// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the NetFilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Peter Kese <peter.kese@ijs.si>
 *              Julian Anastasov <ja@ssi.bg>
 *
 * Changes:
 */

#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/workqueue.h>
#include <linux/seq_file.h>
#include <linux/slab.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/mutex.h>

#include <net/net_namespace.h>
#include <linux/nsproxy.h>
#include <net/ip.h>
#ifdef CONFIG_IP_VS_IPV6
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif
#include <net/route.h>
#include <net/sock.h>
#include <net/genetlink.h>

#include <linux/uaccess.h>

#include <net/ip_vs.h>

MODULE_ALIAS_GENL_FAMILY(IPVS_GENL_NAME);

/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
static DEFINE_MUTEX(__ip_vs_mutex);

/* sysctl variables */

#ifdef CONFIG_IP_VS_DEBUG
static int sysctl_ip_vs_debug_level = 0;

int ip_vs_get_debug_level(void)
{
        return sysctl_ip_vs_debug_level;
}
#endif


/*  Protos */
static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup);


#ifdef CONFIG_IP_VS_IPV6
/* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */
static bool __ip_vs_addr_is_local_v6(struct net *net,
                                     const struct in6_addr *addr)
{
        struct flowi6 fl6 = {
                .daddr = *addr,
        };
        struct dst_entry *dst = ip6_route_output(net, NULL, &fl6);
        bool is_local;

        is_local = !dst->error && dst->dev && (dst->dev->flags & IFF_LOOPBACK);

        dst_release(dst);
        return is_local;
}
#endif

#ifdef CONFIG_SYSCTL
/*
 *      update_defense_level is called from keventd and from sysctl,
 *      so it needs to protect itself from softirqs
 */
static void update_defense_level(struct netns_ipvs *ipvs)
{
        struct sysinfo i;
        int availmem;
        int nomem;
        int to_change = -1;

        /* we only count free and buffered memory (in pages) */
        si_meminfo(&i);
        availmem = i.freeram + i.bufferram;
        /* however in linux 2.5 the i.bufferram is total page cache size,
           we need adjust it */
        /* si_swapinfo(&i); */
        /* availmem = availmem - (i.totalswap - i.freeswap); */

        nomem = (availmem < ipvs->sysctl_amemthresh);

        local_bh_disable();

        /* drop_entry */
        spin_lock(&ipvs->dropentry_lock);
        switch (ipvs->sysctl_drop_entry) {
        case 0:
                atomic_set(&ipvs->dropentry, 0);
                break;
        case 1:
                if (nomem) {
                        atomic_set(&ipvs->dropentry, 1);
                        ipvs->sysctl_drop_entry = 2;
                } else {
                        atomic_set(&ipvs->dropentry, 0);
                }
                break;
        case 2:
                if (nomem) {
                        atomic_set(&ipvs->dropentry, 1);
                } else {
                        atomic_set(&ipvs->dropentry, 0);
                        ipvs->sysctl_drop_entry = 1;
                }
                break;
        case 3:
                atomic_set(&ipvs->dropentry, 1);
                break;
        }
        spin_unlock(&ipvs->dropentry_lock);

        /* drop_packet */
        spin_lock(&ipvs->droppacket_lock);
        switch (ipvs->sysctl_drop_packet) {
        case 0:
                ipvs->drop_rate = 0;
                break;
        case 1:
                if (nomem) {
                        ipvs->drop_rate = ipvs->drop_counter
                                = ipvs->sysctl_amemthresh /
                                (ipvs->sysctl_amemthresh-availmem);
                        ipvs->sysctl_drop_packet = 2;
                } else {
                        ipvs->drop_rate = 0;
                }
                break;
        case 2:
                if (nomem) {
                        ipvs->drop_rate = ipvs->drop_counter
                                = ipvs->sysctl_amemthresh /
                                (ipvs->sysctl_amemthresh-availmem);
                } else {
                        ipvs->drop_rate = 0;
                        ipvs->sysctl_drop_packet = 1;
                }
                break;
        case 3:
                ipvs->drop_rate = ipvs->sysctl_am_droprate;
                break;
        }
        spin_unlock(&ipvs->droppacket_lock);

        /* secure_tcp */
        spin_lock(&ipvs->securetcp_lock);
        switch (ipvs->sysctl_secure_tcp) {
        case 0:
                if (ipvs->old_secure_tcp >= 2)
                        to_change = 0;
                break;
        case 1:
                if (nomem) {
                        if (ipvs->old_secure_tcp < 2)
                                to_change = 1;
                        ipvs->sysctl_secure_tcp = 2;
                } else {
                        if (ipvs->old_secure_tcp >= 2)
                                to_change = 0;
                }
                break;
        case 2:
                if (nomem) {
                        if (ipvs->old_secure_tcp < 2)
                                to_change = 1;
                } else {
                        if (ipvs->old_secure_tcp >= 2)
                                to_change = 0;
                        ipvs->sysctl_secure_tcp = 1;
                }
                break;
        case 3:
                if (ipvs->old_secure_tcp < 2)
                        to_change = 1;
                break;
        }
        ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp;
        if (to_change >= 0)
                ip_vs_protocol_timeout_change(ipvs,
                                              ipvs->sysctl_secure_tcp > 1);
        spin_unlock(&ipvs->securetcp_lock);

        local_bh_enable();
}

/* Handler for delayed work for expiring no
 * destination connections
 */
static void expire_nodest_conn_handler(struct work_struct *work)
{
        struct netns_ipvs *ipvs;

        ipvs = container_of(work, struct netns_ipvs,
                            expire_nodest_conn_work.work);
        ip_vs_expire_nodest_conn_flush(ipvs);
}

/*
 *      Timer for checking the defense
 */
#define DEFENSE_TIMER_PERIOD    1*HZ

static void defense_work_handler(struct work_struct *work)
{
        struct netns_ipvs *ipvs =
                container_of(work, struct netns_ipvs, defense_work.work);

        update_defense_level(ipvs);
        if (atomic_read(&ipvs->dropentry))
                ip_vs_random_dropentry(ipvs);
        queue_delayed_work(system_long_wq, &ipvs->defense_work,
                           DEFENSE_TIMER_PERIOD);
}
#endif

int
ip_vs_use_count_inc(void)
{
        return try_module_get(THIS_MODULE);
}

void
ip_vs_use_count_dec(void)
{
        module_put(THIS_MODULE);
}


/*
 *      Hash table: for virtual service lookups
 */
#define IP_VS_SVC_TAB_BITS 8
#define IP_VS_SVC_TAB_SIZE (1 << IP_VS_SVC_TAB_BITS)
#define IP_VS_SVC_TAB_MASK (IP_VS_SVC_TAB_SIZE - 1)

/* the service table hashed by <protocol, addr, port> */
static struct hlist_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
/* the service table hashed by fwmark */
static struct hlist_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];


/*
 *      Returns hash value for virtual service
 */
static inline unsigned int
ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto,
                  const union nf_inet_addr *addr, __be16 port)
{
        unsigned int porth = ntohs(port);
        __be32 addr_fold = addr->ip;
        __u32 ahash;

#ifdef CONFIG_IP_VS_IPV6
        if (af == AF_INET6)
                addr_fold = addr->ip6[0]^addr->ip6[1]^
                            addr->ip6[2]^addr->ip6[3];
#endif
        ahash = ntohl(addr_fold);
        ahash ^= ((size_t) ipvs >> 8);

        return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) &
               IP_VS_SVC_TAB_MASK;
}

/*
 *      Returns hash value of fwmark for virtual service lookup
 */
static inline unsigned int ip_vs_svc_fwm_hashkey(struct netns_ipvs *ipvs, __u32 fwmark)
{
        return (((size_t)ipvs>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK;
}

/*
 *      Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port>
 *      or in the ip_vs_svc_fwm_table by fwmark.
 *      Should be called with locked tables.
 */
static int ip_vs_svc_hash(struct ip_vs_service *svc)
{
        unsigned int hash;

        if (svc->flags & IP_VS_SVC_F_HASHED) {
                pr_err("%s(): request for already hashed, called from %pS\n",
                       __func__, __builtin_return_address(0));
                return 0;
        }

        if (svc->fwmark == 0) {
                /*
                 *  Hash it by <netns,protocol,addr,port> in ip_vs_svc_table
                 */
                hash = ip_vs_svc_hashkey(svc->ipvs, svc->af, svc->protocol,
                                         &svc->addr, svc->port);
                hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]);
        } else {
                /*
                 *  Hash it by fwmark in svc_fwm_table
                 */
                hash = ip_vs_svc_fwm_hashkey(svc->ipvs, svc->fwmark);
                hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
        }

        svc->flags |= IP_VS_SVC_F_HASHED;
        /* increase its refcnt because it is referenced by the svc table */
        atomic_inc(&svc->refcnt);
        return 1;
}


/*
 *      Unhashes a service from svc_table / svc_fwm_table.
 *      Should be called with locked tables.
 */
static int ip_vs_svc_unhash(struct ip_vs_service *svc)
{
        if (!(svc->flags & IP_VS_SVC_F_HASHED)) {
                pr_err("%s(): request for unhash flagged, called from %pS\n",
                       __func__, __builtin_return_address(0));
                return 0;
        }

        if (svc->fwmark == 0) {
                /* Remove it from the svc_table table */
                hlist_del_rcu(&svc->s_list);
        } else {
                /* Remove it from the svc_fwm_table table */
                hlist_del_rcu(&svc->f_list);
        }

        svc->flags &= ~IP_VS_SVC_F_HASHED;
        atomic_dec(&svc->refcnt);
        return 1;
}


/*
 *      Get service by {netns, proto,addr,port} in the service table.
 */
static inline struct ip_vs_service *
__ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u16 protocol,
                     const union nf_inet_addr *vaddr, __be16 vport)
{
        unsigned int hash;
        struct ip_vs_service *svc;

        /* Check for "full" addressed entries */
        hash = ip_vs_svc_hashkey(ipvs, af, protocol, vaddr, vport);

        hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[hash], s_list) {
                if ((svc->af == af)
                    && ip_vs_addr_equal(af, &svc->addr, vaddr)
                    && (svc->port == vport)
                    && (svc->protocol == protocol)
                    && (svc->ipvs == ipvs)) {
                        /* HIT */
                        return svc;
                }
        }

        return NULL;
}


/*
 *      Get service by {fwmark} in the service table.
 */
static inline struct ip_vs_service *
__ip_vs_svc_fwm_find(struct netns_ipvs *ipvs, int af, __u32 fwmark)
{
        unsigned int hash;
        struct ip_vs_service *svc;

        /* Check for fwmark addressed entries */
        hash = ip_vs_svc_fwm_hashkey(ipvs, fwmark);

        hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) {
                if (svc->fwmark == fwmark && svc->af == af
                    && (svc->ipvs == ipvs)) {
                        /* HIT */
                        return svc;
                }
        }

        return NULL;
}

/* Find service, called under RCU lock */
struct ip_vs_service *
ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol,
                   const union nf_inet_addr *vaddr, __be16 vport)
{
        struct ip_vs_service *svc;

