netfilter: nf_tables: don't assume chain stats are set when jumplabel is set

[mirror_ubuntu-bionic-kernel.git] / include / net / netfilter / nf_tables.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _NET_NF_TABLES_H
#define _NET_NF_TABLES_H

#include <linux/module.h>
#include <linux/list.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/nf_tables.h>
#include <linux/u64_stats_sync.h>
#include <net/netlink.h>

#define NFT_JUMP_STACK_SIZE     16

struct nft_pktinfo {
        struct sk_buff                  *skb;
        bool                            tprot_set;
        u8                              tprot;
        /* for x_tables compatibility */
        struct xt_action_param          xt;
};

static inline struct net *nft_net(const struct nft_pktinfo *pkt)
{
        return pkt->xt.state->net;
}

static inline unsigned int nft_hook(const struct nft_pktinfo *pkt)
{
        return pkt->xt.state->hook;
}

static inline u8 nft_pf(const struct nft_pktinfo *pkt)
{
        return pkt->xt.state->pf;
}

static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt)
{
        return pkt->xt.state->in;
}

static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt)
{
        return pkt->xt.state->out;
}

static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
                                   struct sk_buff *skb,
                                   const struct nf_hook_state *state)
{
        pkt->skb = skb;
        pkt->xt.state = state;
}

static inline void nft_set_pktinfo_proto_unspec(struct nft_pktinfo *pkt,
                                                struct sk_buff *skb)
{
        pkt->tprot_set = false;
        pkt->tprot = 0;
        pkt->xt.thoff = 0;
        pkt->xt.fragoff = 0;
}

static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt,
                                          struct sk_buff *skb,
                                          const struct nf_hook_state *state)
{
        nft_set_pktinfo(pkt, skb, state);
        nft_set_pktinfo_proto_unspec(pkt, skb);
}

/**
 *      struct nft_verdict - nf_tables verdict
 *
 *      @code: nf_tables/netfilter verdict code
 *      @chain: destination chain for NFT_JUMP/NFT_GOTO
 */
struct nft_verdict {
        u32                             code;
        struct nft_chain                *chain;
};

struct nft_data {
        union {
                u32                     data[4];
                struct nft_verdict      verdict;
        };
} __attribute__((aligned(__alignof__(u64))));

/**
 *      struct nft_regs - nf_tables register set
 *
 *      @data: data registers
 *      @verdict: verdict register
 *
 *      The first four data registers alias to the verdict register.
 */
struct nft_regs {
        union {
                u32                     data[20];
                struct nft_verdict      verdict;
        };
};

/* Store/load an u16 or u8 integer to/from the u32 data register.
 *
 * Note, when using concatenations, register allocation happens at 32-bit
 * level. So for store instruction, pad the rest part with zero to avoid
 * garbage values.
 */

static inline void nft_reg_store16(u32 *dreg, u16 val)
{
        *dreg = 0;
        *(u16 *)dreg = val;
}

static inline void nft_reg_store8(u32 *dreg, u8 val)
{
        *dreg = 0;
        *(u8 *)dreg = val;
}

static inline u16 nft_reg_load16(u32 *sreg)
{
        return *(u16 *)sreg;
}

static inline u8 nft_reg_load8(u32 *sreg)
{
        return *(u8 *)sreg;
}

static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
                                 unsigned int len)
{
        memcpy(dst, src, len);
}

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/set context
 *
 *      @net: net namespace
 *      @afi: address family info
 *      @table: the table the chain is contained in
 *      @chain: the chain the rule is contained in
 *      @nla: netlink attributes
 *      @portid: netlink portID of the original message
 *      @seq: netlink sequence number
 *      @report: notify via unicast netlink message
 */
struct nft_ctx {
        struct net                      *net;
        struct nft_af_info              *afi;
        struct nft_table                *table;
        struct nft_chain                *chain;
        const struct nlattr * const     *nla;
        u32                             portid;
        u32                             seq;
        bool                            report;
};

struct nft_data_desc {
        enum nft_data_types             type;
        unsigned int                    len;
};

int nft_data_init(const struct nft_ctx *ctx,
                  struct nft_data *data, unsigned int size,
                  struct nft_data_desc *desc, const struct nlattr *nla);
void nft_data_release(const struct nft_data *data, enum nft_data_types type);
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;
}

static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
{
        return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE;
}

int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest);
unsigned int nft_parse_register(const struct nlattr *attr);
int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg);

int nft_validate_register_load(enum nft_registers reg, unsigned int len);
int nft_validate_register_store(const struct nft_ctx *ctx,
                                enum nft_registers reg,
                                const struct nft_data *data,
                                enum nft_data_types type, unsigned int len);

