/*
 * 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>
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * 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/swap.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>
#endif
#include <net/route.h>
#include <net/sock.h>
#include <net/genetlink.h>

#include <asm/uaccess.h>

#include <net/ip_vs.h>

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

/* lock for service table */
static DEFINE_RWLOCK(__ip_vs_svc_lock);

/* 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);


#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;
        static int old_secure_tcp = 0;
        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 (old_secure_tcp >= 2)
                        to_change = 0;
                break;
        case 1:
                if (nomem) {
                        if (old_secure_tcp < 2)
                                to_change = 1;
                        ipvs->sysctl_secure_tcp = 2;
                } else {
                        if (old_secure_tcp >= 2)
                                to_change = 0;
                }
                break;
        case 2:
                if (nomem) {
                        if (old_secure_tcp < 2)
                                to_change = 1;
                } else {
                        if (old_secure_tcp >= 2)
                                to_change = 0;
                        ipvs->sysctl_secure_tcp = 1;
                }
                break;
        case 3:
                if (old_secure_tcp < 2)
                        to_change = 1;
                break;
        }
        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();
}


/*
 *      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->net);
        schedule_delayed_work(&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 list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
/* the service table hashed by fwmark */
static struct list_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 net *net, int af, unsigned int proto,
                  const union nf_inet_addr *addr, __be16 port)
{
        register 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
        addr_fold ^= ((size_t)net>>8);

        return (proto^ntohl(addr_fold)^(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 net *net, __u32 fwmark)
{
        return (((size_t)net>>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 %pF\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->net, svc->af, svc->protocol,
                                         &svc->addr, svc->port);
                list_add(&svc->s_list, &ip_vs_svc_table[hash]);
        } else {
                /*
                 *  Hash it by fwmark in svc_fwm_table
                 */
                hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark);
                list_add(&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 %pF\n",
                       __func__, __builtin_return_address(0));
                return 0;
        }

        if (svc->fwmark == 0) {
                /* Remove it from the svc_table table */
                list_del(&svc->s_list);
        } else {
                /* Remove it from the svc_fwm_table table */
                list_del(&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 net *net, 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(net, af, protocol, vaddr, vport);

        list_for_each_entry(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)
                    && net_eq(svc->net, net)) {
                        /* 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 net *net, int af, __u32 fwmark)
{
        unsigned int hash;
        struct ip_vs_service *svc;

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

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

        return NULL;
}

struct ip_vs_service *
ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
                  const union nf_inet_addr *vaddr, __be16 vport)
{
        struct ip_vs_service *svc;
        struct netns_ipvs *ipvs = net_ipvs(net);

        read_lock(&__ip_vs_svc_lock);

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

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

        if (svc == NULL
            && protocol == IPPROTO_TCP
            && atomic_read(&ipvs->ftpsvc_counter)
            && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) {
                /*
                 * Check if ftp service entry exists, the packet
                 * might belong to FTP data connections.
                 */
                svc = __ip_vs_service_find(net, 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(net, af, protocol, vaddr, 0);
        }

  out:
        if (svc)
                atomic_inc(&svc->usecnt);
        read_unlock(&__ip_vs_svc_lock);

        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);
        dest->svc = svc;
}

static void
__ip_vs_unbind_svc(struct ip_vs_dest *dest)
{
        struct ip_vs_service *svc = dest->svc;

        dest->svc = NULL;
        if (atomic_dec_and_test(&svc->refcnt)) {
                IP_VS_DBG_BUF(3, "Removing service %u/%s:%u usecnt=%d\n",
                              svc->fwmark,
                              IP_VS_DBG_ADDR(svc->af, &svc->addr),
                              ntohs(svc->port), atomic_read(&svc->usecnt));
                free_percpu(svc->stats.cpustats);
                kfree(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)
{
        register 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;
}

/*
 *      Hashes ip_vs_dest in rs_table by <proto,addr,port>.
 *      should be called with locked tables.
 */
static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
{
        unsigned int hash;

        if (!list_empty(&dest->d_list)) {
                return 0;
        }

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

        list_add(&dest->d_list, &ipvs->rs_table[hash]);

        return 1;
}

/*
 *      UNhashes ip_vs_dest from rs_table.
 *      should be called with locked tables.
 */
static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
{
        /*
         * Remove it from the rs_table table.
         */
        if (!list_empty(&dest->d_list)) {
                list_del_init(&dest->d_list);
        }

        return 1;
}

/*
 *      Lookup real service by <proto,addr,port> in the real service table.
 */
struct ip_vs_dest *
ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
                          const union nf_inet_addr *daddr,
                          __be16 dport)
{
        struct netns_ipvs *ipvs = net_ipvs(net);
        unsigned int hash;
        struct ip_vs_dest *dest;