        /*
         *      Check the table hashed by fwmark first
         */
        if (fwmark) {
                svc = __ip_vs_svc_fwm_find(ipvs, af, fwmark);
                if (svc)
                        goto out;
        }

        /*
         *      Check the table hashed by <protocol,addr,port>
         *      for "full" addressed entries
         */
        svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, vport);

        if (!svc && protocol == IPPROTO_TCP &&
            atomic_read(&ipvs->ftpsvc_counter) &&
            (vport == FTPDATA || !inet_port_requires_bind_service(ipvs->net, ntohs(vport)))) {
                /*
                 * Check if ftp service entry exists, the packet
                 * might belong to FTP data connections.
                 */
                svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, FTPPORT);
        }

        if (svc == NULL
            && atomic_read(&ipvs->nullsvc_counter)) {
                /*
                 * Check if the catch-all port (port zero) exists
                 */
                svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, 0);
        }

  out:
        IP_VS_DBG_BUF(9, "lookup service: fwm %u %s %s:%u %s\n",
                      fwmark, ip_vs_proto_name(protocol),
                      IP_VS_DBG_ADDR(af, vaddr), ntohs(vport),
                      svc ? "hit" : "not hit");

        return svc;
}


static inline void
__ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc)
{
        atomic_inc(&svc->refcnt);
        rcu_assign_pointer(dest->svc, svc);
}

static void ip_vs_service_free(struct ip_vs_service *svc)
{
        free_percpu(svc->stats.cpustats);
        kfree(svc);
}

static void ip_vs_service_rcu_free(struct rcu_head *head)
{
        struct ip_vs_service *svc;

        svc = container_of(head, struct ip_vs_service, rcu_head);
        ip_vs_service_free(svc);
}

static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay)
{
        if (atomic_dec_and_test(&svc->refcnt)) {
                IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n",
                              svc->fwmark,
                              IP_VS_DBG_ADDR(svc->af, &svc->addr),
                              ntohs(svc->port));
                if (do_delay)
                        call_rcu(&svc->rcu_head, ip_vs_service_rcu_free);
                else
                        ip_vs_service_free(svc);
        }
}


/*
 *      Returns hash value for real service
 */
static inline unsigned int ip_vs_rs_hashkey(int af,
                                            const union nf_inet_addr *addr,
                                            __be16 port)
{
        unsigned int porth = ntohs(port);
        __be32 addr_fold = addr->ip;

#ifdef CONFIG_IP_VS_IPV6
        if (af == AF_INET6)
                addr_fold = addr->ip6[0]^addr->ip6[1]^
                            addr->ip6[2]^addr->ip6[3];
#endif

        return (ntohl(addr_fold)^(porth>>IP_VS_RTAB_BITS)^porth)
                & IP_VS_RTAB_MASK;
}

/* Hash ip_vs_dest in rs_table by <proto,addr,port>. */
static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
{
        unsigned int hash;
        __be16 port;

        if (dest->in_rs_table)
                return;

        switch (IP_VS_DFWD_METHOD(dest)) {
        case IP_VS_CONN_F_MASQ:
                port = dest->port;
                break;
        case IP_VS_CONN_F_TUNNEL:
                switch (dest->tun_type) {
                case IP_VS_CONN_F_TUNNEL_TYPE_GUE:
                        port = dest->tun_port;
                        break;
                case IP_VS_CONN_F_TUNNEL_TYPE_IPIP:
                case IP_VS_CONN_F_TUNNEL_TYPE_GRE:
                        port = 0;
                        break;
                default:
                        return;
                }
                break;
        default:
                return;
        }

        /*
         *      Hash by proto,addr,port,
         *      which are the parameters of the real service.
         */
        hash = ip_vs_rs_hashkey(dest->af, &dest->addr, port);

        hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]);
        dest->in_rs_table = 1;
}

/* Unhash ip_vs_dest from rs_table. */
static void ip_vs_rs_unhash(struct ip_vs_dest *dest)
{
        /*
         * Remove it from the rs_table table.
         */
        if (dest->in_rs_table) {
                hlist_del_rcu(&dest->d_list);
                dest->in_rs_table = 0;
        }
}

/* Check if real service by <proto,addr,port> is present */
bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
                            const union nf_inet_addr *daddr, __be16 dport)
{
        unsigned int hash;
        struct ip_vs_dest *dest;

        /* Check for "full" addressed entries */
        hash = ip_vs_rs_hashkey(af, daddr, dport);

        hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
                if (dest->port == dport &&
                    dest->af == af &&
                    ip_vs_addr_equal(af, &dest->addr, daddr) &&
                    (dest->protocol == protocol || dest->vfwmark) &&
                    IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) {
                        /* HIT */
                        return true;
                }
        }

        return false;
}

/* Find real service record by <proto,addr,port>.
 * In case of multiple records with the same <proto,addr,port>, only
 * the first found record is returned.
 *
 * To be called under RCU lock.
 */
struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af,
                                           __u16 protocol,
                                           const union nf_inet_addr *daddr,
                                           __be16 dport)
{
        unsigned int hash;
        struct ip_vs_dest *dest;

        /* Check for "full" addressed entries */
        hash = ip_vs_rs_hashkey(af, daddr, dport);

        hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
                if (dest->port == dport &&
                    dest->af == af &&
                    ip_vs_addr_equal(af, &dest->addr, daddr) &&
                    (dest->protocol == protocol || dest->vfwmark) &&
                    IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) {
                        /* HIT */
                        return dest;
                }
        }

        return NULL;
}

/* Find real service record by <af,addr,tun_port>.
 * In case of multiple records with the same <af,addr,tun_port>, only
 * the first found record is returned.
 *
 * To be called under RCU lock.
 */
struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af,
                                     const union nf_inet_addr *daddr,
                                     __be16 tun_port)
{
        struct ip_vs_dest *dest;
        unsigned int hash;

        /* Check for "full" addressed entries */
        hash = ip_vs_rs_hashkey(af, daddr, tun_port);

        hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
                if (dest->tun_port == tun_port &&
                    dest->af == af &&
                    ip_vs_addr_equal(af, &dest->addr, daddr) &&
                    IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_TUNNEL) {
                        /* HIT */
                        return dest;
                }
        }

        return NULL;
}

/* Lookup destination by {addr,port} in the given service
 * Called under RCU lock.
 */
static struct ip_vs_dest *
ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af,
                  const union nf_inet_addr *daddr, __be16 dport)
{
        struct ip_vs_dest *dest;

        /*
         * Find the destination for the given service
         */
        list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
                if ((dest->af == dest_af) &&
                    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
                    (dest->port == dport)) {
                        /* HIT */
                        return dest;
                }
        }

        return NULL;
}

/*
 * Find destination by {daddr,dport,vaddr,protocol}
 * Created to be used in ip_vs_process_message() in
 * the backup synchronization daemon. It finds the
 * destination to be bound to the received connection
 * on the backup.
 * Called under RCU lock, no refcnt is returned.
 */
struct ip_vs_dest *ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af,
                                   const union nf_inet_addr *daddr,
                                   __be16 dport,
                                   const union nf_inet_addr *vaddr,
                                   __be16 vport, __u16 protocol, __u32 fwmark,
                                   __u32 flags)
{
        struct ip_vs_dest *dest;
        struct ip_vs_service *svc;
        __be16 port = dport;

        svc = ip_vs_service_find(ipvs, svc_af, fwmark, protocol, vaddr, vport);
        if (!svc)
                return NULL;
        if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
                port = 0;
        dest = ip_vs_lookup_dest(svc, dest_af, daddr, port);
        if (!dest)
                dest = ip_vs_lookup_dest(svc, dest_af, daddr, port ^ dport);
        return dest;
}

void ip_vs_dest_dst_rcu_free(struct rcu_head *head)
{
        struct ip_vs_dest_dst *dest_dst = container_of(head,
                                                       struct ip_vs_dest_dst,
                                                       rcu_head);

        dst_release(dest_dst->dst_cache);
        kfree(dest_dst);
}

/* Release dest_dst and dst_cache for dest in user context */
static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest)
{
        struct ip_vs_dest_dst *old;

        old = rcu_dereference_protected(dest->dest_dst, 1);
        if (old) {
                RCU_INIT_POINTER(dest->dest_dst, NULL);
                call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
        }
}

/*
 *  Lookup dest by {svc,addr,port} in the destination trash.
 *  The destination trash is used to hold the destinations that are removed
 *  from the service table but are still referenced by some conn entries.
 *  The reason to add the destination trash is when the dest is temporary
 *  down (either by administrator or by monitor program), the dest can be
 *  picked back from the trash, the remaining connections to the dest can
 *  continue, and the counting information of the dest is also useful for
 *  scheduling.
 */
static struct ip_vs_dest *
ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af,
                     const union nf_inet_addr *daddr, __be16 dport)
{
        struct ip_vs_dest *dest;
        struct netns_ipvs *ipvs = svc->ipvs;

        /*
         * Find the destination in trash
         */
        spin_lock_bh(&ipvs->dest_trash_lock);
        list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
                IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
                              "dest->refcnt=%d\n",
                              dest->vfwmark,
                              IP_VS_DBG_ADDR(dest->af, &dest->addr),
                              ntohs(dest->port),
                              refcount_read(&dest->refcnt));
                if (dest->af == dest_af &&
                    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
                    dest->port == dport &&
                    dest->vfwmark == svc->fwmark &&
                    dest->protocol == svc->protocol &&
                    (svc->fwmark ||
                     (ip_vs_addr_equal(svc->af, &dest->vaddr, &svc->addr) &&
                      dest->vport == svc->port))) {
                        /* HIT */
                        list_del(&dest->t_list);
                        goto out;
                }
        }

        dest = NULL;

out:
        spin_unlock_bh(&ipvs->dest_trash_lock);

        return dest;
}

static void ip_vs_dest_free(struct ip_vs_dest *dest)
{
        struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1);

        __ip_vs_dst_cache_reset(dest);
        __ip_vs_svc_put(svc, false);
        free_percpu(dest->stats.cpustats);
        ip_vs_dest_put_and_free(dest);
}

/*
 *  Clean up all the destinations in the trash
 *  Called by the ip_vs_control_cleanup()
 *
 *  When the ip_vs_control_clearup is activated by ipvs module exit,
 *  the service tables must have been flushed and all the connections
 *  are expired, and the refcnt of each destination in the trash must
 *  be 1, so we simply release them here.
 */
static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs)
{
        struct ip_vs_dest *dest, *nxt;

        del_timer_sync(&ipvs->dest_trash_timer);
        /* No need to use dest_trash_lock */
        list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, t_list) {
                list_del(&dest->t_list);
                ip_vs_dest_free(dest);
        }
}

static void
ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src)
{
#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c

        spin_lock_bh(&src->lock);