/**
 *      struct nft_userdata - user defined data associated with an object
 *
 *      @len: length of the data
 *      @data: content
 *
 *      The presence of user data is indicated in an object specific fashion,
 *      so a length of zero can't occur and the value "len" indicates data
 *      of length len + 1.
 */
struct nft_userdata {
        u8                      len;
        unsigned char           data[0];
};

/**
 *      struct nft_set_elem - generic representation of set elements
 *
 *      @key: element key
 *      @priv: element private data and extensions
 */
struct nft_set_elem {
        union {
                u32             buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
                struct nft_data val;
        } key;
        void                    *priv;
};

struct nft_set;
struct nft_set_iter {
        u8              genmask;
        unsigned int    count;
        unsigned int    skip;
        int             err;
        int             (*fn)(const struct nft_ctx *ctx,
                              struct nft_set *set,
                              const struct nft_set_iter *iter,
                              struct nft_set_elem *elem);
};

/**
 *      struct nft_set_desc - description of set elements
 *
 *      @klen: key length
 *      @dlen: data length
 *      @size: number of set elements
 */
struct nft_set_desc {
        unsigned int            klen;
        unsigned int            dlen;
        unsigned int            size;
};

/**
 *      enum nft_set_class - performance class
 *
 *      @NFT_LOOKUP_O_1: constant, O(1)
 *      @NFT_LOOKUP_O_LOG_N: logarithmic, O(log N)
 *      @NFT_LOOKUP_O_N: linear, O(N)
 */
enum nft_set_class {
        NFT_SET_CLASS_O_1,
        NFT_SET_CLASS_O_LOG_N,
        NFT_SET_CLASS_O_N,
};

/**
 *      struct nft_set_estimate - estimation of memory and performance
 *                                characteristics
 *
 *      @size: required memory
 *      @lookup: lookup performance class
 *      @space: memory class
 */
struct nft_set_estimate {
        unsigned int            size;
        enum nft_set_class      lookup;
        enum nft_set_class      space;
};

/**
 *      struct nft_set_type - nf_tables set type
 *
 *      @select_ops: function to select nft_set_ops
 *      @ops: default ops, used when no select_ops functions is present
 *      @list: used internally
 *      @owner: module reference
 */
struct nft_set_type {
        const struct nft_set_ops        *(*select_ops)(const struct nft_ctx *,
                                                       const struct nft_set_desc *desc,
                                                       u32 flags);
        const struct nft_set_ops        *ops;
        struct list_head                list;
        struct module                   *owner;
};

struct nft_set_ext;
struct nft_expr;

/**
 *      struct nft_set_ops - nf_tables set operations
 *
 *      @lookup: look up an element within the set
 *      @insert: insert new element into set
 *      @activate: activate new element in the next generation
 *      @deactivate: lookup for element and deactivate it in the next generation
 *      @flush: deactivate element in the next generation
 *      @remove: remove element from set
 *      @walk: iterate over all set elemeennts
 *      @get: get set elements
 *      @privsize: function to return size of set private data
 *      @init: initialize private data of new set instance
 *      @destroy: destroy private data of set instance
 *      @elemsize: element private size
 *      @features: features supported by the implementation
 */
struct nft_set_ops {
        bool                            (*lookup)(const struct net *net,
                                                  const struct nft_set *set,
                                                  const u32 *key,
                                                  const struct nft_set_ext **ext);
        bool                            (*update)(struct nft_set *set,
                                                  const u32 *key,
                                                  void *(*new)(struct nft_set *,
                                                               const struct nft_expr *,
                                                               struct nft_regs *),
                                                  const struct nft_expr *expr,
                                                  struct nft_regs *regs,
                                                  const struct nft_set_ext **ext);

        int                             (*insert)(const struct net *net,
                                                  const struct nft_set *set,
                                                  const struct nft_set_elem *elem,
                                                  struct nft_set_ext **ext);
        void                            (*activate)(const struct net *net,
                                                    const struct nft_set *set,
                                                    const struct nft_set_elem *elem);
        void *                          (*deactivate)(const struct net *net,
                                                      const struct nft_set *set,
                                                      const struct nft_set_elem *elem);
        bool                            (*flush)(const struct net *net,
                                                 const struct nft_set *set,
                                                 void *priv);
        void                            (*remove)(const struct net *net,
                                                  const struct nft_set *set,
                                                  const struct nft_set_elem *elem);
        void                            (*walk)(const struct nft_ctx *ctx,
                                                struct nft_set *set,
                                                struct nft_set_iter *iter);
        void *                          (*get)(const struct net *net,
                                               const struct nft_set *set,
                                               const struct nft_set_elem *elem,
                                               unsigned int flags);

