/*
 * xfrm_policy.c
 *
 * Changes:
 *      Mitsuru KANDA @USAGI
 *      Kazunori MIYAZAWA @USAGI
 *      Kunihiro Ishiguro <kunihiro@ipinfusion.com>
 *              IPv6 support
 *      Kazunori MIYAZAWA @USAGI
 *      YOSHIFUJI Hideaki
 *              Split up af-specific portion
 *      Derek Atkins <derek@ihtfp.com>          Add the post_input processor
 *
 */

#include <linux/err.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/cache.h>
#include <linux/audit.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>
#ifdef CONFIG_XFRM_STATISTICS
#include <net/snmp.h>
#endif

#include "xfrm_hash.h"

DEFINE_MUTEX(xfrm_cfg_mutex);
EXPORT_SYMBOL(xfrm_cfg_mutex);

static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
static struct dst_entry *xfrm_policy_sk_bundles;
static DEFINE_RWLOCK(xfrm_policy_lock);

static DEFINE_RWLOCK(xfrm_policy_afinfo_lock);
static struct xfrm_policy_afinfo *xfrm_policy_afinfo[NPROTO];

static struct kmem_cache *xfrm_dst_cache __read_mostly;

static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family);
static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo);
static void xfrm_init_pmtu(struct dst_entry *dst);
static int stale_bundle(struct dst_entry *dst);
static int xfrm_bundle_ok(struct xfrm_dst *xdst);


static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
                                                int dir);

static inline int
__xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
{
        const struct flowi4 *fl4 = &fl->u.ip4;

        return  addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) &&
                addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) &&
                !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
                !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
                (fl4->flowi4_proto == sel->proto || !sel->proto) &&
                (fl4->flowi4_oif == sel->ifindex || !sel->ifindex);
}

static inline int
__xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
{
        const struct flowi6 *fl6 = &fl->u.ip6;

        return  addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) &&
                addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) &&
                !((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) &&
                !((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) &&
                (fl6->flowi6_proto == sel->proto || !sel->proto) &&
                (fl6->flowi6_oif == sel->ifindex || !sel->ifindex);
}

int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl,
                        unsigned short family)
{
        switch (family) {
        case AF_INET:
                return __xfrm4_selector_match(sel, fl);
        case AF_INET6:
                return __xfrm6_selector_match(sel, fl);
        }
        return 0;
}

static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos,
                                                  const xfrm_address_t *saddr,
                                                  const xfrm_address_t *daddr,
                                                  int family)
{
        struct xfrm_policy_afinfo *afinfo;
        struct dst_entry *dst;

        afinfo = xfrm_policy_get_afinfo(family);
        if (unlikely(afinfo == NULL))
                return ERR_PTR(-EAFNOSUPPORT);

        dst = afinfo->dst_lookup(net, tos, saddr, daddr);

        xfrm_policy_put_afinfo(afinfo);

        return dst;
}

static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos,
                                                xfrm_address_t *prev_saddr,
                                                xfrm_address_t *prev_daddr,
                                                int family)
{
        struct net *net = xs_net(x);
        xfrm_address_t *saddr = &x->props.saddr;
        xfrm_address_t *daddr = &x->id.daddr;
        struct dst_entry *dst;

        if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) {
                saddr = x->coaddr;
                daddr = prev_daddr;
        }
        if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) {
                saddr = prev_saddr;
                daddr = x->coaddr;
        }

        dst = __xfrm_dst_lookup(net, tos, saddr, daddr, family);

        if (!IS_ERR(dst)) {
                if (prev_saddr != saddr)
                        memcpy(prev_saddr, saddr,  sizeof(*prev_saddr));
                if (prev_daddr != daddr)
                        memcpy(prev_daddr, daddr,  sizeof(*prev_daddr));
        }

        return dst;
}

static inline unsigned long make_jiffies(long secs)
{
        if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
                return MAX_SCHEDULE_TIMEOUT-1;
        else
                return secs*HZ;
}