        IP_VS_SHOW_STATS_COUNTER(conns);
        IP_VS_SHOW_STATS_COUNTER(inpkts);
        IP_VS_SHOW_STATS_COUNTER(outpkts);
        IP_VS_SHOW_STATS_COUNTER(inbytes);
        IP_VS_SHOW_STATS_COUNTER(outbytes);

        ip_vs_read_estimator(dst, src);

        spin_unlock_bh(&src->lock);
}

static void
ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src)
{
        dst->conns = (u32)src->conns;
        dst->inpkts = (u32)src->inpkts;
        dst->outpkts = (u32)src->outpkts;
        dst->inbytes = src->inbytes;
        dst->outbytes = src->outbytes;
        dst->cps = (u32)src->cps;
        dst->inpps = (u32)src->inpps;
        dst->outpps = (u32)src->outpps;
        dst->inbps = (u32)src->inbps;
        dst->outbps = (u32)src->outbps;
}

static void
ip_vs_zero_stats(struct ip_vs_stats *stats)
{
        spin_lock_bh(&stats->lock);

        /* get current counters as zero point, rates are zeroed */

#define IP_VS_ZERO_STATS_COUNTER(c) stats->kstats0.c = stats->kstats.c

        IP_VS_ZERO_STATS_COUNTER(conns);
        IP_VS_ZERO_STATS_COUNTER(inpkts);
        IP_VS_ZERO_STATS_COUNTER(outpkts);
        IP_VS_ZERO_STATS_COUNTER(inbytes);
        IP_VS_ZERO_STATS_COUNTER(outbytes);

        ip_vs_zero_estimator(stats);

        spin_unlock_bh(&stats->lock);
}

/*
 *      Update a destination in the given service
 */
static void
__ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
                    struct ip_vs_dest_user_kern *udest, int add)
{
        struct netns_ipvs *ipvs = svc->ipvs;
        struct ip_vs_service *old_svc;
        struct ip_vs_scheduler *sched;
        int conn_flags;

        /* We cannot modify an address and change the address family */
        BUG_ON(!add && udest->af != dest->af);

        if (add && udest->af != svc->af)
                ipvs->mixed_address_family_dests++;

        /* keep the last_weight with latest non-0 weight */
        if (add || udest->weight != 0)
                atomic_set(&dest->last_weight, udest->weight);

        /* set the weight and the flags */
        atomic_set(&dest->weight, udest->weight);
        conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
        conn_flags |= IP_VS_CONN_F_INACTIVE;

        /* Need to rehash? */
        if ((udest->conn_flags & IP_VS_CONN_F_FWD_MASK) !=
            IP_VS_DFWD_METHOD(dest) ||
            udest->tun_type != dest->tun_type ||
            udest->tun_port != dest->tun_port)
                ip_vs_rs_unhash(dest);

        /* set the tunnel info */
        dest->tun_type = udest->tun_type;
        dest->tun_port = udest->tun_port;
        dest->tun_flags = udest->tun_flags;

        /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
        if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) {
                conn_flags |= IP_VS_CONN_F_NOOUTPUT;
        } else {
                /* FTP-NAT requires conntrack for mangling */
                if (svc->port == FTPPORT)
                        ip_vs_register_conntrack(svc);
        }
        atomic_set(&dest->conn_flags, conn_flags);
        /* Put the real service in rs_table if not present. */
        ip_vs_rs_hash(ipvs, dest);

        /* bind the service */
        old_svc = rcu_dereference_protected(dest->svc, 1);
        if (!old_svc) {
                __ip_vs_bind_svc(dest, svc);
        } else {
                if (old_svc != svc) {
                        ip_vs_zero_stats(&dest->stats);
                        __ip_vs_bind_svc(dest, svc);
                        __ip_vs_svc_put(old_svc, true);
                }
        }

        /* set the dest status flags */
        dest->flags |= IP_VS_DEST_F_AVAILABLE;

        if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold)
                dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
        dest->u_threshold = udest->u_threshold;
        dest->l_threshold = udest->l_threshold;

        dest->af = udest->af;

        spin_lock_bh(&dest->dst_lock);
        __ip_vs_dst_cache_reset(dest);
        spin_unlock_bh(&dest->dst_lock);

        if (add) {
                ip_vs_start_estimator(svc->ipvs, &dest->stats);
                list_add_rcu(&dest->n_list, &svc->destinations);
                svc->num_dests++;
                sched = rcu_dereference_protected(svc->scheduler, 1);
                if (sched && sched->add_dest)
                        sched->add_dest(svc, dest);
        } else {
                sched = rcu_dereference_protected(svc->scheduler, 1);
                if (sched && sched->upd_dest)
                        sched->upd_dest(svc, dest);
        }
}


/*
 *      Create a destination for the given service
 */
static int
ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
               struct ip_vs_dest **dest_p)
{
        struct ip_vs_dest *dest;
        unsigned int atype, i;

        EnterFunction(2);

#ifdef CONFIG_IP_VS_IPV6
        if (udest->af == AF_INET6) {
                int ret;

                atype = ipv6_addr_type(&udest->addr.in6);
                if ((!(atype & IPV6_ADDR_UNICAST) ||
                        atype & IPV6_ADDR_LINKLOCAL) &&
                        !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6))
                        return -EINVAL;

                ret = nf_defrag_ipv6_enable(svc->ipvs->net);
                if (ret)
                        return ret;
        } else
#endif
        {
                atype = inet_addr_type(svc->ipvs->net, udest->addr.ip);
                if (atype != RTN_LOCAL && atype != RTN_UNICAST)
                        return -EINVAL;
        }

        dest = kzalloc(sizeof(struct ip_vs_dest), GFP_KERNEL);
        if (dest == NULL)
                return -ENOMEM;

        dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
        if (!dest->stats.cpustats)
                goto err_alloc;

        for_each_possible_cpu(i) {

                struct ip_vs_cpu_stats *ip_vs_dest_stats;
                ip_vs_dest_stats = per_cpu_ptr(dest->stats.cpustats, i);
                u64_stats_init(&ip_vs_dest_stats->syncp);
        }

        dest->af = udest->af;
        dest->protocol = svc->protocol;
        dest->vaddr = svc->addr;
        dest->vport = svc->port;
        dest->vfwmark = svc->fwmark;
        ip_vs_addr_copy(udest->af, &dest->addr, &udest->addr);
        dest->port = udest->port;

        atomic_set(&dest->activeconns, 0);
        atomic_set(&dest->inactconns, 0);
        atomic_set(&dest->persistconns, 0);
        refcount_set(&dest->refcnt, 1);

        INIT_HLIST_NODE(&dest->d_list);
        spin_lock_init(&dest->dst_lock);
        spin_lock_init(&dest->stats.lock);
        __ip_vs_update_dest(svc, dest, udest, 1);

        *dest_p = dest;

        LeaveFunction(2);
        return 0;

err_alloc:
        kfree(dest);
        return -ENOMEM;
}


/*
 *      Add a destination into an existing service
 */
static int
ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
{
        struct ip_vs_dest *dest;
        union nf_inet_addr daddr;
        __be16 dport = udest->port;
        int ret;

        EnterFunction(2);

        if (udest->weight < 0) {
                pr_err("%s(): server weight less than zero\n", __func__);
                return -ERANGE;
        }

        if (udest->l_threshold > udest->u_threshold) {
                pr_err("%s(): lower threshold is higher than upper threshold\n",
                        __func__);
                return -ERANGE;
        }

        if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
                if (udest->tun_port == 0) {
                        pr_err("%s(): tunnel port is zero\n", __func__);
                        return -EINVAL;
                }
        }

        ip_vs_addr_copy(udest->af, &daddr, &udest->addr);

        /* We use function that requires RCU lock */
        rcu_read_lock();
        dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
        rcu_read_unlock();

        if (dest != NULL) {
                IP_VS_DBG(1, "%s(): dest already exists\n", __func__);
                return -EEXIST;
        }

        /*
         * Check if the dest already exists in the trash and
         * is from the same service
         */
        dest = ip_vs_trash_get_dest(svc, udest->af, &daddr, dport);

        if (dest != NULL) {
                IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
                              "dest->refcnt=%d, service %u/%s:%u\n",
                              IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
                              refcount_read(&dest->refcnt),
                              dest->vfwmark,
                              IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
                              ntohs(dest->vport));

                __ip_vs_update_dest(svc, dest, udest, 1);
                ret = 0;
        } else {
                /*
                 * Allocate and initialize the dest structure
                 */
                ret = ip_vs_new_dest(svc, udest, &dest);
        }
        LeaveFunction(2);

        return ret;
}


/*
 *      Edit a destination in the given service
 */
static int
ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
{
        struct ip_vs_dest *dest;
        union nf_inet_addr daddr;
        __be16 dport = udest->port;

        EnterFunction(2);

        if (udest->weight < 0) {
                pr_err("%s(): server weight less than zero\n", __func__);
                return -ERANGE;
        }

        if (udest->l_threshold > udest->u_threshold) {
                pr_err("%s(): lower threshold is higher than upper threshold\n",
                        __func__);
                return -ERANGE;
        }

        if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
                if (udest->tun_port == 0) {
                        pr_err("%s(): tunnel port is zero\n", __func__);
                        return -EINVAL;
                }
        }

        ip_vs_addr_copy(udest->af, &daddr, &udest->addr);

        /* We use function that requires RCU lock */
        rcu_read_lock();
        dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
        rcu_read_unlock();

        if (dest == NULL) {
                IP_VS_DBG(1, "%s(): dest doesn't exist\n", __func__);
                return -ENOENT;
        }

        __ip_vs_update_dest(svc, dest, udest, 0);
        LeaveFunction(2);

        return 0;
}

/*
 *      Delete a destination (must be already unlinked from the service)
 */
static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest,
                             bool cleanup)
{
        ip_vs_stop_estimator(ipvs, &dest->stats);

        /*
         *  Remove it from the d-linked list with the real services.
         */
        ip_vs_rs_unhash(dest);

        spin_lock_bh(&ipvs->dest_trash_lock);
        IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
                      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
                      refcount_read(&dest->refcnt));
        if (list_empty(&ipvs->dest_trash) && !cleanup)
                mod_timer(&ipvs->dest_trash_timer,
                          jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
        /* dest lives in trash with reference */
        list_add(&dest->t_list, &ipvs->dest_trash);
        dest->idle_start = 0;
        spin_unlock_bh(&ipvs->dest_trash_lock);

        /* Queue up delayed work to expire all no destination connections.
         * No-op when CONFIG_SYSCTL is disabled.
         */
        if (!cleanup)
                ip_vs_enqueue_expire_nodest_conns(ipvs);
}


/*
 *      Unlink a destination from the given service
 */
static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
                                struct ip_vs_dest *dest,
                                int svcupd)
{
        dest->flags &= ~IP_VS_DEST_F_AVAILABLE;

