nla_get_be32(tb[NFTA_SE_FLAGS]));
+ if (flags & ~NFT_SE_INTERVAL_END)
+ return -EINVAL;
+ }
+
+ size = sizeof(*elem);
+ if (priv->flags & NFT_SET_MAP) {
+ if (tb[NFTA_SE_DATA] == NULL && !(flags & NFT_SE_INTERVAL_END))
+ return -EINVAL;
+ size += sizeof(elem->data[0]);
+ } else {
+ if (tb[NFTA_SE_DATA] != NULL)
+ return -EINVAL;
+ }
+
+ elem = kzalloc(size, GFP_KERNEL);
+ if (elem == NULL)
+ return -ENOMEM;
+ elem->flags = flags;
+
+ err = nft_data_init(ctx, &elem->key, &d1, tb[NFTA_SE_KEY]);
+ if (err < 0)
+ goto err1;
+ err = -EINVAL;
+ if (d1.type != NFT_DATA_VALUE || d1.len != priv->klen)
+ goto err2;
+
+ if (tb[NFTA_SE_DATA] != NULL) {
+ err = nft_data_init(ctx, elem->data, &d2, tb[NFTA_SE_DATA]);
+ if (err < 0)
+ goto err2;
+ err = -EINVAL;
+ if (priv->dreg != NFT_REG_VERDICT && d2.len != priv->dlen)
+ goto err2;
+ err = nft_validate_data_load(ctx, priv->dreg, elem->data, d2.type);
+ if (err < 0)
+ goto err3;
+ }
+
+ *new = elem;
+ return 0;
+
+err3:
+ nft_data_uninit(elem->data, d2.type);
+err2:
+ nft_data_uninit(&elem->key, d1.type);
+err1:
+ kfree(elem);
+ return err;
+}
+
+static int nft_set_elem_dump(struct sk_buff *skb, const struct nft_expr *expr,
+ const struct nft_set_elem *elem)
+
+{
+ const struct nft_set *priv = nft_expr_priv(expr);
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, NFTA_LIST_ELEM);
+ if (nest == NULL)
+ goto nla_put_failure;
+
+ if (nft_data_dump(skb, NFTA_SE_KEY, &elem->key,
+ NFT_DATA_VALUE, priv->klen) < 0)
+ goto nla_put_failure;
+
+ if (priv->flags & NFT_SET_MAP && !(elem->flags & NFT_SE_INTERVAL_END)) {
+ if (nft_data_dump(skb, NFTA_SE_DATA, elem->data,
+ nft_dreg_to_type(priv->dreg), priv->dlen) < 0)
+ goto nla_put_failure;
+ }
+
+ if (elem->flags){
+ if (nla_put_be32(skb, NFTA_SE_FLAGS, htonl(elem->flags)))
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static void nft_set_destroy(const struct nft_expr *expr)
+{
+ struct nft_set *priv = nft_expr_priv(expr);
+ struct nft_set_elem *elem;
+ struct rb_node *node;
+
+ while ((node = priv->root.rb_node) != NULL) {
+ rb_erase(node, &priv->root);
+ elem = rb_entry(node, struct nft_set_elem, node);
+ nft_set_elem_destroy(expr, elem);
+ }
+}
+
+static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
+ [NFTA_SET_FLAGS] = { .type = NLA_U32 },
+ [NFTA_SET_SREG] = { .type = NLA_U32 },
+ [NFTA_SET_DREG] = { .type = NLA_U32 },
+ [NFTA_SET_KLEN] = { .type = NLA_U32 },
+ [NFTA_SET_DLEN] = { .type = NLA_U32 },
+ [NFTA_SET_ELEMENTS] = { .type = NLA_NESTED },
+};
+
+static int nft_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_set *priv = nft_expr_priv(expr);
+ struct nft_set_elem *elem, *uninitialized_var(new);
+ struct rb_node *parent, **p;
+ const struct nlattr *nla;
+ int err, rem, d;
+
+ if (tb[NFTA_SET_SREG] == NULL ||
+ tb[NFTA_SET_KLEN] == NULL ||
+ tb[NFTA_SET_ELEMENTS] == NULL)
+ return -EINVAL;
+
+ priv->root = RB_ROOT;
+
+ if (tb[NFTA_SET_FLAGS] != NULL) {
+ priv->flags = ntohl(nla_get_be32(tb[NFTA_SET_FLAGS]));
+ if (priv->flags & ~(NFT_SET_INTERVAL | NFT_SET_MAP))
+ return -EINVAL;
+ }
+
+ priv->sreg = ntohl(nla_get_be32(tb[NFTA_SET_SREG]));
+ err = nft_validate_input_register(priv->sreg);