static void xfrm_policy_timer(unsigned long data)
{
        struct xfrm_policy *xp = (struct xfrm_policy*)data;
        unsigned long now = get_seconds();
        long next = LONG_MAX;
        int warn = 0;
        int dir;

        read_lock(&xp->lock);

        if (unlikely(xp->walk.dead))
                goto out;

        dir = xfrm_policy_id2dir(xp->index);

        if (xp->lft.hard_add_expires_seconds) {
                long tmo = xp->lft.hard_add_expires_seconds +
                        xp->curlft.add_time - now;
                if (tmo <= 0)
                        goto expired;
                if (tmo < next)
                        next = tmo;
        }
        if (xp->lft.hard_use_expires_seconds) {
                long tmo = xp->lft.hard_use_expires_seconds +
                        (xp->curlft.use_time ? : xp->curlft.add_time) - now;
                if (tmo <= 0)
                        goto expired;
                if (tmo < next)
                        next = tmo;
        }
        if (xp->lft.soft_add_expires_seconds) {
                long tmo = xp->lft.soft_add_expires_seconds +
                        xp->curlft.add_time - now;
                if (tmo <= 0) {
                        warn = 1;
                        tmo = XFRM_KM_TIMEOUT;
                }
                if (tmo < next)
                        next = tmo;
        }
        if (xp->lft.soft_use_expires_seconds) {
                long tmo = xp->lft.soft_use_expires_seconds +
                        (xp->curlft.use_time ? : xp->curlft.add_time) - now;
                if (tmo <= 0) {
                        warn = 1;
                        tmo = XFRM_KM_TIMEOUT;
                }
                if (tmo < next)
                        next = tmo;
        }

        if (warn)
                km_policy_expired(xp, dir, 0, 0);
        if (next != LONG_MAX &&
            !mod_timer(&xp->timer, jiffies + make_jiffies(next)))
                xfrm_pol_hold(xp);

out:
        read_unlock(&xp->lock);
        xfrm_pol_put(xp);
        return;

expired:
        read_unlock(&xp->lock);
        if (!xfrm_policy_delete(xp, dir))
                km_policy_expired(xp, dir, 1, 0);
        xfrm_pol_put(xp);
}

static struct flow_cache_object *xfrm_policy_flo_get(struct flow_cache_object *flo)
{
        struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo);

        if (unlikely(pol->walk.dead))
                flo = NULL;
        else
                xfrm_pol_hold(pol);

        return flo;
}

static int xfrm_policy_flo_check(struct flow_cache_object *flo)
{
        struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo);

        return !pol->walk.dead;
}

static void xfrm_policy_flo_delete(struct flow_cache_object *flo)
{
        xfrm_pol_put(container_of(flo, struct xfrm_policy, flo));
}

static const struct flow_cache_ops xfrm_policy_fc_ops = {
        .get = xfrm_policy_flo_get,
        .check = xfrm_policy_flo_check,
        .delete = xfrm_policy_flo_delete,
};

/* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2
 * SPD calls.
 */

struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
{
        struct xfrm_policy *policy;

        policy = kzalloc(sizeof(struct xfrm_policy), gfp);

        if (policy) {
                write_pnet(&policy->xp_net, net);
                INIT_LIST_HEAD(&policy->walk.all);
                INIT_HLIST_NODE(&policy->bydst);
                INIT_HLIST_NODE(&policy->byidx);
                rwlock_init(&policy->lock);
                atomic_set(&policy->refcnt, 1);
                setup_timer(&policy->timer, xfrm_policy_timer,
                                (unsigned long)policy);
                policy->flo.ops = &xfrm_policy_fc_ops;
        }
        return policy;
}
EXPORT_SYMBOL(xfrm_policy_alloc);