        /*
         *  Remove it from the d-linked destination list.
         */
        list_del_rcu(&dest->n_list);
        svc->num_dests--;

        if (dest->af != svc->af)
                svc->ipvs->mixed_address_family_dests--;

        if (svcupd) {
                struct ip_vs_scheduler *sched;

                sched = rcu_dereference_protected(svc->scheduler, 1);
                if (sched && sched->del_dest)
                        sched->del_dest(svc, dest);
        }
}


/*
 *      Delete a destination server in the given service
 */
static int
ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
{
        struct ip_vs_dest *dest;
        __be16 dport = udest->port;

        EnterFunction(2);

        /* We use function that requires RCU lock */
        rcu_read_lock();
        dest = ip_vs_lookup_dest(svc, udest->af, &udest->addr, dport);
        rcu_read_unlock();

        if (dest == NULL) {
                IP_VS_DBG(1, "%s(): destination not found!\n", __func__);
                return -ENOENT;
        }

        /*
         *      Unlink dest from the service
         */
        __ip_vs_unlink_dest(svc, dest, 1);

        /*
         *      Delete the destination
         */
        __ip_vs_del_dest(svc->ipvs, dest, false);

        LeaveFunction(2);

        return 0;
}

static void ip_vs_dest_trash_expire(struct timer_list *t)
{
        struct netns_ipvs *ipvs = from_timer(ipvs, t, dest_trash_timer);
        struct ip_vs_dest *dest, *next;
        unsigned long now = jiffies;

        spin_lock(&ipvs->dest_trash_lock);
        list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
                if (refcount_read(&dest->refcnt) > 1)
                        continue;
                if (dest->idle_start) {
                        if (time_before(now, dest->idle_start +
                                             IP_VS_DEST_TRASH_PERIOD))
                                continue;
                } else {
                        dest->idle_start = max(1UL, now);
                        continue;
                }
                IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n",
                              dest->vfwmark,
                              IP_VS_DBG_ADDR(dest->af, &dest->addr),
                              ntohs(dest->port));
                list_del(&dest->t_list);
                ip_vs_dest_free(dest);
        }
        if (!list_empty(&ipvs->dest_trash))
                mod_timer(&ipvs->dest_trash_timer,
                          jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
        spin_unlock(&ipvs->dest_trash_lock);
}

/*
 *      Add a service into the service hash table
 */
static int
ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
                  struct ip_vs_service **svc_p)
{
        int ret = 0, i;
        struct ip_vs_scheduler *sched = NULL;
        struct ip_vs_pe *pe = NULL;
        struct ip_vs_service *svc = NULL;
        int ret_hooks = -1;

        /* increase the module use count */
        if (!ip_vs_use_count_inc())
                return -ENOPROTOOPT;

        /* Lookup the scheduler by 'u->sched_name' */
        if (strcmp(u->sched_name, "none")) {
                sched = ip_vs_scheduler_get(u->sched_name);
                if (!sched) {
                        pr_info("Scheduler module ip_vs_%s not found\n",
                                u->sched_name);
                        ret = -ENOENT;
                        goto out_err;
                }
        }

        if (u->pe_name && *u->pe_name) {
                pe = ip_vs_pe_getbyname(u->pe_name);
                if (pe == NULL) {
                        pr_info("persistence engine module ip_vs_pe_%s "
                                "not found\n", u->pe_name);
                        ret = -ENOENT;
                        goto out_err;
                }
        }

#ifdef CONFIG_IP_VS_IPV6
        if (u->af == AF_INET6) {
                __u32 plen = (__force __u32) u->netmask;

                if (plen < 1 || plen > 128) {
                        ret = -EINVAL;
                        goto out_err;
                }

                ret = nf_defrag_ipv6_enable(ipvs->net);
                if (ret)
                        goto out_err;
        }
#endif

        if ((u->af == AF_INET && !ipvs->num_services) ||
            (u->af == AF_INET6 && !ipvs->num_services6)) {
                ret = ip_vs_register_hooks(ipvs, u->af);
                if (ret < 0)
                        goto out_err;
                ret_hooks = ret;
        }

        svc = kzalloc(sizeof(struct ip_vs_service), GFP_KERNEL);
        if (svc == NULL) {
                IP_VS_DBG(1, "%s(): no memory\n", __func__);
                ret = -ENOMEM;
                goto out_err;
        }
        svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
        if (!svc->stats.cpustats) {
                ret = -ENOMEM;
                goto out_err;
        }

        for_each_possible_cpu(i) {
                struct ip_vs_cpu_stats *ip_vs_stats;
                ip_vs_stats = per_cpu_ptr(svc->stats.cpustats, i);
                u64_stats_init(&ip_vs_stats->syncp);
        }


        /* I'm the first user of the service */
        atomic_set(&svc->refcnt, 0);

        svc->af = u->af;
        svc->protocol = u->protocol;
        ip_vs_addr_copy(svc->af, &svc->addr, &u->addr);
        svc->port = u->port;
        svc->fwmark = u->fwmark;
        svc->flags = u->flags & ~IP_VS_SVC_F_HASHED;
        svc->timeout = u->timeout * HZ;
        svc->netmask = u->netmask;
        svc->ipvs = ipvs;

        INIT_LIST_HEAD(&svc->destinations);
        spin_lock_init(&svc->sched_lock);
        spin_lock_init(&svc->stats.lock);

        /* Bind the scheduler */
        if (sched) {
                ret = ip_vs_bind_scheduler(svc, sched);
                if (ret)
                        goto out_err;
                sched = NULL;
        }

        /* Bind the ct retriever */
        RCU_INIT_POINTER(svc->pe, pe);
        pe = NULL;

        /* Update the virtual service counters */
        if (svc->port == FTPPORT)
                atomic_inc(&ipvs->ftpsvc_counter);
        else if (svc->port == 0)
                atomic_inc(&ipvs->nullsvc_counter);
        if (svc->pe && svc->pe->conn_out)
                atomic_inc(&ipvs->conn_out_counter);

        ip_vs_start_estimator(ipvs, &svc->stats);

        /* Count only IPv4 services for old get/setsockopt interface */
        if (svc->af == AF_INET)
                ipvs->num_services++;
        else if (svc->af == AF_INET6)
                ipvs->num_services6++;

        /* Hash the service into the service table */
        ip_vs_svc_hash(svc);

        *svc_p = svc;
        /* Now there is a service - full throttle */
        ipvs->enable = 1;
        return 0;


 out_err:
        if (ret_hooks >= 0)
                ip_vs_unregister_hooks(ipvs, u->af);
        if (svc != NULL) {
                ip_vs_unbind_scheduler(svc, sched);
                ip_vs_service_free(svc);
        }
        ip_vs_scheduler_put(sched);
        ip_vs_pe_put(pe);

        /* decrease the module use count */
        ip_vs_use_count_dec();

        return ret;
}


/*
 *      Edit a service and bind it with a new scheduler
 */
static int
ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
{
        struct ip_vs_scheduler *sched = NULL, *old_sched;
        struct ip_vs_pe *pe = NULL, *old_pe = NULL;
        int ret = 0;
        bool new_pe_conn_out, old_pe_conn_out;

        /*
         * Lookup the scheduler, by 'u->sched_name'
         */
        if (strcmp(u->sched_name, "none")) {
                sched = ip_vs_scheduler_get(u->sched_name);
                if (!sched) {
                        pr_info("Scheduler module ip_vs_%s not found\n",
                                u->sched_name);
                        return -ENOENT;
                }
        }
        old_sched = sched;

        if (u->pe_name && *u->pe_name) {
                pe = ip_vs_pe_getbyname(u->pe_name);
                if (pe == NULL) {
                        pr_info("persistence engine module ip_vs_pe_%s "
                                "not found\n", u->pe_name);
                        ret = -ENOENT;
                        goto out;
                }
                old_pe = pe;
        }

#ifdef CONFIG_IP_VS_IPV6
        if (u->af == AF_INET6) {
                __u32 plen = (__force __u32) u->netmask;

                if (plen < 1 || plen > 128) {
                        ret = -EINVAL;
                        goto out;
                }
        }
#endif

        old_sched = rcu_dereference_protected(svc->scheduler, 1);
        if (sched != old_sched) {
                if (old_sched) {
                        ip_vs_unbind_scheduler(svc, old_sched);
                        RCU_INIT_POINTER(svc->scheduler, NULL);
                        /* Wait all svc->sched_data users */
                        synchronize_rcu();
                }
                /* Bind the new scheduler */
                if (sched) {
                        ret = ip_vs_bind_scheduler(svc, sched);
                        if (ret) {
                                ip_vs_scheduler_put(sched);
                                goto out;
                        }
                }
        }

        /*
         * Set the flags and timeout value
         */
        svc->flags = u->flags | IP_VS_SVC_F_HASHED;
        svc->timeout = u->timeout * HZ;
        svc->netmask = u->netmask;

        old_pe = rcu_dereference_protected(svc->pe, 1);
        if (pe != old_pe) {
                rcu_assign_pointer(svc->pe, pe);
                /* check for optional methods in new pe */
                new_pe_conn_out = (pe && pe->conn_out) ? true : false;
                old_pe_conn_out = (old_pe && old_pe->conn_out) ? true : false;
                if (new_pe_conn_out && !old_pe_conn_out)
                        atomic_inc(&svc->ipvs->conn_out_counter);
                if (old_pe_conn_out && !new_pe_conn_out)
                        atomic_dec(&svc->ipvs->conn_out_counter);
        }

out:
        ip_vs_scheduler_put(old_sched);
        ip_vs_pe_put(old_pe);
        return ret;
}

/*
 *      Delete a service from the service list
 *      - The service must be unlinked, unlocked and not referenced!
 *      - We are called under _bh lock
 */
static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
{
        struct ip_vs_dest *dest, *nxt;
        struct ip_vs_scheduler *old_sched;
        struct ip_vs_pe *old_pe;
        struct netns_ipvs *ipvs = svc->ipvs;

        if (svc->af == AF_INET) {
                ipvs->num_services--;
                if (!ipvs->num_services)
                        ip_vs_unregister_hooks(ipvs, svc->af);
        } else if (svc->af == AF_INET6) {
                ipvs->num_services6--;
                if (!ipvs->num_services6)
                        ip_vs_unregister_hooks(ipvs, svc->af);
        }

        ip_vs_stop_estimator(svc->ipvs, &svc->stats);

        /* Unbind scheduler */
        old_sched = rcu_dereference_protected(svc->scheduler, 1);
        ip_vs_unbind_scheduler(svc, old_sched);
        ip_vs_scheduler_put(old_sched);

        /* Unbind persistence engine, keep svc->pe */
        old_pe = rcu_dereference_protected(svc->pe, 1);
        if (old_pe && old_pe->conn_out)
                atomic_dec(&ipvs->conn_out_counter);
        ip_vs_pe_put(old_pe);