        unsigned int                    (*privsize)(const struct nlattr * const nla[],
                                                    const struct nft_set_desc *desc);
        bool                            (*estimate)(const struct nft_set_desc *desc,
                                                    u32 features,
                                                    struct nft_set_estimate *est);
        int                             (*init)(const struct nft_set *set,
                                                const struct nft_set_desc *desc,
                                                const struct nlattr * const nla[]);
        void                            (*destroy)(const struct nft_set *set);

        unsigned int                    elemsize;
        u32                             features;
        const struct nft_set_type       *type;
};

int nft_register_set(struct nft_set_type *type);
void nft_unregister_set(struct nft_set_type *type);

/**
 *      struct nft_set - nf_tables set instance
 *
 *      @list: table set list node
 *      @bindings: list of set bindings
 *      @name: name of the set
 *      @ktype: key type (numeric type defined by userspace, not used in the kernel)
 *      @dtype: data type (verdict or numeric type defined by userspace)
 *      @objtype: object type (see NFT_OBJECT_* definitions)
 *      @size: maximum set size
 *      @nelems: number of elements
 *      @ndeact: number of deactivated elements queued for removal
 *      @timeout: default timeout value in jiffies
 *      @gc_int: garbage collection interval in msecs
 *      @policy: set parameterization (see enum nft_set_policies)
 *      @udlen: user data length
 *      @udata: user data
 *      @ops: set ops
 *      @flags: set flags
 *      @genmask: generation mask
 *      @klen: key length
 *      @dlen: data length
 *      @data: private set data
 */
struct nft_set {
        struct list_head                list;
        struct list_head                bindings;
        char                            *name;
        u32                             ktype;
        u32                             dtype;
        u32                             objtype;
        u32                             size;
        atomic_t                        nelems;
        u32                             ndeact;
        u64                             timeout;
        u32                             gc_int;
        u16                             policy;
        u16                             udlen;
        unsigned char                   *udata;
        /* runtime data below here */
        const struct nft_set_ops        *ops ____cacheline_aligned;
        u16                             flags:14,
                                        genmask:2;
        u8                              klen;
        u8                              dlen;
        unsigned char                   data[]
                __attribute__((aligned(__alignof__(u64))));
};

static inline void *nft_set_priv(const struct nft_set *set)
{
        return (void *)set->data;
}

static inline struct nft_set *nft_set_container_of(const void *priv)
{
        return (void *)priv - offsetof(struct nft_set, data);
}

struct nft_set *nft_set_lookup(const struct net *net,
                               const struct nft_table *table,
                               const struct nlattr *nla_set_name,
                               const struct nlattr *nla_set_id,
                               u8 genmask);

static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
{
        return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ;
}

/**
 *      struct nft_set_binding - nf_tables set binding
 *
 *      @list: set bindings list node
 *      @chain: chain containing the rule bound to the set
 *      @flags: set action flags
 *
 *      A set binding contains all information necessary for validation
 *      of new elements added to a bound set.
 */
struct nft_set_binding {
        struct list_head                list;
        const struct nft_chain          *chain;
        u32                             flags;
};

int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
                       struct nft_set_binding *binding);
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
                          struct nft_set_binding *binding);

/**
 *      enum nft_set_extensions - set extension type IDs
 *
 *      @NFT_SET_EXT_KEY: element key
 *      @NFT_SET_EXT_DATA: mapping data
 *      @NFT_SET_EXT_FLAGS: element flags
 *      @NFT_SET_EXT_TIMEOUT: element timeout
 *      @NFT_SET_EXT_EXPIRATION: element expiration time
 *      @NFT_SET_EXT_USERDATA: user data associated with the element
 *      @NFT_SET_EXT_EXPR: expression assiociated with the element
 *      @NFT_SET_EXT_OBJREF: stateful object reference associated with element
 *      @NFT_SET_EXT_NUM: number of extension types
 */
enum nft_set_extensions {
        NFT_SET_EXT_KEY,
        NFT_SET_EXT_DATA,
        NFT_SET_EXT_FLAGS,
        NFT_SET_EXT_TIMEOUT,
        NFT_SET_EXT_EXPIRATION,
        NFT_SET_EXT_USERDATA,
        NFT_SET_EXT_EXPR,
        NFT_SET_EXT_OBJREF,
        NFT_SET_EXT_NUM
};