        /*
         *      Check for "full" addressed entries
         *      Return the first found entry
         */
        hash = ip_vs_rs_hashkey(af, daddr, dport);

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

        return NULL;
}

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

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

        return NULL;
}

/*
 * Find destination by {daddr,dport,vaddr,protocol}
 * Cretaed 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.
 *
 * ip_vs_lookup_real_service() looked promissing, but
 * seems not working as expected.
 */
struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int 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_get(net, 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, daddr, port);
        if (!dest)
                dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
        if (dest)
                atomic_inc(&dest->refcnt);
        ip_vs_service_put(svc);
        return dest;
}

/*
 *  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, const union nf_inet_addr *daddr,
                     __be16 dport)
{
        struct ip_vs_dest *dest, *nxt;
        struct netns_ipvs *ipvs = net_ipvs(svc->net);

        /*
         * Find the destination in trash
         */
        list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
                IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
                              "dest->refcnt=%d\n",
                              dest->vfwmark,
                              IP_VS_DBG_ADDR(svc->af, &dest->addr),
                              ntohs(dest->port),
                              atomic_read(&dest->refcnt));
                if (dest->af == svc->af &&
                    ip_vs_addr_equal(svc->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 */
                        return dest;
                }

                /*
                 * Try to purge the destination from trash if not referenced
                 */
                if (atomic_read(&dest->refcnt) == 1) {
                        IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u "
                                      "from trash\n",
                                      dest->vfwmark,
                                      IP_VS_DBG_ADDR(svc->af, &dest->addr),
                                      ntohs(dest->port));
                        list_del(&dest->n_list);
                        ip_vs_dst_reset(dest);
                        __ip_vs_unbind_svc(dest);
                        free_percpu(dest->stats.cpustats);
                        kfree(dest);
                }
        }

        return NULL;
}


/*
 *  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 net *net)
{
        struct ip_vs_dest *dest, *nxt;
        struct netns_ipvs *ipvs = net_ipvs(net);

        list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
                list_del(&dest->n_list);
                ip_vs_dst_reset(dest);
                __ip_vs_unbind_svc(dest);
                free_percpu(dest->stats.cpustats);
                kfree(dest);
        }
}

static void
ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
{
#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.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_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->ustats0.c = stats->ustats.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 = net_ipvs(svc->net);
        int conn_flags;

        /* 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;

        /* 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 {
                /*
                 *    Put the real service in rs_table if not present.
                 *    For now only for NAT!
                 */
                write_lock_bh(&ipvs->rs_lock);
                ip_vs_rs_hash(ipvs, dest);
                write_unlock_bh(&ipvs->rs_lock);
        }
        atomic_set(&dest->conn_flags, conn_flags);

        /* bind the service */
        if (!dest->svc) {
                __ip_vs_bind_svc(dest, svc);
        } else {
                if (dest->svc != svc) {
                        __ip_vs_unbind_svc(dest);
                        ip_vs_zero_stats(&dest->stats);
                        __ip_vs_bind_svc(dest, svc);
                }
        }

        /* 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;

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

        if (add)
                ip_vs_start_estimator(svc->net, &dest->stats);

        write_lock_bh(&__ip_vs_svc_lock);

        /* Wait until all other svc users go away */
        IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);

        if (add) {
                list_add(&dest->n_list, &svc->destinations);
                svc->num_dests++;
        }

        /* call the update_service, because server weight may be changed */
        if (svc->scheduler->update_service)
                svc->scheduler->update_service(svc);

        write_unlock_bh(&__ip_vs_svc_lock);
}


/*
 *      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;

        EnterFunction(2);

#ifdef CONFIG_IP_VS_IPV6
        if (svc->af == AF_INET6) {
                atype = ipv6_addr_type(&udest->addr.in6);
                if ((!(atype & IPV6_ADDR_UNICAST) ||
                        atype & IPV6_ADDR_LINKLOCAL) &&
                        !__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6))
                        return -EINVAL;
        } else
#endif
        {
                atype = inet_addr_type(svc->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;

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

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

        INIT_LIST_HEAD(&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;
        }

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

        /*
         * Check if the dest already exists in the list
         */
        dest = ip_vs_lookup_dest(svc, &daddr, dport);

        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, &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(svc->af, &daddr), ntohs(dport),
                              atomic_read(&dest->refcnt),
                              dest->vfwmark,
                              IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
                              ntohs(dest->vport));

                /*
                 * Get the destination from the trash
                 */
                list_del(&dest->n_list);

                __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;
        }

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

        /*
         *  Lookup the destination list
         */
        dest = ip_vs_lookup_dest(svc, &daddr, dport);