        /*
         *    Unlink the whole destination list
         */
        list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
                __ip_vs_unlink_dest(svc, dest, 0);
                __ip_vs_del_dest(svc->ipvs, dest, cleanup);
        }

        /*
         *    Update the virtual service counters
         */
        if (svc->port == FTPPORT)
                atomic_dec(&ipvs->ftpsvc_counter);
        else if (svc->port == 0)
                atomic_dec(&ipvs->nullsvc_counter);

        /*
         *    Free the service if nobody refers to it
         */
        __ip_vs_svc_put(svc, true);

        /* decrease the module use count */
        ip_vs_use_count_dec();
}

/*
 * Unlink a service from list and try to delete it if its refcnt reached 0
 */
static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup)
{
        ip_vs_unregister_conntrack(svc);
        /* Hold svc to avoid double release from dest_trash */
        atomic_inc(&svc->refcnt);
        /*
         * Unhash it from the service table
         */
        ip_vs_svc_unhash(svc);

        __ip_vs_del_service(svc, cleanup);
}

/*
 *      Delete a service from the service list
 */
static int ip_vs_del_service(struct ip_vs_service *svc)
{
        if (svc == NULL)
                return -EEXIST;
        ip_vs_unlink_service(svc, false);

        return 0;
}


/*
 *      Flush all the virtual services
 */
static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup)
{
        int idx;
        struct ip_vs_service *svc;
        struct hlist_node *n;

        /*
         * Flush the service table hashed by <netns,protocol,addr,port>
         */
        for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx],
                                          s_list) {
                        if (svc->ipvs == ipvs)
                                ip_vs_unlink_service(svc, cleanup);
                }
        }

        /*
         * Flush the service table hashed by fwmark
         */
        for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx],
                                          f_list) {
                        if (svc->ipvs == ipvs)
                                ip_vs_unlink_service(svc, cleanup);
                }
        }

        return 0;
}

/*
 *      Delete service by {netns} in the service table.
 *      Called by __ip_vs_batch_cleanup()
 */
void ip_vs_service_nets_cleanup(struct list_head *net_list)
{
        struct netns_ipvs *ipvs;
        struct net *net;

        EnterFunction(2);
        /* Check for "full" addressed entries */
        mutex_lock(&__ip_vs_mutex);
        list_for_each_entry(net, net_list, exit_list) {
                ipvs = net_ipvs(net);
                ip_vs_flush(ipvs, true);
        }
        mutex_unlock(&__ip_vs_mutex);
        LeaveFunction(2);
}

/* Put all references for device (dst_cache) */
static inline void
ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
{
        struct ip_vs_dest_dst *dest_dst;

        spin_lock_bh(&dest->dst_lock);
        dest_dst = rcu_dereference_protected(dest->dest_dst, 1);
        if (dest_dst && dest_dst->dst_cache->dev == dev) {
                IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n",
                              dev->name,
                              IP_VS_DBG_ADDR(dest->af, &dest->addr),
                              ntohs(dest->port),
                              refcount_read(&dest->refcnt));
                __ip_vs_dst_cache_reset(dest);
        }
        spin_unlock_bh(&dest->dst_lock);

}
/* Netdev event receiver
 * Currently only NETDEV_DOWN is handled to release refs to cached dsts
 */
static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
                           void *ptr)
{
        struct net_device *dev = netdev_notifier_info_to_dev(ptr);
        struct net *net = dev_net(dev);
        struct netns_ipvs *ipvs = net_ipvs(net);
        struct ip_vs_service *svc;
        struct ip_vs_dest *dest;
        unsigned int idx;

        if (event != NETDEV_DOWN || !ipvs)
                return NOTIFY_DONE;
        IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name);
        EnterFunction(2);
        mutex_lock(&__ip_vs_mutex);
        for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
                        if (svc->ipvs == ipvs) {
                                list_for_each_entry(dest, &svc->destinations,
                                                    n_list) {
                                        ip_vs_forget_dev(dest, dev);
                                }
                        }
                }

                hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
                        if (svc->ipvs == ipvs) {
                                list_for_each_entry(dest, &svc->destinations,
                                                    n_list) {
                                        ip_vs_forget_dev(dest, dev);
                                }
                        }

                }
        }

        spin_lock_bh(&ipvs->dest_trash_lock);
        list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
                ip_vs_forget_dev(dest, dev);
        }
        spin_unlock_bh(&ipvs->dest_trash_lock);
        mutex_unlock(&__ip_vs_mutex);
        LeaveFunction(2);
        return NOTIFY_DONE;
}

/*
 *      Zero counters in a service or all services
 */
static int ip_vs_zero_service(struct ip_vs_service *svc)
{
        struct ip_vs_dest *dest;

        list_for_each_entry(dest, &svc->destinations, n_list) {
                ip_vs_zero_stats(&dest->stats);
        }
        ip_vs_zero_stats(&svc->stats);
        return 0;
}

static int ip_vs_zero_all(struct netns_ipvs *ipvs)
{
        int idx;
        struct ip_vs_service *svc;

        for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
                        if (svc->ipvs == ipvs)
                                ip_vs_zero_service(svc);
                }
        }

        for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
                        if (svc->ipvs == ipvs)
                                ip_vs_zero_service(svc);
                }
        }

        ip_vs_zero_stats(&ipvs->tot_stats);
        return 0;
}

#ifdef CONFIG_SYSCTL

static int three = 3;

static int
proc_do_defense_mode(struct ctl_table *table, int write,
                     void *buffer, size_t *lenp, loff_t *ppos)
{
        struct netns_ipvs *ipvs = table->extra2;
        int *valp = table->data;
        int val = *valp;
        int rc;

        struct ctl_table tmp = {
                .data = &val,
                .maxlen = sizeof(int),
                .mode = table->mode,
        };

        rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
        if (write && (*valp != val)) {
                if (val < 0 || val > 3) {
                        rc = -EINVAL;
                } else {
                        *valp = val;
                        update_defense_level(ipvs);
                }
        }
        return rc;
}

static int
proc_do_sync_threshold(struct ctl_table *table, int write,
                       void *buffer, size_t *lenp, loff_t *ppos)
{
        int *valp = table->data;
        int val[2];
        int rc;
        struct ctl_table tmp = {
                .data = &val,
                .maxlen = table->maxlen,
                .mode = table->mode,
        };

        memcpy(val, valp, sizeof(val));
        rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
        if (write) {
                if (val[0] < 0 || val[1] < 0 ||
                    (val[0] >= val[1] && val[1]))
                        rc = -EINVAL;
                else
                        memcpy(valp, val, sizeof(val));
        }
        return rc;
}

static int
proc_do_sync_ports(struct ctl_table *table, int write,
                   void *buffer, size_t *lenp, loff_t *ppos)
{
        int *valp = table->data;
        int val = *valp;
        int rc;

        struct ctl_table tmp = {
                .data = &val,
                .maxlen = sizeof(int),
                .mode = table->mode,
        };

        rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
        if (write && (*valp != val)) {
                if (val < 1 || !is_power_of_2(val))
                        rc = -EINVAL;
                else
                        *valp = val;
        }
        return rc;
}

/*
 *      IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
 *      Do not change order or insert new entries without
 *      align with netns init in ip_vs_control_net_init()
 */

static struct ctl_table vs_vars[] = {
        {
                .procname       = "amemthresh",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "am_droprate",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "drop_entry",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_do_defense_mode,
        },
        {
                .procname       = "drop_packet",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_do_defense_mode,
        },
#ifdef CONFIG_IP_VS_NFCT
        {
                .procname       = "conntrack",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
#endif
        {
                .procname       = "secure_tcp",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_do_defense_mode,
        },
        {
                .procname       = "snat_reroute",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
        {
                .procname       = "sync_version",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_minmax,
                .extra1         = SYSCTL_ZERO,
                .extra2         = SYSCTL_ONE,
        },
        {
                .procname       = "sync_ports",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_do_sync_ports,
        },
        {
                .procname       = "sync_persist_mode",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "sync_qlen_max",
                .maxlen         = sizeof(unsigned long),
                .mode           = 0644,
                .proc_handler   = proc_doulongvec_minmax,
        },
        {
                .procname       = "sync_sock_size",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "cache_bypass",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "expire_nodest_conn",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "sloppy_tcp",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "sloppy_sctp",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "expire_quiescent_template",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "sync_threshold",
                .maxlen         =
                        sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold),
                .mode           = 0644,
                .proc_handler   = proc_do_sync_threshold,
        },
        {
                .procname       = "sync_refresh_period",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "sync_retries",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_minmax,
                .extra1         = SYSCTL_ZERO,
                .extra2         = &three,
        },
        {
                .procname       = "nat_icmp_send",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "pmtu_disc",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "backup_only",
                .maxlen         = sizeof(int),
                .mode           = 0644,

                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "conn_reuse_mode",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "schedule_icmp",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "ignore_tunneled",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .procname       = "run_estimation",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
#ifdef CONFIG_IP_VS_DEBUG
        {
                .procname       = "debug_level",
                .data           = &sysctl_ip_vs_debug_level,
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
#endif
        { }
};

#endif

#ifdef CONFIG_PROC_FS

struct ip_vs_iter {
        struct seq_net_private p;  /* Do not move this, netns depends upon it*/
        struct hlist_head *table;
        int bucket;
};

/*
 *      Write the contents of the VS rule table to a PROCfs file.
 *      (It is kept just for backward compatibility)
 */
static inline const char *ip_vs_fwd_name(unsigned int flags)
{
        switch (flags & IP_VS_CONN_F_FWD_MASK) {
        case IP_VS_CONN_F_LOCALNODE:
                return "Local";
        case IP_VS_CONN_F_TUNNEL:
                return "Tunnel";
        case IP_VS_CONN_F_DROUTE:
                return "Route";
        default:
                return "Masq";
        }
}


/* Get the Nth entry in the two lists */
static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
{
        struct net *net = seq_file_net(seq);
        struct netns_ipvs *ipvs = net_ipvs(net);
        struct ip_vs_iter *iter = seq->private;
        int idx;
        struct ip_vs_service *svc;

        /* look in hash by protocol */
        for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) {
                        if ((svc->ipvs == ipvs) && pos-- == 0) {
                                iter->table = ip_vs_svc_table;
                                iter->bucket = idx;
                                return svc;
                        }
                }
        }

        /* keep looking in fwmark */
        for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx],
                                         f_list) {
                        if ((svc->ipvs == ipvs) && pos-- == 0) {
                                iter->table = ip_vs_svc_fwm_table;
                                iter->bucket = idx;
                                return svc;
                        }
                }
        }

        return NULL;
}

static void *ip_vs_info_seq_start(struct seq_file *seq, loff_t *pos)
        __acquires(RCU)
{
        rcu_read_lock();
        return *pos ? ip_vs_info_array(seq, *pos - 1) : SEQ_START_TOKEN;
}


static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
        struct hlist_node *e;
        struct ip_vs_iter *iter;
        struct ip_vs_service *svc;