/**
 *      struct nft_set_ext_type - set extension type
 *
 *      @len: fixed part length of the extension
 *      @align: alignment requirements of the extension
 */
struct nft_set_ext_type {
        u8      len;
        u8      align;
};

extern const struct nft_set_ext_type nft_set_ext_types[];

/**
 *      struct nft_set_ext_tmpl - set extension template
 *
 *      @len: length of extension area
 *      @offset: offsets of individual extension types
 */
struct nft_set_ext_tmpl {
        u16     len;
        u8      offset[NFT_SET_EXT_NUM];
};

/**
 *      struct nft_set_ext - set extensions
 *
 *      @genmask: generation mask
 *      @offset: offsets of individual extension types
 *      @data: beginning of extension data
 */
struct nft_set_ext {
        u8      genmask;
        u8      offset[NFT_SET_EXT_NUM];
        char    data[0];
};

static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl)
{
        memset(tmpl, 0, sizeof(*tmpl));
        tmpl->len = sizeof(struct nft_set_ext);
}

static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id,
                                          unsigned int len)
{
        tmpl->len        = ALIGN(tmpl->len, nft_set_ext_types[id].align);
        BUG_ON(tmpl->len > U8_MAX);
        tmpl->offset[id] = tmpl->len;
        tmpl->len       += nft_set_ext_types[id].len + len;
}

static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id)
{
        nft_set_ext_add_length(tmpl, id, 0);
}

static inline void nft_set_ext_init(struct nft_set_ext *ext,
                                    const struct nft_set_ext_tmpl *tmpl)
{
        memcpy(ext->offset, tmpl->offset, sizeof(ext->offset));
}

static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id)
{
        return !!ext->offset[id];
}

static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id)
{
        return ext && __nft_set_ext_exists(ext, id);
}

static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id)
{
        return (void *)ext + ext->offset[id];
}

static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_KEY);
}

static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_DATA);
}

static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_FLAGS);
}

static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
}

static inline unsigned long *nft_set_ext_expiration(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION);
}

static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_USERDATA);
}

static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_EXPR);
}

static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
{
        return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
               time_is_before_eq_jiffies(*nft_set_ext_expiration(ext));
}

static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
                                                   void *elem)
{
        return elem + set->ops->elemsize;
}

static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext)
{
        return nft_set_ext(ext, NFT_SET_EXT_OBJREF);
}

void *nft_set_elem_init(const struct nft_set *set,
                        const struct nft_set_ext_tmpl *tmpl,
                        const u32 *key, const u32 *data,
                        u64 timeout, gfp_t gfp);
void nft_set_elem_destroy(const struct nft_set *set, void *elem,
                          bool destroy_expr);

/**
 *      struct nft_set_gc_batch_head - nf_tables set garbage collection batch
 *
 *      @rcu: rcu head
 *      @set: set the elements belong to
 *      @cnt: count of elements
 */
struct nft_set_gc_batch_head {
        struct rcu_head                 rcu;
        const struct nft_set            *set;
        unsigned int                    cnt;
};

#define NFT_SET_GC_BATCH_SIZE   ((PAGE_SIZE -                             \
                                  sizeof(struct nft_set_gc_batch_head)) / \
                                 sizeof(void *))

/**
 *      struct nft_set_gc_batch - nf_tables set garbage collection batch
 *
 *      @head: GC batch head
 *      @elems: garbage collection elements
 */
struct nft_set_gc_batch {
        struct nft_set_gc_batch_head    head;
        void                            *elems[NFT_SET_GC_BATCH_SIZE];
};

struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set,
                                                gfp_t gfp);
void nft_set_gc_batch_release(struct rcu_head *rcu);

static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb)
{
        if (gcb != NULL)
                call_rcu(&gcb->head.rcu, nft_set_gc_batch_release);
}

static inline struct nft_set_gc_batch *
nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb,
                       gfp_t gfp)
{
        if (gcb != NULL) {
                if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems))
                        return gcb;
                nft_set_gc_batch_complete(gcb);
        }
        return nft_set_gc_batch_alloc(set, gfp);
}

static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb,
                                        void *elem)
{
        gcb->elems[gcb->head.cnt++] = elem;
}