        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 net *net, struct ip_vs_dest *dest)
{
        struct netns_ipvs *ipvs = net_ipvs(net);

        ip_vs_stop_estimator(net, &dest->stats);

        /*
         *  Remove it from the d-linked list with the real services.
         */
        write_lock_bh(&ipvs->rs_lock);
        ip_vs_rs_unhash(dest);
        write_unlock_bh(&ipvs->rs_lock);

        /*
         *  Decrease the refcnt of the dest, and free the dest
         *  if nobody refers to it (refcnt=0). Otherwise, throw
         *  the destination into the trash.
         */
        if (atomic_dec_and_test(&dest->refcnt)) {
                IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u\n",
                              dest->vfwmark,
                              IP_VS_DBG_ADDR(dest->af, &dest->addr),
                              ntohs(dest->port));
                ip_vs_dst_reset(dest);
                /* simply decrease svc->refcnt here, let the caller check
                   and release the service if nobody refers to it.
                   Only user context can release destination and service,
                   and only one user context can update virtual service at a
                   time, so the operation here is OK */
                atomic_dec(&dest->svc->refcnt);
                free_percpu(dest->stats.cpustats);
                kfree(dest);
        } else {
                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),
                              atomic_read(&dest->refcnt));
                list_add(&dest->n_list, &ipvs->dest_trash);
                atomic_inc(&dest->refcnt);
        }
}


/*
 *      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(&dest->n_list);
        svc->num_dests--;

        /*
         *  Call the update_service function of its scheduler
         */
        if (svcupd && svc->scheduler->update_service)
                        svc->scheduler->update_service(svc);
}


/*
 *      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);

        dest = ip_vs_lookup_dest(svc, &udest->addr, dport);

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

        write_lock_bh(&__ip_vs_svc_lock);

        /*
         *      Wait until all other svc users go away.
         */
        IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);

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

        write_unlock_bh(&__ip_vs_svc_lock);

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

        LeaveFunction(2);

        return 0;
}


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

        /* increase the module use count */
        ip_vs_use_count_inc();

        /* Lookup the scheduler by 'u->sched_name' */
        sched = ip_vs_scheduler_get(u->sched_name);
        if (sched == NULL) {
                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 && (u->netmask < 1 || u->netmask > 128)) {
                ret = -EINVAL;
                goto out_err;
        }
#endif

        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;
        }

        /* I'm the first user of the service */
        atomic_set(&svc->usecnt, 0);
        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;
        svc->timeout = u->timeout * HZ;
        svc->netmask = u->netmask;
        svc->net = net;

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

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

        /* Bind the ct retriever */
        ip_vs_bind_pe(svc, 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);

        ip_vs_start_estimator(net, &svc->stats);

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

        /* Hash the service into the service table */
        write_lock_bh(&__ip_vs_svc_lock);
        ip_vs_svc_hash(svc);
        write_unlock_bh(&__ip_vs_svc_lock);

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


 out_err:
        if (svc != NULL) {
                ip_vs_unbind_scheduler(svc);
                if (svc->inc) {
                        local_bh_disable();
                        ip_vs_app_inc_put(svc->inc);
                        local_bh_enable();
                }
                if (svc->stats.cpustats)
                        free_percpu(svc->stats.cpustats);
                kfree(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, *old_sched;
        struct ip_vs_pe *pe = NULL, *old_pe = NULL;
        int ret = 0;

        /*
         * Lookup the scheduler, by 'u->sched_name'
         */
        sched = ip_vs_scheduler_get(u->sched_name);
        if (sched == NULL) {
                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 && (u->netmask < 1 || u->netmask > 128)) {
                ret = -EINVAL;
                goto out;
        }
#endif

        write_lock_bh(&__ip_vs_svc_lock);

        /*
         * Wait until all other svc users go away.
         */
        IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);

        /*
         * 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_sched = svc->scheduler;
        if (sched != old_sched) {
                /*
                 * Unbind the old scheduler
                 */
                if ((ret = ip_vs_unbind_scheduler(svc))) {
                        old_sched = sched;
                        goto out_unlock;
                }

                /*
                 * Bind the new scheduler
                 */
                if ((ret = ip_vs_bind_scheduler(svc, sched))) {
                        /*
                         * If ip_vs_bind_scheduler fails, restore the old
                         * scheduler.
                         * The main reason of failure is out of memory.
                         *
                         * The question is if the old scheduler can be
                         * restored all the time. TODO: if it cannot be
                         * restored some time, we must delete the service,
                         * otherwise the system may crash.
                         */
                        ip_vs_bind_scheduler(svc, old_sched);
                        old_sched = sched;
                        goto out_unlock;
                }
        }

        old_pe = svc->pe;
        if (pe != old_pe) {
                ip_vs_unbind_pe(svc);
                ip_vs_bind_pe(svc, pe);
        }

out_unlock:
        write_unlock_bh(&__ip_vs_svc_lock);
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)
{
        struct ip_vs_dest *dest, *nxt;
        struct ip_vs_scheduler *old_sched;
        struct ip_vs_pe *old_pe;
        struct netns_ipvs *ipvs = net_ipvs(svc->net);

        pr_info("%s: enter\n", __func__);