        ++*pos;
        if (v == SEQ_START_TOKEN)
                return ip_vs_info_array(seq,0);

        svc = v;
        iter = seq->private;

        if (iter->table == ip_vs_svc_table) {
                /* next service in table hashed by protocol */
                e = rcu_dereference(hlist_next_rcu(&svc->s_list));
                if (e)
                        return hlist_entry(e, struct ip_vs_service, s_list);

                while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
                        hlist_for_each_entry_rcu(svc,
                                                 &ip_vs_svc_table[iter->bucket],
                                                 s_list) {
                                return svc;
                        }
                }

                iter->table = ip_vs_svc_fwm_table;
                iter->bucket = -1;
                goto scan_fwmark;
        }

        /* next service in hashed by fwmark */
        e = rcu_dereference(hlist_next_rcu(&svc->f_list));
        if (e)
                return hlist_entry(e, struct ip_vs_service, f_list);

 scan_fwmark:
        while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
                hlist_for_each_entry_rcu(svc,
                                         &ip_vs_svc_fwm_table[iter->bucket],
                                         f_list)
                        return svc;
        }

        return NULL;
}

static void ip_vs_info_seq_stop(struct seq_file *seq, void *v)
        __releases(RCU)
{
        rcu_read_unlock();
}


static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
{
        if (v == SEQ_START_TOKEN) {
                seq_printf(seq,
                        "IP Virtual Server version %d.%d.%d (size=%d)\n",
                        NVERSION(IP_VS_VERSION_CODE), ip_vs_conn_tab_size);
                seq_puts(seq,
                         "Prot LocalAddress:Port Scheduler Flags\n");
                seq_puts(seq,
                         "  -> RemoteAddress:Port Forward Weight ActiveConn InActConn\n");
        } else {
                struct net *net = seq_file_net(seq);
                struct netns_ipvs *ipvs = net_ipvs(net);
                const struct ip_vs_service *svc = v;
                const struct ip_vs_iter *iter = seq->private;
                const struct ip_vs_dest *dest;
                struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
                char *sched_name = sched ? sched->name : "none";

                if (svc->ipvs != ipvs)
                        return 0;
                if (iter->table == ip_vs_svc_table) {
#ifdef CONFIG_IP_VS_IPV6
                        if (svc->af == AF_INET6)
                                seq_printf(seq, "%s  [%pI6]:%04X %s ",
                                           ip_vs_proto_name(svc->protocol),
                                           &svc->addr.in6,
                                           ntohs(svc->port),
                                           sched_name);
                        else
#endif
                                seq_printf(seq, "%s  %08X:%04X %s %s ",
                                           ip_vs_proto_name(svc->protocol),
                                           ntohl(svc->addr.ip),
                                           ntohs(svc->port),
                                           sched_name,
                                           (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
                } else {
                        seq_printf(seq, "FWM  %08X %s %s",
                                   svc->fwmark, sched_name,
                                   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
                }

                if (svc->flags & IP_VS_SVC_F_PERSISTENT)
                        seq_printf(seq, "persistent %d %08X\n",
                                svc->timeout,
                                ntohl(svc->netmask));
                else
                        seq_putc(seq, '\n');

                list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
#ifdef CONFIG_IP_VS_IPV6
                        if (dest->af == AF_INET6)
                                seq_printf(seq,
                                           "  -> [%pI6]:%04X"
                                           "      %-7s %-6d %-10d %-10d\n",
                                           &dest->addr.in6,
                                           ntohs(dest->port),
                                           ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
                                           atomic_read(&dest->weight),
                                           atomic_read(&dest->activeconns),
                                           atomic_read(&dest->inactconns));
                        else
#endif
                                seq_printf(seq,
                                           "  -> %08X:%04X      "
                                           "%-7s %-6d %-10d %-10d\n",
                                           ntohl(dest->addr.ip),
                                           ntohs(dest->port),
                                           ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
                                           atomic_read(&dest->weight),
                                           atomic_read(&dest->activeconns),
                                           atomic_read(&dest->inactconns));

                }
        }
        return 0;
}

static const struct seq_operations ip_vs_info_seq_ops = {
        .start = ip_vs_info_seq_start,
        .next  = ip_vs_info_seq_next,
        .stop  = ip_vs_info_seq_stop,
        .show  = ip_vs_info_seq_show,
};

static int ip_vs_stats_show(struct seq_file *seq, void *v)
{
        struct net *net = seq_file_single_net(seq);
        struct ip_vs_kstats show;

/*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
        seq_puts(seq,
                 "   Total Incoming Outgoing         Incoming         Outgoing\n");
        seq_puts(seq,
                 "   Conns  Packets  Packets            Bytes            Bytes\n");

        ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
        seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n",
                   (unsigned long long)show.conns,
                   (unsigned long long)show.inpkts,
                   (unsigned long long)show.outpkts,
                   (unsigned long long)show.inbytes,
                   (unsigned long long)show.outbytes);

/*                01234567 01234567 01234567 0123456701234567 0123456701234567*/
        seq_puts(seq,
                 " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
        seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n",
                   (unsigned long long)show.cps,
                   (unsigned long long)show.inpps,
                   (unsigned long long)show.outpps,
                   (unsigned long long)show.inbps,
                   (unsigned long long)show.outbps);

        return 0;
}

static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
{
        struct net *net = seq_file_single_net(seq);
        struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
        struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats;
        struct ip_vs_kstats kstats;
        int i;

/*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
        seq_puts(seq,
                 "       Total Incoming Outgoing         Incoming         Outgoing\n");
        seq_puts(seq,
                 "CPU    Conns  Packets  Packets            Bytes            Bytes\n");

        for_each_possible_cpu(i) {
                struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
                unsigned int start;
                u64 conns, inpkts, outpkts, inbytes, outbytes;

                do {
                        start = u64_stats_fetch_begin_irq(&u->syncp);
                        conns = u->cnt.conns;
                        inpkts = u->cnt.inpkts;
                        outpkts = u->cnt.outpkts;
                        inbytes = u->cnt.inbytes;
                        outbytes = u->cnt.outbytes;
                } while (u64_stats_fetch_retry_irq(&u->syncp, start));

                seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n",
                           i, (u64)conns, (u64)inpkts,
                           (u64)outpkts, (u64)inbytes,
                           (u64)outbytes);
        }

        ip_vs_copy_stats(&kstats, tot_stats);

        seq_printf(seq, "  ~ %8LX %8LX %8LX %16LX %16LX\n\n",
                   (unsigned long long)kstats.conns,
                   (unsigned long long)kstats.inpkts,
                   (unsigned long long)kstats.outpkts,
                   (unsigned long long)kstats.inbytes,
                   (unsigned long long)kstats.outbytes);

/*                ... 01234567 01234567 01234567 0123456701234567 0123456701234567 */
        seq_puts(seq,
                 "     Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
        seq_printf(seq, "    %8LX %8LX %8LX %16LX %16LX\n",
                   kstats.cps,
                   kstats.inpps,
                   kstats.outpps,
                   kstats.inbps,
                   kstats.outbps);

        return 0;
}
#endif

/*
 *      Set timeout values for tcp tcpfin udp in the timeout_table.
 */
static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u)
{
#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP)
        struct ip_vs_proto_data *pd;
#endif

        IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n",
                  u->tcp_timeout,
                  u->tcp_fin_timeout,
                  u->udp_timeout);

#ifdef CONFIG_IP_VS_PROTO_TCP
        if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
            u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
                return -EINVAL;
        }
#endif

#ifdef CONFIG_IP_VS_PROTO_UDP
        if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
                return -EINVAL;
#endif

#ifdef CONFIG_IP_VS_PROTO_TCP
        if (u->tcp_timeout) {
                pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
                pd->timeout_table[IP_VS_TCP_S_ESTABLISHED]
                        = u->tcp_timeout * HZ;
        }

        if (u->tcp_fin_timeout) {
                pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
                pd->timeout_table[IP_VS_TCP_S_FIN_WAIT]
                        = u->tcp_fin_timeout * HZ;
        }
#endif

#ifdef CONFIG_IP_VS_PROTO_UDP
        if (u->udp_timeout) {
                pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
                pd->timeout_table[IP_VS_UDP_S_NORMAL]
                        = u->udp_timeout * HZ;
        }
#endif
        return 0;
}

#define CMDID(cmd)              (cmd - IP_VS_BASE_CTL)

struct ip_vs_svcdest_user {
        struct ip_vs_service_user       s;
        struct ip_vs_dest_user          d;
};

static const unsigned char set_arglen[CMDID(IP_VS_SO_SET_MAX) + 1] = {
        [CMDID(IP_VS_SO_SET_ADD)]         = sizeof(struct ip_vs_service_user),
        [CMDID(IP_VS_SO_SET_EDIT)]        = sizeof(struct ip_vs_service_user),
        [CMDID(IP_VS_SO_SET_DEL)]         = sizeof(struct ip_vs_service_user),
        [CMDID(IP_VS_SO_SET_ADDDEST)]     = sizeof(struct ip_vs_svcdest_user),
        [CMDID(IP_VS_SO_SET_DELDEST)]     = sizeof(struct ip_vs_svcdest_user),
        [CMDID(IP_VS_SO_SET_EDITDEST)]    = sizeof(struct ip_vs_svcdest_user),
        [CMDID(IP_VS_SO_SET_TIMEOUT)]     = sizeof(struct ip_vs_timeout_user),
        [CMDID(IP_VS_SO_SET_STARTDAEMON)] = sizeof(struct ip_vs_daemon_user),
        [CMDID(IP_VS_SO_SET_STOPDAEMON)]  = sizeof(struct ip_vs_daemon_user),
        [CMDID(IP_VS_SO_SET_ZERO)]        = sizeof(struct ip_vs_service_user),
};

union ip_vs_set_arglen {
        struct ip_vs_service_user       field_IP_VS_SO_SET_ADD;
        struct ip_vs_service_user       field_IP_VS_SO_SET_EDIT;
        struct ip_vs_service_user       field_IP_VS_SO_SET_DEL;
        struct ip_vs_svcdest_user       field_IP_VS_SO_SET_ADDDEST;
        struct ip_vs_svcdest_user       field_IP_VS_SO_SET_DELDEST;
        struct ip_vs_svcdest_user       field_IP_VS_SO_SET_EDITDEST;
        struct ip_vs_timeout_user       field_IP_VS_SO_SET_TIMEOUT;
        struct ip_vs_daemon_user        field_IP_VS_SO_SET_STARTDAEMON;
        struct ip_vs_daemon_user        field_IP_VS_SO_SET_STOPDAEMON;
        struct ip_vs_service_user       field_IP_VS_SO_SET_ZERO;
};