/**
 *      struct nft_expr_type - nf_tables expression type
 *
 *      @select_ops: function to select nft_expr_ops
 *      @ops: default ops, used when no select_ops functions is present
 *      @list: used internally
 *      @name: Identifier
 *      @owner: module reference
 *      @policy: netlink attribute policy
 *      @maxattr: highest netlink attribute number
 *      @family: address family for AF-specific types
 *      @flags: expression type flags
 */
struct nft_expr_type {
        const struct nft_expr_ops       *(*select_ops)(const struct nft_ctx *,
                                                       const struct nlattr * const tb[]);
        const struct nft_expr_ops       *ops;
        struct list_head                list;
        const char                      *name;
        struct module                   *owner;
        const struct nla_policy         *policy;
        unsigned int                    maxattr;
        u8                              family;
        u8                              flags;
};

#define NFT_EXPR_STATEFUL               0x1

/**
 *      struct nft_expr_ops - nf_tables expression operations
 *
 *      @eval: Expression evaluation function
 *      @size: full expression size, including private data size
 *      @init: initialization function
 *      @destroy: destruction function
 *      @dump: function to dump parameters
 *      @type: expression type
 *      @validate: validate expression, called during loop detection
 *      @data: extra data to attach to this expression operation
 */
struct nft_expr;
struct nft_expr_ops {
        void                            (*eval)(const struct nft_expr *expr,
                                                struct nft_regs *regs,
                                                const struct nft_pktinfo *pkt);
        int                             (*clone)(struct nft_expr *dst,
                                                 const struct nft_expr *src);
        unsigned int                    size;

        int                             (*init)(const struct nft_ctx *ctx,
                                                const struct nft_expr *expr,
                                                const struct nlattr * const tb[]);
        void                            (*destroy)(const struct nft_ctx *ctx,
                                                   const struct nft_expr *expr);
        int                             (*dump)(struct sk_buff *skb,
                                                const struct nft_expr *expr);
        int                             (*validate)(const struct nft_ctx *ctx,
                                                    const struct nft_expr *expr,
                                                    const struct nft_data **data);
        const struct nft_expr_type      *type;
        void                            *data;
};

#define NFT_EXPR_MAXATTR                16
#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_expr *nft_expr_init(const struct nft_ctx *ctx,
                               const struct nlattr *nla);
void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr);
int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
                  const struct nft_expr *expr);

static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
{
        int err;

        if (src->ops->clone) {
                dst->ops = src->ops;
                err = src->ops->clone(dst, src);
                if (err < 0)
                        return err;
        } else {
                memcpy(dst, src, src->ops->size);
        }

        __module_get(src->ops->type->owner);
        return 0;
}

/**
 *      struct nft_rule - nf_tables rule
 *
 *      @list: used internally
 *      @handle: rule handle
 *      @genmask: generation mask
 *      @dlen: length of expression data
 *      @udata: user data is appended to the rule
 *      @data: expression data
 */
struct nft_rule {
        struct list_head                list;
        u64                             handle:42,
                                        genmask:2,
                                        dlen:12,
                                        udata:1;
        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];
}

static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule)
{
        return (void *)&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,
};

/**
 *      struct nft_chain - nf_tables chain
 *
 *      @rules: list of rules in the chain
 *      @list: used internally
 *      @table: table that this chain belongs to
 *      @handle: chain handle
 *      @use: number of jump references to this chain
 *      @level: length of longest path to this chain
 *      @flags: bitmask of enum nft_chain_flags
 *      @name: name of the chain
 */
struct nft_chain {
        struct list_head                rules;
        struct list_head                list;
        struct nft_table                *table;
        u64                             handle;
        u32                             use;
        u16                             level;
        u8                              flags:6,
                                        genmask:2;
        char                            *name;
};

enum nft_chain_type {
        NFT_CHAIN_T_DEFAULT = 0,
        NFT_CHAIN_T_ROUTE,
        NFT_CHAIN_T_NAT,
        NFT_CHAIN_T_MAX
};

/**
 *      struct nf_chain_type - nf_tables chain type info
 *
 *      @name: name of the type
 *      @type: numeric identifier
 *      @family: address family
 *      @owner: module owner
 *      @hook_mask: mask of valid hooks
 *      @hooks: hookfn overrides
 */
struct nf_chain_type {
        const char                      *name;
        enum nft_chain_type             type;
        int                             family;
        struct module                   *owner;
        unsigned int                    hook_mask;
        nf_hookfn                       *hooks[NF_MAX_HOOKS];
};

int nft_chain_validate_dependency(const struct nft_chain *chain,
                                  enum nft_chain_type type);
int nft_chain_validate_hooks(const struct nft_chain *chain,
                             unsigned int hook_flags);

struct nft_stats {
        u64                     bytes;
        u64                     pkts;
        struct u64_stats_sync   syncp;
};