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

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

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

        /* Unbind persistence engine */
        old_pe = svc->pe;
        ip_vs_unbind_pe(svc);
        ip_vs_pe_put(old_pe);

        /* Unbind app inc */
        if (svc->inc) {
                ip_vs_app_inc_put(svc->inc);
                svc->inc = NULL;
        }

        /*
         *    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->net, dest);
        }

        /*
         *    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
         */
        if (atomic_read(&svc->refcnt) == 0) {
                IP_VS_DBG_BUF(3, "Removing service %u/%s:%u usecnt=%d\n",
                              svc->fwmark,
                              IP_VS_DBG_ADDR(svc->af, &svc->addr),
                              ntohs(svc->port), atomic_read(&svc->usecnt));
                free_percpu(svc->stats.cpustats);
                kfree(svc);
        }

        /* 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)
{
        /*
         * Unhash it from the service table
         */
        write_lock_bh(&__ip_vs_svc_lock);

        ip_vs_svc_unhash(svc);

        /*
         * Wait until all the svc users go away.
         */
        IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);

        __ip_vs_del_service(svc);

        write_unlock_bh(&__ip_vs_svc_lock);
}

/*
 *      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);

        return 0;
}


/*
 *      Flush all the virtual services
 */
static int ip_vs_flush(struct net *net)
{
        int idx;
        struct ip_vs_service *svc, *nxt;

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

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

        return 0;
}

/*
 *      Delete service by {netns} in the service table.
 *      Called by __ip_vs_cleanup()
 */
void ip_vs_service_net_cleanup(struct net *net)
{
        EnterFunction(2);
        /* Check for "full" addressed entries */
        mutex_lock(&__ip_vs_mutex);
        ip_vs_flush(net);
        mutex_unlock(&__ip_vs_mutex);
        LeaveFunction(2);
}
/*
 * Release dst hold by dst_cache
 */
static inline void
__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev)
{
        spin_lock_bh(&dest->dst_lock);
        if (dest->dst_cache && dest->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),
                              atomic_read(&dest->refcnt));
                ip_vs_dst_reset(dest);
        }
        spin_unlock_bh(&dest->dst_lock);

}
/*
 * Netdev event receiver
 * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to
 * a device that is "unregister" it must be released.
 */
static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
                            void *ptr)
{
        struct net_device *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_UNREGISTER || !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++) {
                list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
                        if (net_eq(svc->net, net)) {
                                list_for_each_entry(dest, &svc->destinations,
                                                    n_list) {
                                        __ip_vs_dev_reset(dest, dev);
                                }
                        }
                }

                list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
                        if (net_eq(svc->net, net)) {
                                list_for_each_entry(dest, &svc->destinations,
                                                    n_list) {
                                        __ip_vs_dev_reset(dest, dev);
                                }
                        }

                }
        }

        list_for_each_entry(dest, &ipvs->dest_trash, n_list) {
                __ip_vs_dev_reset(dest, dev);
        }
        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;

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

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

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

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

        ip_vs_zero_stats(&net_ipvs(net)->tot_stats);
        return 0;
}

#ifdef CONFIG_SYSCTL

static int zero;
static int three = 3;

static int
proc_do_defense_mode(ctl_table *table, int write,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
{
        struct net *net = current->nsproxy->net_ns;
        int *valp = table->data;
        int val = *valp;
        int rc;

        rc = proc_dointvec(table, write, buffer, lenp, ppos);
        if (write && (*valp != val)) {
                if ((*valp < 0) || (*valp > 3)) {
                        /* Restore the correct value */
                        *valp = val;
                } else {
                        update_defense_level(net_ipvs(net));
                }
        }
        return rc;
}

static int
proc_do_sync_threshold(ctl_table *table, int write,
                       void __user *buffer, size_t *lenp, loff_t *ppos)
{
        int *valp = table->data;
        int val[2];
        int rc;

        /* backup the value first */
        memcpy(val, valp, sizeof(val));

        rc = proc_dointvec(table, write, buffer, lenp, ppos);
        if (write && (valp[0] < 0 || valp[1] < 0 ||
            (valp[0] >= valp[1] && valp[1]))) {
                /* Restore the correct value */
                memcpy(valp, val, sizeof(val));
        }
        return rc;
}