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_SET_DREG] != NULL) {
+ if (!(priv->flags & NFT_SET_MAP))
+ return -EINVAL;
+ if (tb[NFTA_SET_DLEN] == NULL)
+ return -EINVAL;
+
+ priv->dreg = ntohl(nla_get_be32(tb[NFTA_SET_DREG]));
+ err = nft_validate_output_register(priv->dreg);
+ if (err < 0)
+ return err;
+
+ if (priv->dreg == NFT_REG_VERDICT)
+ priv->dlen = FIELD_SIZEOF(struct nft_data, data);
+ else {
+ priv->dlen = ntohl(nla_get_be32(tb[NFTA_SET_DLEN]));
+ if (priv->dlen == 0 ||
+ priv->dlen > FIELD_SIZEOF(struct nft_data, data))
+ return -EINVAL;
+ }
+ } else {
+ if (priv->flags & NFT_SET_MAP)
+ return -EINVAL;
+ if (tb[NFTA_SET_DLEN] != NULL)
+ return -EINVAL;
+ }
+
+ priv->klen = ntohl(nla_get_be32(tb[NFTA_SET_KLEN]));
+ if (priv->klen == 0 ||
+ priv->klen > FIELD_SIZEOF(struct nft_data, data))
+ return -EINVAL;
+
+ nla_for_each_nested(nla, tb[NFTA_SET_ELEMENTS], rem) {
+ err = -EINVAL;
+ if (nla_type(nla) != NFTA_LIST_ELEM)
+ goto err1;
+
+ err = nft_set_elem_init(ctx, expr, nla, &new);
+ if (err < 0)
+ goto err1;
+
+ parent = NULL;
+ p = &priv->root.rb_node;
+ while (*p != NULL) {
+ parent = *p;
+ elem = rb_entry(parent, struct nft_set_elem, node);
+ d = nft_data_cmp(&elem->key, &new->key, priv->klen);
+ if (d < 0)
+ p = &parent->rb_left;
+ else if (d > 0)
+ p = &parent->rb_right;
+ else {
+ err = -EEXIST;
+ goto err2;
+ }
+ }
+ rb_link_node(&new->node, parent, p);
+ rb_insert_color(&new->node, &priv->root);
+ }
+
+ return 0;
+
+err2:
+ nft_set_elem_destroy(expr, new);
+err1:
+ nft_set_destroy(expr);
+ return err;
+}
+
+static int nft_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ struct nft_set *priv = nft_expr_priv(expr);
+ const struct nft_set_elem *elem;
+ struct rb_node *node;
+ struct nlattr *list;
+
+ if (priv->flags) {
+ if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(priv->flags)))
+ goto nla_put_failure;
+ }
+
+ if (nla_put_be32(skb, NFTA_SET_SREG, htonl(priv->sreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_SET_KLEN, htonl(priv->klen)))
+ goto nla_put_failure;
+
+ if (priv->flags & NFT_SET_MAP) {
+ if (nla_put_be32(skb, NFTA_SET_DREG, htonl(priv->dreg)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_SET_DLEN, htonl(priv->dlen)))
+ goto nla_put_failure;
+ }
+
+ list = nla_nest_start(skb, NFTA_SET_ELEMENTS);
+ if (list == NULL)
+ goto nla_put_failure;
+
+ for (node = rb_first(&priv->root); node; node = rb_next(node)) {
+ elem = rb_entry(node, struct nft_set_elem, node);
+ if (nft_set_elem_dump(skb, expr, elem) < 0)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, list);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_ops nft_set_ops __read_mostly = {
+ .name = "set",
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_set)),
+ .owner = THIS_MODULE,
+ .eval = nft_set_eval,
+ .init = nft_set_init,
+ .destroy = nft_set_destroy,
+ .dump = nft_set_dump,
+ .policy = nft_set_policy,
+ .maxattr = NFTA_SET_MAX,
+};
+
+static int __init nft_set_module_init(void)
+{
+ return nft_register_expr(&nft_set_ops);
+}
+
+static void __exit nft_set_module_exit(void)
+{
+ nft_unregister_expr(&nft_set_ops);
+}
+
+module_init(nft_set_module_init);
+module_exit(nft_set_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("set");