#define NFT_HOOK_OPS_MAX                2

/**
 *      struct nft_base_chain - nf_tables base chain
 *
 *      @ops: netfilter hook ops
 *      @type: chain type
 *      @policy: default policy
 *      @stats: per-cpu chain stats
 *      @chain: the chain
 *      @dev_name: device name that this base chain is attached to (if any)
 */
struct nft_base_chain {
        struct nf_hook_ops              ops[NFT_HOOK_OPS_MAX];
        const struct nf_chain_type      *type;
        u8                              policy;
        u8                              flags;
        struct nft_stats __percpu       *stats;
        struct nft_chain                chain;
        char                            dev_name[IFNAMSIZ];
};

static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain)
{
        return container_of(chain, struct nft_base_chain, chain);
}

static inline bool nft_is_base_chain(const struct nft_chain *chain)
{
        return chain->flags & NFT_BASE_CHAIN;
}

int __nft_release_basechain(struct nft_ctx *ctx);

unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);

/**
 *      struct nft_table - nf_tables table
 *
 *      @list: used internally
 *      @chains: chains in the table
 *      @sets: sets in the table
 *      @objects: stateful objects in the table
 *      @hgenerator: handle generator state
 *      @use: number of chain references to this table
 *      @flags: table flag (see enum nft_table_flags)
 *      @genmask: generation mask
 *      @name: name of the table
 */
struct nft_table {
        struct list_head                list;
        struct list_head                chains;
        struct list_head                sets;
        struct list_head                objects;
        u64                             hgenerator;
        u32                             use;
        u16                             flags:14,
                                        genmask:2;
        char                            *name;
};

enum nft_af_flags {
        NFT_AF_NEEDS_DEV        = (1 << 0),
};

/**
 *      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
 *      @flags: family flags
 *      @nops: number of hook ops in this family
 *      @hook_ops_init: initialization function for chain hook ops
 *      @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;
        u32                             flags;
        unsigned int                    nops;
        void                            (*hook_ops_init)(struct nf_hook_ops *,
                                                         unsigned int);
        nf_hookfn                       *hooks[NF_MAX_HOOKS];
};

int nft_register_afinfo(struct net *, struct nft_af_info *);
void nft_unregister_afinfo(struct net *, struct nft_af_info *);

int nft_register_chain_type(const struct nf_chain_type *);
void nft_unregister_chain_type(const struct nf_chain_type *);

int nft_register_expr(struct nft_expr_type *);
void nft_unregister_expr(struct nft_expr_type *);

int nft_verdict_dump(struct sk_buff *skb, int type,
                     const struct nft_verdict *v);

/**
 *      struct nft_object - nf_tables stateful object
 *
 *      @list: table stateful object list node
 *      @table: table this object belongs to
 *      @name: name of this stateful object
 *      @genmask: generation mask
 *      @use: number of references to this stateful object
 *      @data: object data, layout depends on type
 *      @ops: object operations
 *      @data: pointer to object data
 */
struct nft_object {
        struct list_head                list;
        char                            *name;
        struct nft_table                *table;
        u32                             genmask:2,
                                        use:30;
        /* runtime data below here */
        const struct nft_object_ops     *ops ____cacheline_aligned;
        unsigned char                   data[]
                __attribute__((aligned(__alignof__(u64))));
};

static inline void *nft_obj_data(const struct nft_object *obj)
{
        return (void *)obj->data;
}

#define nft_expr_obj(expr)      *((struct nft_object **)nft_expr_priv(expr))

struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
                                        const struct nlattr *nla, u32 objtype,
                                        u8 genmask);

void nft_obj_notify(struct net *net, struct nft_table *table,
                    struct nft_object *obj, u32 portid, u32 seq,
                    int event, int family, int report, gfp_t gfp);

/**
 *      struct nft_object_type - stateful object type
 *
 *      @select_ops: function to select nft_object_ops
 *      @ops: default ops, used when no select_ops functions is present
 *      @list: list node in list of object types
 *      @type: stateful object numeric type
 *      @owner: module owner
 *      @maxattr: maximum netlink attribute
 *      @policy: netlink attribute policy
 */
struct nft_object_type {
        const struct nft_object_ops     *(*select_ops)(const struct nft_ctx *,
                                                       const struct nlattr * const tb[]);
        const struct nft_object_ops     *ops;
        struct list_head                list;
        u32                             type;
        unsigned int                    maxattr;
        struct module                   *owner;
        const struct nla_policy         *policy;
};