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

        rc = proc_dointvec(table, write, buffer, lenp, ppos);
        if (write && (*valp != val)) {
                if ((*valp < 0) || (*valp > 1)) {
                        /* Restore the correct value */
                        *valp = val;
                }
        }
        return rc;
}

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

        rc = proc_dointvec(table, write, buffer, lenp, ppos);
        if (write && (*valp != val)) {
                if (*valp < 1 || !is_power_of_2(*valp)) {
                        /* Restore the correct value */
                        *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_do_sync_mode,
        },
        {
                .procname       = "sync_ports",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = &proc_do_sync_ports,
        },
        {
                .procname       = "sync_qlen_max",
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
        {
                .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       = "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         = &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,
        },
#ifdef CONFIG_IP_VS_DEBUG
        {
                .procname       = "debug_level",
                .data           = &sysctl_ip_vs_debug_level,
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
#endif
#if 0
        {
                .procname       = "timeout_established",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_ESTABLISHED],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_synsent",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_SYN_SENT],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_synrecv",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_SYN_RECV],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_finwait",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_FIN_WAIT],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_timewait",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_TIME_WAIT],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_close",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_CLOSE],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_closewait",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_CLOSE_WAIT],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_lastack",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_LAST_ACK],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_listen",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_LISTEN],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_synack",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_SYNACK],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_udp",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_UDP],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
        {
                .procname       = "timeout_icmp",
                .data   = &vs_timeout_table_dos.timeout[IP_VS_S_ICMP],
                .maxlen         = sizeof(int),
                .mode           = 0644,
                .proc_handler   = proc_dointvec_jiffies,
        },
#endif
        { }
};

#endif

#ifdef CONFIG_PROC_FS

struct ip_vs_iter {
        struct seq_net_private p;  /* Do not move this, netns depends upon it*/
        struct list_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 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++) {
                list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
                        if (net_eq(svc->net, net) && 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++) {
                list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
                        if (net_eq(svc->net, net) && 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(__ip_vs_svc_lock)
{

        read_lock_bh(&__ip_vs_svc_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 list_head *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 */

                if ((e = svc->s_list.next) != &ip_vs_svc_table[iter->bucket])
                        return list_entry(e, struct ip_vs_service, s_list);


                while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
                        list_for_each_entry(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 */
        if ((e = svc->f_list.next) != &ip_vs_svc_fwm_table[iter->bucket])
                return list_entry(e, struct ip_vs_service, f_list);

 scan_fwmark:
        while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
                list_for_each_entry(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(__ip_vs_svc_lock)
{
        read_unlock_bh(&__ip_vs_svc_lock);
}


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 {
                const struct ip_vs_service *svc = v;
                const struct ip_vs_iter *iter = seq->private;
                const struct ip_vs_dest *dest;

                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),
                                           svc->scheduler->name);
                        else
#endif
                                seq_printf(seq, "%s  %08X:%04X %s %s ",
                                           ip_vs_proto_name(svc->protocol),
                                           ntohl(svc->addr.ip),
                                           ntohs(svc->port),
                                           svc->scheduler->name,
                                           (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
                } else {
                        seq_printf(seq, "FWM  %08X %s %s",
                                   svc->fwmark, svc->scheduler->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(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_info_open(struct inode *inode, struct file *file)
{
        return seq_open_net(inode, file, &ip_vs_info_seq_ops,
                        sizeof(struct ip_vs_iter));
}

static const struct file_operations ip_vs_info_fops = {
        .owner   = THIS_MODULE,
        .open    = ip_vs_info_open,
        .read    = seq_read,
        .llseek  = seq_lseek,
        .release = seq_release_net,
};

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

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

        ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats);
        seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", show.conns,
                   show.inpkts, 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, "%8X %8X %8X %16X %16X\n",
                        show.cps, show.inpps, show.outpps,
                        show.inbps, show.outbps);

        return 0;
}

static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
{
        return single_open_net(inode, file, ip_vs_stats_show);
}

static const struct file_operations ip_vs_stats_fops = {
        .owner = THIS_MODULE,
        .open = ip_vs_stats_seq_open,
        .read = seq_read,
        .llseek = seq_lseek,
        .release = single_release_net,
};

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 *cpustats = tot_stats->cpustats;
        struct ip_vs_stats_user rates;
        int i;