#define MAX_SET_ARGLEN  sizeof(union ip_vs_set_arglen)

static void ip_vs_copy_usvc_compat(struct ip_vs_service_user_kern *usvc,
                                  struct ip_vs_service_user *usvc_compat)
{
        memset(usvc, 0, sizeof(*usvc));

        usvc->af                = AF_INET;
        usvc->protocol          = usvc_compat->protocol;
        usvc->addr.ip           = usvc_compat->addr;
        usvc->port              = usvc_compat->port;
        usvc->fwmark            = usvc_compat->fwmark;

        /* Deep copy of sched_name is not needed here */
        usvc->sched_name        = usvc_compat->sched_name;

        usvc->flags             = usvc_compat->flags;
        usvc->timeout           = usvc_compat->timeout;
        usvc->netmask           = usvc_compat->netmask;
}

static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
                                   struct ip_vs_dest_user *udest_compat)
{
        memset(udest, 0, sizeof(*udest));

        udest->addr.ip          = udest_compat->addr;
        udest->port             = udest_compat->port;
        udest->conn_flags       = udest_compat->conn_flags;
        udest->weight           = udest_compat->weight;
        udest->u_threshold      = udest_compat->u_threshold;
        udest->l_threshold      = udest_compat->l_threshold;
        udest->af               = AF_INET;
        udest->tun_type         = IP_VS_CONN_F_TUNNEL_TYPE_IPIP;
}

static int
do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len)
{
        struct net *net = sock_net(sk);
        int ret;
        unsigned char arg[MAX_SET_ARGLEN];
        struct ip_vs_service_user *usvc_compat;
        struct ip_vs_service_user_kern usvc;
        struct ip_vs_service *svc;
        struct ip_vs_dest_user *udest_compat;
        struct ip_vs_dest_user_kern udest;
        struct netns_ipvs *ipvs = net_ipvs(net);

        BUILD_BUG_ON(sizeof(arg) > 255);
        if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
                return -EPERM;

        if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_SET_MAX)
                return -EINVAL;
        if (len != set_arglen[CMDID(cmd)]) {
                IP_VS_DBG(1, "set_ctl: len %u != %u\n",
                          len, set_arglen[CMDID(cmd)]);
                return -EINVAL;
        }

        if (copy_from_sockptr(arg, ptr, len) != 0)
                return -EFAULT;

        /* Handle daemons since they have another lock */
        if (cmd == IP_VS_SO_SET_STARTDAEMON ||
            cmd == IP_VS_SO_SET_STOPDAEMON) {
                struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;

                if (cmd == IP_VS_SO_SET_STARTDAEMON) {
                        struct ipvs_sync_daemon_cfg cfg;

                        memset(&cfg, 0, sizeof(cfg));
                        ret = -EINVAL;
                        if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
                                    sizeof(cfg.mcast_ifn)) <= 0)
                                return ret;
                        cfg.syncid = dm->syncid;
                        ret = start_sync_thread(ipvs, &cfg, dm->state);
                } else {
                        ret = stop_sync_thread(ipvs, dm->state);
                }
                return ret;
        }

        mutex_lock(&__ip_vs_mutex);
        if (cmd == IP_VS_SO_SET_FLUSH) {
                /* Flush the virtual service */
                ret = ip_vs_flush(ipvs, false);
                goto out_unlock;
        } else if (cmd == IP_VS_SO_SET_TIMEOUT) {
                /* Set timeout values for (tcp tcpfin udp) */
                ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg);
                goto out_unlock;
        } else if (!len) {
                /* No more commands with len == 0 below */
                ret = -EINVAL;
                goto out_unlock;
        }

        usvc_compat = (struct ip_vs_service_user *)arg;
        udest_compat = (struct ip_vs_dest_user *)(usvc_compat + 1);

        /* We only use the new structs internally, so copy userspace compat
         * structs to extended internal versions */
        ip_vs_copy_usvc_compat(&usvc, usvc_compat);
        ip_vs_copy_udest_compat(&udest, udest_compat);

        if (cmd == IP_VS_SO_SET_ZERO) {
                /* if no service address is set, zero counters in all */
                if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) {
                        ret = ip_vs_zero_all(ipvs);
                        goto out_unlock;
                }
        }

        if ((cmd == IP_VS_SO_SET_ADD || cmd == IP_VS_SO_SET_EDIT) &&
            strnlen(usvc.sched_name, IP_VS_SCHEDNAME_MAXLEN) ==
            IP_VS_SCHEDNAME_MAXLEN) {
                ret = -EINVAL;
                goto out_unlock;
        }

        /* Check for valid protocol: TCP or UDP or SCTP, even for fwmark!=0 */
        if (usvc.protocol != IPPROTO_TCP && usvc.protocol != IPPROTO_UDP &&
            usvc.protocol != IPPROTO_SCTP) {
                pr_err("set_ctl: invalid protocol: %d %pI4:%d\n",
                       usvc.protocol, &usvc.addr.ip,
                       ntohs(usvc.port));
                ret = -EFAULT;
                goto out_unlock;
        }

        /* Lookup the exact service by <protocol, addr, port> or fwmark */
        rcu_read_lock();
        if (usvc.fwmark == 0)
                svc = __ip_vs_service_find(ipvs, usvc.af, usvc.protocol,
                                           &usvc.addr, usvc.port);
        else
                svc = __ip_vs_svc_fwm_find(ipvs, usvc.af, usvc.fwmark);
        rcu_read_unlock();

        if (cmd != IP_VS_SO_SET_ADD
            && (svc == NULL || svc->protocol != usvc.protocol)) {
                ret = -ESRCH;
                goto out_unlock;
        }

        switch (cmd) {
        case IP_VS_SO_SET_ADD:
                if (svc != NULL)
                        ret = -EEXIST;
                else
                        ret = ip_vs_add_service(ipvs, &usvc, &svc);
                break;
        case IP_VS_SO_SET_EDIT:
                ret = ip_vs_edit_service(svc, &usvc);
                break;
        case IP_VS_SO_SET_DEL:
                ret = ip_vs_del_service(svc);
                if (!ret)
                        goto out_unlock;
                break;
        case IP_VS_SO_SET_ZERO:
                ret = ip_vs_zero_service(svc);
                break;
        case IP_VS_SO_SET_ADDDEST:
                ret = ip_vs_add_dest(svc, &udest);
                break;
        case IP_VS_SO_SET_EDITDEST:
                ret = ip_vs_edit_dest(svc, &udest);
                break;
        case IP_VS_SO_SET_DELDEST:
                ret = ip_vs_del_dest(svc, &udest);
        }

  out_unlock:
        mutex_unlock(&__ip_vs_mutex);
        return ret;
}


static void
ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
{
        struct ip_vs_scheduler *sched;
        struct ip_vs_kstats kstats;
        char *sched_name;

        sched = rcu_dereference_protected(src->scheduler, 1);
        sched_name = sched ? sched->name : "none";
        dst->protocol = src->protocol;
        dst->addr = src->addr.ip;
        dst->port = src->port;
        dst->fwmark = src->fwmark;
        strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
        dst->flags = src->flags;
        dst->timeout = src->timeout / HZ;
        dst->netmask = src->netmask;
        dst->num_dests = src->num_dests;
        ip_vs_copy_stats(&kstats, &src->stats);
        ip_vs_export_stats_user(&dst->stats, &kstats);
}

static inline int
__ip_vs_get_service_entries(struct netns_ipvs *ipvs,
                            const struct ip_vs_get_services *get,
                            struct ip_vs_get_services __user *uptr)
{
        int idx, count=0;
        struct ip_vs_service *svc;
        struct ip_vs_service_entry entry;
        int ret = 0;

        for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
                        /* Only expose IPv4 entries to old interface */
                        if (svc->af != AF_INET || (svc->ipvs != ipvs))
                                continue;

                        if (count >= get->num_services)
                                goto out;
                        memset(&entry, 0, sizeof(entry));
                        ip_vs_copy_service(&entry, svc);
                        if (copy_to_user(&uptr->entrytable[count],
                                         &entry, sizeof(entry))) {
                                ret = -EFAULT;
                                goto out;
                        }
                        count++;
                }
        }

        for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
                hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
                        /* Only expose IPv4 entries to old interface */
                        if (svc->af != AF_INET || (svc->ipvs != ipvs))
                                continue;

                        if (count >= get->num_services)
                                goto out;
                        memset(&entry, 0, sizeof(entry));
                        ip_vs_copy_service(&entry, svc);
                        if (copy_to_user(&uptr->entrytable[count],
                                         &entry, sizeof(entry))) {
                                ret = -EFAULT;
                                goto out;
                        }
                        count++;
                }
        }
out:
        return ret;
}

static inline int
__ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *get,
                         struct ip_vs_get_dests __user *uptr)
{
        struct ip_vs_service *svc;
        union nf_inet_addr addr = { .ip = get->addr };
        int ret = 0;

        rcu_read_lock();
        if (get->fwmark)
                svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, get->fwmark);
        else
                svc = __ip_vs_service_find(ipvs, AF_INET, get->protocol, &addr,
                                           get->port);
        rcu_read_unlock();

        if (svc) {
                int count = 0;
                struct ip_vs_dest *dest;
                struct ip_vs_dest_entry entry;
                struct ip_vs_kstats kstats;

                memset(&entry, 0, sizeof(entry));
                list_for_each_entry(dest, &svc->destinations, n_list) {
                        if (count >= get->num_dests)
                                break;

                        /* Cannot expose heterogeneous members via sockopt
                         * interface
                         */
                        if (dest->af != svc->af)
                                continue;

                        entry.addr = dest->addr.ip;
                        entry.port = dest->port;
                        entry.conn_flags = atomic_read(&dest->conn_flags);
                        entry.weight = atomic_read(&dest->weight);
                        entry.u_threshold = dest->u_threshold;
                        entry.l_threshold = dest->l_threshold;
                        entry.activeconns = atomic_read(&dest->activeconns);
                        entry.inactconns = atomic_read(&dest->inactconns);
                        entry.persistconns = atomic_read(&dest->persistconns);
                        ip_vs_copy_stats(&kstats, &dest->stats);
                        ip_vs_export_stats_user(&entry.stats, &kstats);
                        if (copy_to_user(&uptr->entrytable[count],
                                         &entry, sizeof(entry))) {
                                ret = -EFAULT;
                                break;
                        }
                        count++;
                }
        } else
                ret = -ESRCH;
        return ret;
}

static inline void
__ip_vs_get_timeouts(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u)
{
#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP)
        struct ip_vs_proto_data *pd;
#endif

        memset(u, 0, sizeof (*u));