/**
 *      struct nft_object_ops - stateful object operations
 *
 *      @eval: stateful object evaluation function
 *      @size: stateful object size
 *      @init: initialize object from netlink attributes
 *      @destroy: release existing stateful object
 *      @dump: netlink dump stateful object
 */
struct nft_object_ops {
        void                            (*eval)(struct nft_object *obj,
                                                struct nft_regs *regs,
                                                const struct nft_pktinfo *pkt);
        unsigned int                    size;
        int                             (*init)(const struct nft_ctx *ctx,
                                                const struct nlattr *const tb[],
                                                struct nft_object *obj);
        void                            (*destroy)(struct nft_object *obj);
        int                             (*dump)(struct sk_buff *skb,
                                                struct nft_object *obj,
                                                bool reset);
        const struct nft_object_type    *type;
};

int nft_register_obj(struct nft_object_type *obj_type);
void nft_unregister_obj(struct nft_object_type *obj_type);

/**
 *      struct nft_traceinfo - nft tracing information and state
 *
 *      @pkt: pktinfo currently processed
 *      @basechain: base chain currently processed
 *      @chain: chain currently processed
 *      @rule:  rule that was evaluated
 *      @verdict: verdict given by rule
 *      @type: event type (enum nft_trace_types)
 *      @packet_dumped: packet headers sent in a previous traceinfo message
 *      @trace: other struct members are initialised
 */
struct nft_traceinfo {
        const struct nft_pktinfo        *pkt;
        const struct nft_base_chain     *basechain;
        const struct nft_chain          *chain;
        const struct nft_rule           *rule;
        const struct nft_verdict        *verdict;
        enum nft_trace_types            type;
        bool                            packet_dumped;
        bool                            trace;
};

void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt,
                    const struct nft_verdict *verdict,
                    const struct nft_chain *basechain);

void nft_trace_notify(struct nft_traceinfo *info);

#define nft_dereference(p)                                      \
        nfnl_dereference(p, NFNL_SUBSYS_NFTABLES)

#define MODULE_ALIAS_NFT_FAMILY(family) \
        MODULE_ALIAS("nft-afinfo-" __stringify(family))

#define MODULE_ALIAS_NFT_CHAIN(family, name) \
        MODULE_ALIAS("nft-chain-" __stringify(family) "-" name)

#define MODULE_ALIAS_NFT_AF_EXPR(family, name) \
        MODULE_ALIAS("nft-expr-" __stringify(family) "-" name)

#define MODULE_ALIAS_NFT_EXPR(name) \
        MODULE_ALIAS("nft-expr-" name)

#define MODULE_ALIAS_NFT_SET() \
        MODULE_ALIAS("nft-set")

#define MODULE_ALIAS_NFT_OBJ(type) \
        MODULE_ALIAS("nft-obj-" __stringify(type))

/*
 * The gencursor defines two generations, the currently active and the
 * next one. Objects contain a bitmask of 2 bits specifying the generations
 * they're active in. A set bit means they're inactive in the generation
 * represented by that bit.
 *
 * New objects start out as inactive in the current and active in the
 * next generation. When committing the ruleset the bitmask is cleared,
 * meaning they're active in all generations. When removing an object,
 * it is set inactive in the next generation. After committing the ruleset,
 * the objects are removed.
 */
static inline unsigned int nft_gencursor_next(const struct net *net)
{
        return net->nft.gencursor + 1 == 1 ? 1 : 0;
}

static inline u8 nft_genmask_next(const struct net *net)
{
        return 1 << nft_gencursor_next(net);
}

static inline u8 nft_genmask_cur(const struct net *net)
{
        /* Use READ_ONCE() to prevent refetching the value for atomicity */
        return 1 << READ_ONCE(net->nft.gencursor);
}

#define NFT_GENMASK_ANY         ((1 << 0) | (1 << 1))

/*
 * Generic transaction helpers
 */

/* Check if this object is currently active. */
#define nft_is_active(__net, __obj)                             \
        (((__obj)->genmask & nft_genmask_cur(__net)) == 0)

/* Check if this object is active in the next generation. */
#define nft_is_active_next(__net, __obj)                        \
        (((__obj)->genmask & nft_genmask_next(__net)) == 0)