/*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
        seq_puts(seq,
                 "       Total Incoming Outgoing         Incoming         Outgoing\n");
        seq_printf(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 inbytes, outbytes;

                do {
                        start = u64_stats_fetch_begin_bh(&u->syncp);
                        inbytes = u->ustats.inbytes;
                        outbytes = u->ustats.outbytes;
                } while (u64_stats_fetch_retry_bh(&u->syncp, start));

                seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
                           i, u->ustats.conns, u->ustats.inpkts,
                           u->ustats.outpkts, (__u64)inbytes,
                           (__u64)outbytes);
        }

        spin_lock_bh(&tot_stats->lock);

        seq_printf(seq, "  ~ %8X %8X %8X %16LX %16LX\n\n",
                   tot_stats->ustats.conns, tot_stats->ustats.inpkts,
                   tot_stats->ustats.outpkts,
                   (unsigned long long) tot_stats->ustats.inbytes,
                   (unsigned long long) tot_stats->ustats.outbytes);

        ip_vs_read_estimator(&rates, tot_stats);

        spin_unlock_bh(&tot_stats->lock);

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

        return 0;
}

static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file)
{
        return single_open_net(inode, file, ip_vs_stats_percpu_show);
}

static const struct file_operations ip_vs_stats_percpu_fops = {
        .owner = THIS_MODULE,
        .open = ip_vs_stats_percpu_seq_open,
        .read = seq_read,
        .llseek = seq_lseek,
        .release = single_release_net,
};
#endif

/*
 *      Set timeout values for tcp tcpfin udp in the timeout_table.
 */
static int ip_vs_set_timeout(struct net *net, 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) {
                pd = ip_vs_proto_data_get(net, 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(net, 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(net, IPPROTO_UDP);
                pd->timeout_table[IP_VS_UDP_S_NORMAL]
                        = u->udp_timeout * HZ;
        }
#endif
        return 0;
}


#define SET_CMDID(cmd)          (cmd - IP_VS_BASE_CTL)
#define SERVICE_ARG_LEN         (sizeof(struct ip_vs_service_user))
#define SVCDEST_ARG_LEN         (sizeof(struct ip_vs_service_user) +    \
                                 sizeof(struct ip_vs_dest_user))
#define TIMEOUT_ARG_LEN         (sizeof(struct ip_vs_timeout_user))
#define DAEMON_ARG_LEN          (sizeof(struct ip_vs_daemon_user))
#define MAX_ARG_LEN             SVCDEST_ARG_LEN

static const unsigned char set_arglen[SET_CMDID(IP_VS_SO_SET_MAX)+1] = {
        [SET_CMDID(IP_VS_SO_SET_ADD)]           = SERVICE_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_EDIT)]          = SERVICE_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_DEL)]           = SERVICE_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_FLUSH)]         = 0,
        [SET_CMDID(IP_VS_SO_SET_ADDDEST)]       = SVCDEST_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_DELDEST)]       = SVCDEST_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_EDITDEST)]      = SVCDEST_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_TIMEOUT)]       = TIMEOUT_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_STARTDAEMON)]   = DAEMON_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_STOPDAEMON)]    = DAEMON_ARG_LEN,
        [SET_CMDID(IP_VS_SO_SET_ZERO)]          = SERVICE_ARG_LEN,
};

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;
}

static int
do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
{
        struct net *net = sock_net(sk);
        int ret;
        unsigned char arg[MAX_ARG_LEN];
        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);

        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 < 0 || len >  MAX_ARG_LEN)
                return -EINVAL;
        if (len != set_arglen[SET_CMDID(cmd)]) {
                pr_err("set_ctl: len %u != %u\n",
                       len, set_arglen[SET_CMDID(cmd)]);
                return -EINVAL;
        }

        if (copy_from_user(arg, user, len) != 0)
                return -EFAULT;

        /* increase the module use count */
        ip_vs_use_count_inc();

        /* 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 (mutex_lock_interruptible(&ipvs->sync_mutex)) {
                        ret = -ERESTARTSYS;
                        goto out_dec;
                }
                if (cmd == IP_VS_SO_SET_STARTDAEMON)
                        ret = start_sync_thread(net, dm->state, dm->mcast_ifn,
                                                dm->syncid);
                else
                        ret = stop_sync_thread(net, dm->state);
                mutex_unlock(&ipvs->sync_mutex);
                goto out_dec;
        }

        if (mutex_lock_interruptible(&__ip_vs_mutex)) {
                ret = -ERESTARTSYS;
                goto out_dec;
        }

        if (cmd == IP_VS_SO_SET_FLUSH) {
                /* Flush the virtual service */
                ret = ip_vs_flush(net);
                goto out_unlock;
        } else if (cmd == IP_VS_SO_SET_TIMEOUT) {
                /* Set timeout values for (tcp tcpfin udp) */
                ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg);
                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(net);
                        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 %s\n",
                       usvc.protocol, &usvc.addr.ip,
                       ntohs(usvc.port), usvc.sched_name);
                ret = -EFAULT;
                goto out_unlock;
        }