#ifdef CONFIG_IP_VS_PROTO_TCP
        pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
        u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
        u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
#endif
#ifdef CONFIG_IP_VS_PROTO_UDP
        pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP);
        u->udp_timeout =
                        pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
#endif
}

static const unsigned char get_arglen[CMDID(IP_VS_SO_GET_MAX) + 1] = {
        [CMDID(IP_VS_SO_GET_VERSION)]  = 64,
        [CMDID(IP_VS_SO_GET_INFO)]     = sizeof(struct ip_vs_getinfo),
        [CMDID(IP_VS_SO_GET_SERVICES)] = sizeof(struct ip_vs_get_services),
        [CMDID(IP_VS_SO_GET_SERVICE)]  = sizeof(struct ip_vs_service_entry),
        [CMDID(IP_VS_SO_GET_DESTS)]    = sizeof(struct ip_vs_get_dests),
        [CMDID(IP_VS_SO_GET_TIMEOUT)]  = sizeof(struct ip_vs_timeout_user),
        [CMDID(IP_VS_SO_GET_DAEMON)]   = 2 * sizeof(struct ip_vs_daemon_user),
};

union ip_vs_get_arglen {
        char                            field_IP_VS_SO_GET_VERSION[64];
        struct ip_vs_getinfo            field_IP_VS_SO_GET_INFO;
        struct ip_vs_get_services       field_IP_VS_SO_GET_SERVICES;
        struct ip_vs_service_entry      field_IP_VS_SO_GET_SERVICE;
        struct ip_vs_get_dests          field_IP_VS_SO_GET_DESTS;
        struct ip_vs_timeout_user       field_IP_VS_SO_GET_TIMEOUT;
        struct ip_vs_daemon_user        field_IP_VS_SO_GET_DAEMON[2];
};

#define MAX_GET_ARGLEN  sizeof(union ip_vs_get_arglen)

static int
do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
        unsigned char arg[MAX_GET_ARGLEN];
        int ret = 0;
        unsigned int copylen;
        struct net *net = sock_net(sk);
        struct netns_ipvs *ipvs = net_ipvs(net);

        BUG_ON(!net);
        BUILD_BUG_ON(sizeof(arg) > 255);
        if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
                return -EPERM;

        if (cmd < IP_VS_BASE_CTL || cmd > IP_VS_SO_GET_MAX)
                return -EINVAL;

        copylen = get_arglen[CMDID(cmd)];
        if (*len < (int) copylen) {
                IP_VS_DBG(1, "get_ctl: len %d < %u\n", *len, copylen);
                return -EINVAL;
        }

        if (copy_from_user(arg, user, copylen) != 0)
                return -EFAULT;
        /*
         * Handle daemons first since it has its own locking
         */
        if (cmd == IP_VS_SO_GET_DAEMON) {
                struct ip_vs_daemon_user d[2];

                memset(&d, 0, sizeof(d));
                mutex_lock(&ipvs->sync_mutex);
                if (ipvs->sync_state & IP_VS_STATE_MASTER) {
                        d[0].state = IP_VS_STATE_MASTER;
                        strlcpy(d[0].mcast_ifn, ipvs->mcfg.mcast_ifn,
                                sizeof(d[0].mcast_ifn));
                        d[0].syncid = ipvs->mcfg.syncid;
                }
                if (ipvs->sync_state & IP_VS_STATE_BACKUP) {
                        d[1].state = IP_VS_STATE_BACKUP;
                        strlcpy(d[1].mcast_ifn, ipvs->bcfg.mcast_ifn,
                                sizeof(d[1].mcast_ifn));
                        d[1].syncid = ipvs->bcfg.syncid;
                }
                if (copy_to_user(user, &d, sizeof(d)) != 0)
                        ret = -EFAULT;
                mutex_unlock(&ipvs->sync_mutex);
                return ret;
        }

        mutex_lock(&__ip_vs_mutex);
        switch (cmd) {
        case IP_VS_SO_GET_VERSION:
        {
                char buf[64];

                sprintf(buf, "IP Virtual Server version %d.%d.%d (size=%d)",
                        NVERSION(IP_VS_VERSION_CODE), ip_vs_conn_tab_size);
                if (copy_to_user(user, buf, strlen(buf)+1) != 0) {
                        ret = -EFAULT;
                        goto out;
                }
                *len = strlen(buf)+1;
        }
        break;

        case IP_VS_SO_GET_INFO:
        {
                struct ip_vs_getinfo info;
                info.version = IP_VS_VERSION_CODE;
                info.size = ip_vs_conn_tab_size;
                info.num_services = ipvs->num_services;
                if (copy_to_user(user, &info, sizeof(info)) != 0)
                        ret = -EFAULT;
        }
        break;

        case IP_VS_SO_GET_SERVICES:
        {
                struct ip_vs_get_services *get;
                int size;

                get = (struct ip_vs_get_services *)arg;
                size = struct_size(get, entrytable, get->num_services);
                if (*len != size) {
                        pr_err("length: %u != %u\n", *len, size);
                        ret = -EINVAL;
                        goto out;
                }
                ret = __ip_vs_get_service_entries(ipvs, get, user);
        }
        break;

        case IP_VS_SO_GET_SERVICE:
        {
                struct ip_vs_service_entry *entry;
                struct ip_vs_service *svc;
                union nf_inet_addr addr;

                entry = (struct ip_vs_service_entry *)arg;
                addr.ip = entry->addr;
                rcu_read_lock();
                if (entry->fwmark)
                        svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, entry->fwmark);
                else
                        svc = __ip_vs_service_find(ipvs, AF_INET,
                                                   entry->protocol, &addr,
                                                   entry->port);
                rcu_read_unlock();
                if (svc) {
                        ip_vs_copy_service(entry, svc);
                        if (copy_to_user(user, entry, sizeof(*entry)) != 0)
                                ret = -EFAULT;
                } else
                        ret = -ESRCH;
        }
        break;

        case IP_VS_SO_GET_DESTS:
        {
                struct ip_vs_get_dests *get;
                int size;

                get = (struct ip_vs_get_dests *)arg;
                size = struct_size(get, entrytable, get->num_dests);
                if (*len != size) {
                        pr_err("length: %u != %u\n", *len, size);
                        ret = -EINVAL;
                        goto out;
                }
                ret = __ip_vs_get_dest_entries(ipvs, get, user);
        }
        break;

        case IP_VS_SO_GET_TIMEOUT:
        {
                struct ip_vs_timeout_user t;

                __ip_vs_get_timeouts(ipvs, &t);
                if (copy_to_user(user, &t, sizeof(t)) != 0)
                        ret = -EFAULT;
        }
        break;

        default:
                ret = -EINVAL;
        }

out:
        mutex_unlock(&__ip_vs_mutex);
        return ret;
}


static struct nf_sockopt_ops ip_vs_sockopts = {
        .pf             = PF_INET,
        .set_optmin     = IP_VS_BASE_CTL,
        .set_optmax     = IP_VS_SO_SET_MAX+1,
        .set            = do_ip_vs_set_ctl,
        .get_optmin     = IP_VS_BASE_CTL,
        .get_optmax     = IP_VS_SO_GET_MAX+1,
        .get            = do_ip_vs_get_ctl,
        .owner          = THIS_MODULE,
};

/*
 * Generic Netlink interface
 */

/* IPVS genetlink family */
static struct genl_family ip_vs_genl_family;

/* Policy used for first-level command attributes */
static const struct nla_policy ip_vs_cmd_policy[IPVS_CMD_ATTR_MAX + 1] = {
        [IPVS_CMD_ATTR_SERVICE]         = { .type = NLA_NESTED },
        [IPVS_CMD_ATTR_DEST]            = { .type = NLA_NESTED },
        [IPVS_CMD_ATTR_DAEMON]          = { .type = NLA_NESTED },
        [IPVS_CMD_ATTR_TIMEOUT_TCP]     = { .type = NLA_U32 },
        [IPVS_CMD_ATTR_TIMEOUT_TCP_FIN] = { .type = NLA_U32 },
        [IPVS_CMD_ATTR_TIMEOUT_UDP]     = { .type = NLA_U32 },
};

/* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DAEMON */
static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = {
        [IPVS_DAEMON_ATTR_STATE]        = { .type = NLA_U32 },
        [IPVS_DAEMON_ATTR_MCAST_IFN]    = { .type = NLA_NUL_STRING,
                                            .len = IP_VS_IFNAME_MAXLEN - 1 },
        [IPVS_DAEMON_ATTR_SYNC_ID]      = { .type = NLA_U32 },
        [IPVS_DAEMON_ATTR_SYNC_MAXLEN]  = { .type = NLA_U16 },
        [IPVS_DAEMON_ATTR_MCAST_GROUP]  = { .type = NLA_U32 },
        [IPVS_DAEMON_ATTR_MCAST_GROUP6] = { .len = sizeof(struct in6_addr) },
        [IPVS_DAEMON_ATTR_MCAST_PORT]   = { .type = NLA_U16 },
        [IPVS_DAEMON_ATTR_MCAST_TTL]    = { .type = NLA_U8 },
};

/* Policy used for attributes in nested attribute IPVS_CMD_ATTR_SERVICE */
static const struct nla_policy ip_vs_svc_policy[IPVS_SVC_ATTR_MAX + 1] = {
        [IPVS_SVC_ATTR_AF]              = { .type = NLA_U16 },
        [IPVS_SVC_ATTR_PROTOCOL]        = { .type = NLA_U16 },
        [IPVS_SVC_ATTR_ADDR]            = { .type = NLA_BINARY,
                                            .len = sizeof(union nf_inet_addr) },
        [IPVS_SVC_ATTR_PORT]            = { .type = NLA_U16 },
        [IPVS_SVC_ATTR_FWMARK]          = { .type = NLA_U32 },
        [IPVS_SVC_ATTR_SCHED_NAME]      = { .type = NLA_NUL_STRING,
                                            .len = IP_VS_SCHEDNAME_MAXLEN - 1 },
        [IPVS_SVC_ATTR_PE_NAME]         = { .type = NLA_NUL_STRING,
                                            .len = IP_VS_PENAME_MAXLEN },
        [IPVS_SVC_ATTR_FLAGS]           = { .type = NLA_BINARY,
                                            .len = sizeof(struct ip_vs_flags) },
        [IPVS_SVC_ATTR_TIMEOUT]         = { .type = NLA_U32 },
        [IPVS_SVC_ATTR_NETMASK]         = { .type = NLA_U32 },
        [IPVS_SVC_ATTR_STATS]           = { .type = NLA_NESTED },
};

/* Policy used for attributes in nested attribute IPVS_CMD_ATTR_DEST */
static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
        [IPVS_DEST_ATTR_ADDR]           = { .type = NLA_BINARY,
                                            .len = sizeof(union nf_inet_addr) },
        [IPVS_DEST_ATTR_PORT]           = { .type = NLA_U16 },
        [IPVS_DEST_ATTR_FWD_METHOD]     = { .type = NLA_U32 },
        [IPVS_DEST_ATTR_WEIGHT]         = { .type = NLA_U32 },
        [IPVS_DEST_ATTR_U_THRESH]       = { .type = NLA_U32 },