/* This object becomes active in the next generation. */
#define nft_activate_next(__net, __obj)                         \
        (__obj)->genmask = nft_genmask_cur(__net)

/* This object becomes inactive in the next generation. */
#define nft_deactivate_next(__net, __obj)                       \
        (__obj)->genmask = nft_genmask_next(__net)

/* After committing the ruleset, clear the stale generation bit. */
#define nft_clear(__net, __obj)                                 \
        (__obj)->genmask &= ~nft_genmask_next(__net)
#define nft_active_genmask(__obj, __genmask)                    \
        !((__obj)->genmask & __genmask)

/*
 * Set element transaction helpers
 */

static inline bool nft_set_elem_active(const struct nft_set_ext *ext,
                                       u8 genmask)
{
        return !(ext->genmask & genmask);
}

static inline void nft_set_elem_change_active(const struct net *net,
                                              const struct nft_set *set,
                                              struct nft_set_ext *ext)
{
        ext->genmask ^= nft_genmask_next(net);
}

/*
 * We use a free bit in the genmask field to indicate the element
 * is busy, meaning it is currently being processed either by
 * the netlink API or GC.
 *
 * Even though the genmask is only a single byte wide, this works
 * because the extension structure if fully constant once initialized,
 * so there are no non-atomic write accesses unless it is already
 * marked busy.
 */
#define NFT_SET_ELEM_BUSY_MASK  (1 << 2)

#if defined(__LITTLE_ENDIAN_BITFIELD)
#define NFT_SET_ELEM_BUSY_BIT   2
#elif defined(__BIG_ENDIAN_BITFIELD)
#define NFT_SET_ELEM_BUSY_BIT   (BITS_PER_LONG - BITS_PER_BYTE + 2)
#else
#error
#endif

static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext)
{
        unsigned long *word = (unsigned long *)ext;

        BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0);
        return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word);
}

static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext)
{
        unsigned long *word = (unsigned long *)ext;

        clear_bit(NFT_SET_ELEM_BUSY_BIT, word);
}

/**
 *      struct nft_trans - nf_tables object update in transaction
 *
 *      @list: used internally
 *      @msg_type: message type
 *      @ctx: transaction context
 *      @data: internal information related to the transaction
 */
struct nft_trans {
        struct list_head                list;
        int                             msg_type;
        struct nft_ctx                  ctx;
        char                            data[0];
};

struct nft_trans_rule {
        struct nft_rule                 *rule;
        u32                             rule_id;
};

#define nft_trans_rule(trans)   \
        (((struct nft_trans_rule *)trans->data)->rule)
#define nft_trans_rule_id(trans)        \
        (((struct nft_trans_rule *)trans->data)->rule_id)

struct nft_trans_set {
        struct nft_set                  *set;
        u32                             set_id;
};

#define nft_trans_set(trans)    \
        (((struct nft_trans_set *)trans->data)->set)
#define nft_trans_set_id(trans) \
        (((struct nft_trans_set *)trans->data)->set_id)

struct nft_trans_chain {
        bool                            update;
        char                            *name;
        struct nft_stats __percpu       *stats;
        u8                              policy;
};

#define nft_trans_chain_update(trans)   \
        (((struct nft_trans_chain *)trans->data)->update)
#define nft_trans_chain_name(trans)     \
        (((struct nft_trans_chain *)trans->data)->name)
#define nft_trans_chain_stats(trans)    \
        (((struct nft_trans_chain *)trans->data)->stats)
#define nft_trans_chain_policy(trans)   \
        (((struct nft_trans_chain *)trans->data)->policy)

struct nft_trans_table {
        bool                            update;
        bool                            enable;
};

#define nft_trans_table_update(trans)   \
        (((struct nft_trans_table *)trans->data)->update)
#define nft_trans_table_enable(trans)   \
        (((struct nft_trans_table *)trans->data)->enable)

struct nft_trans_elem {
        struct nft_set                  *set;
        struct nft_set_elem             elem;
};

#define nft_trans_elem_set(trans)       \
        (((struct nft_trans_elem *)trans->data)->set)
#define nft_trans_elem(trans)   \
        (((struct nft_trans_elem *)trans->data)->elem)

struct nft_trans_obj {
        struct nft_object               *obj;
};

#define nft_trans_obj(trans)    \
        (((struct nft_trans_obj *)trans->data)->obj)

#endif /* _NET_NF_TABLES_H */