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

        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(net, &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);
                break;
        default:
                ret = -EINVAL;
        }

  out_unlock:
        mutex_unlock(&__ip_vs_mutex);
  out_dec:
        /* decrease the module use count */
        ip_vs_use_count_dec();

        return ret;
}


static void
ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
{
        dst->protocol = src->protocol;
        dst->addr = src->addr.ip;
        dst->port = src->port;
        dst->fwmark = src->fwmark;
        strlcpy(dst->sched_name, src->scheduler->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(&dst->stats, &src->stats);
}

static inline int
__ip_vs_get_service_entries(struct net *net,
                            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++) {
                list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
                        /* Only expose IPv4 entries to old interface */
                        if (svc->af != AF_INET || !net_eq(svc->net, net))
                                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++) {
                list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
                        /* Only expose IPv4 entries to old interface */
                        if (svc->af != AF_INET || !net_eq(svc->net, net))
                                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 net *net, 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;

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

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

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

                        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(&entry.stats, &dest->stats);
                        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 net *net, 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(net, 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(net, IPPROTO_UDP);
        u->udp_timeout =
                        pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
#endif
}


#define GET_CMDID(cmd)          (cmd - IP_VS_BASE_CTL)
#define GET_INFO_ARG_LEN        (sizeof(struct ip_vs_getinfo))
#define GET_SERVICES_ARG_LEN    (sizeof(struct ip_vs_get_services))
#define GET_SERVICE_ARG_LEN     (sizeof(struct ip_vs_service_entry))
#define GET_DESTS_ARG_LEN       (sizeof(struct ip_vs_get_dests))
#define GET_TIMEOUT_ARG_LEN     (sizeof(struct ip_vs_timeout_user))
#define GET_DAEMON_ARG_LEN      (sizeof(struct ip_vs_daemon_user) * 2)

static const unsigned char get_arglen[GET_CMDID(IP_VS_SO_GET_MAX)+1] = {
        [GET_CMDID(IP_VS_SO_GET_VERSION)]       = 64,
        [GET_CMDID(IP_VS_SO_GET_INFO)]          = GET_INFO_ARG_LEN,
        [GET_CMDID(IP_VS_SO_GET_SERVICES)]      = GET_SERVICES_ARG_LEN,
        [GET_CMDID(IP_VS_SO_GET_SERVICE)]       = GET_SERVICE_ARG_LEN,
        [GET_CMDID(IP_VS_SO_GET_DESTS)]         = GET_DESTS_ARG_LEN,
        [GET_CMDID(IP_VS_SO_GET_TIMEOUT)]       = GET_TIMEOUT_ARG_LEN,
        [GET_CMDID(IP_VS_SO_GET_DAEMON)]        = GET_DAEMON_ARG_LEN,
};

static int
do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
        unsigned char arg[128];
        int ret = 0;
        unsigned int copylen;
        struct net *net = sock_net(sk);
        struct netns_ipvs *ipvs = net_ipvs(net);

        BUG_ON(!net);
        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;

        if (*len < get_arglen[GET_CMDID(cmd)]) {
                pr_err("get_ctl: len %u < %u\n",
                       *len, get_arglen[GET_CMDID(cmd)]);
                return -EINVAL;
        }

        copylen = get_arglen[GET_CMDID(cmd)];
        if (copylen > 128)
                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));
                if (mutex_lock_interruptible(&ipvs->sync_mutex))
                        return -ERESTARTSYS;

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

        if (mutex_lock_interruptible(&__ip_vs_mutex))
                return -ERESTARTSYS;

        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 = sizeof(*get) +
                        sizeof(struct ip_vs_service_entry) * get->num_services;
                if (*len != size) {
                        pr_err("length: %u != %u\n", *len, size);
                        ret = -EINVAL;
                        goto out;
                }
                ret = __ip_vs_get_service_entries(net, 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;
                if (entry->fwmark)
                        svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark);
                else
                        svc = __ip_vs_service_find(net, AF_INET,
                                                   entry->protocol, &addr,
                                                   entry->port);
                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 = sizeof(*get) +
                        sizeof(struct ip_vs_dest_entry) * get->num_dests;
                if (*len != size) {
                        pr_err("length: %u != %u\n", *len, size);
                        ret = -EINVAL;
                        goto out;
                }
                ret = __ip_vs_get_dest_entries(net, get, user);
        }
        break;

        case IP_VS_SO_GET_TIMEOUT:
        {
                struct ip_vs_timeout_user t;

                __ip_vs_get_timeouts(net, &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 = {
        .id             = GENL_ID_GENERATE,
        .hdrsize        = 0,
        .name           = IPVS_GENL_NAME,
        .version        = IPVS_GENL_VERSION,
        .maxattr        = IPVS_CMD_MAX,
        .netnsok        = true,         /* Make ipvsadm to work on netns */
};

/* 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 },
        [IPVS_DAEMON_ATTR_SYNC_ID]      = { .type = NLA_U32 },
};

/* 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 },
        [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 },
        [IPVS_DEST_ATTR_L_THRESH]       = { .type = NLA_U32 },
        [IPVS_DEST_ATTR_ACTIVE_CONNS]   = { .type = NLA_U32 },
        [IPVS_DEST_ATTR_INACT_CONNS]    = { .type = NLA_U32 },
        [IPVS_DEST_ATTR_PERSIST_CONNS]  = { .type = NLA_U32 },
        [IPVS_DEST_ATTR_STATS]          = { .type = NLA_NESTED },
};

static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
                                 struct ip_vs_stats *stats)
{
        struct ip_vs_stats_user ustats;
        struct nlattr *nl_stats = nla_nest_start(skb, container_type);
        if (!nl_stats)
                return -EMSGSIZE;

        ip_vs_copy_stats(&ustats, stats);

        if (nla_put_u32(skb, IPVS_STATS_ATTR_CONNS, ustats.conns) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_INPKTS, ustats.inpkts) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_OUTPKTS, ustats.outpkts) ||
            nla_put_u64(skb, IPVS_STATS_ATTR_INBYTES, ustats.inbytes) ||
            nla_put_u64(skb, IPVS_STATS_ATTR_OUTBYTES, ustats.outbytes) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_CPS, ustats.cps) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_INPPS, ustats.inpps) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_OUTPPS, ustats.outpps) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_INBPS, ustats.inbps) ||
            nla_put_u32(skb, IPVS_STATS_ATTR_OUTBPS, ustats.outbps))
                goto nla_put_failure;
        nla_nest_end(skb, nl_stats);

        return 0;

nla_put_failure:
        nla_nest_cancel(skb, nl_stats);
        return -EMSGSIZE;
}

static int ip_vs_genl_fill_service(struct sk_buff *skb,
                                   struct ip_vs_service *svc)
{
        struct nlattr *nl_service;
        struct ip_vs_flags flags = { .flags = svc->flags,
                                     .mask = ~0 };

        nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
        if (!nl_service)
                return -EMSGSIZE;

        if (nla_put_u16(skb, IPVS_SVC_ATTR_AF, svc->af))
                goto nla_put_failure;
        if (svc->fwmark) {
                if (nla_put_u32(skb, IPVS_SVC_ATTR_FWMARK, svc->fwmark))
                        goto nla_put_failure;
        } else {
                if (nla_put_u16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol) ||
                    nla_put(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr) ||
                    nla_put_u16(skb, IPVS_SVC_ATTR_PORT, svc->port))
                        goto nla_put_failure;
        }

        if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name) ||
            (svc->pe &&
             nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, svc->pe->name)) ||
            nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
            nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
            nla_put_u32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask))
                goto nla_put_failure;
        if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &svc->stats))
                goto nla_put_failure;

        nla_nest_end(skb, nl_service);

        return 0;

nla_put_failure:
        nla_nest_cancel(skb, nl_service);
        return -EMSGSIZE;
}

static int ip_vs_genl_dump_service(struct sk_buff *skb,
                                   struct ip_vs_service *svc,
                                   struct netlink_callback *cb)
{
        void *hdr;

        hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
                          &ip_vs_genl_family, NLM_F_MULTI,
                          IPVS_CMD_NEW_SERVICE);
        if (!hdr)
                return -EMSGSIZE;

        if (ip_vs_genl_fill_service(skb, svc) < 0)
                goto nla_put_failure;

        return genlmsg_end(skb, hdr);

nla_put_failure:
        genlmsg_cancel(skb, hdr);
        return -EMSGSIZE;
}

static int ip_vs_genl_dump_services(struct sk_buff *skb,
                                    struct netlink_callback *cb)
{
        int idx = 0, i;
        int start = cb->args[0];
        struct ip_vs_service *svc;
        struct net *net = skb_sknet(skb);

        mutex_lock(&__ip_vs_mutex);
        for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
                list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
                        if (++idx <= start || !net_eq(svc->net, net))
                                continue;
                        if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
                                idx--;
                                goto nla_put_failure;
                        }
                }
        }

        for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
                list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
                        if (++idx <= start || !net_eq(svc->net, net))
                                continue;
                        if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
                                idx--;
                                goto nla_put_failure;
                        }
                }
        }

nla_put_failure:
        mutex_unlock(&__ip_vs_mutex);
        cb->args[0] = idx;

        return skb->len;
}