/* Destroy xfrm_policy: descendant resources must be released to this moment. */

void xfrm_policy_destroy(struct xfrm_policy *policy)
{
        BUG_ON(!policy->walk.dead);

        if (del_timer(&policy->timer))
                BUG();

        security_xfrm_policy_free(policy->security);
        kfree(policy);
}
EXPORT_SYMBOL(xfrm_policy_destroy);

/* Rule must be locked. Release descentant resources, announce
 * entry dead. The rule must be unlinked from lists to the moment.
 */

static void xfrm_policy_kill(struct xfrm_policy *policy)
{
        policy->walk.dead = 1;

        atomic_inc(&policy->genid);

        if (del_timer(&policy->timer))
                xfrm_pol_put(policy);

        xfrm_pol_put(policy);
}

static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024;

static inline unsigned int idx_hash(struct net *net, u32 index)
{
        return __idx_hash(index, net->xfrm.policy_idx_hmask);
}

static struct hlist_head *policy_hash_bysel(struct net *net,
                                            const struct xfrm_selector *sel,
                                            unsigned short family, int dir)
{
        unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
        unsigned int hash = __sel_hash(sel, family, hmask);

        return (hash == hmask + 1 ?
                &net->xfrm.policy_inexact[dir] :
                net->xfrm.policy_bydst[dir].table + hash);
}

static struct hlist_head *policy_hash_direct(struct net *net,
                                             const xfrm_address_t *daddr,
                                             const xfrm_address_t *saddr,
                                             unsigned short family, int dir)
{
        unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
        unsigned int hash = __addr_hash(daddr, saddr, family, hmask);

        return net->xfrm.policy_bydst[dir].table + hash;
}

static void xfrm_dst_hash_transfer(struct hlist_head *list,
                                   struct hlist_head *ndsttable,
                                   unsigned int nhashmask)
{
        struct hlist_node *entry, *tmp, *entry0 = NULL;
        struct xfrm_policy *pol;
        unsigned int h0 = 0;

redo:
        hlist_for_each_entry_safe(pol, entry, tmp, list, bydst) {
                unsigned int h;

                h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
                                pol->family, nhashmask);
                if (!entry0) {
                        hlist_del(entry);
                        hlist_add_head(&pol->bydst, ndsttable+h);
                        h0 = h;
                } else {
                        if (h != h0)
                                continue;
                        hlist_del(entry);
                        hlist_add_after(entry0, &pol->bydst);
                }
                entry0 = entry;
        }
        if (!hlist_empty(list)) {
                entry0 = NULL;
                goto redo;
        }
}

static void xfrm_idx_hash_transfer(struct hlist_head *list,
                                   struct hlist_head *nidxtable,
                                   unsigned int nhashmask)
{
        struct hlist_node *entry, *tmp;
        struct xfrm_policy *pol;

        hlist_for_each_entry_safe(pol, entry, tmp, list, byidx) {
                unsigned int h;

                h = __idx_hash(pol->index, nhashmask);
                hlist_add_head(&pol->byidx, nidxtable+h);
        }
}

static unsigned long xfrm_new_hash_mask(unsigned int old_hmask)
{
        return ((old_hmask + 1) << 1) - 1;
}

static void xfrm_bydst_resize(struct net *net, int dir)
{
        unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
        unsigned int nhashmask = xfrm_new_hash_mask(hmask);
        unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head);
        struct hlist_head *odst = net->xfrm.policy_bydst[dir].table;
        struct hlist_head *ndst = xfrm_hash_alloc(nsize);
        int i;

        if (!ndst)
                return;

        write_lock_bh(&xfrm_policy_lock);

        for (i = hmask; i >= 0; i--)
                xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);

        net->xfrm.policy_bydst[dir].table = ndst;
        net->xfrm.policy_bydst[dir].hmask = nhashmask;

        write_unlock_bh(&xfrm_policy_lock);

        xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
}

static void xfrm_byidx_resize(struct net *net, int total)
{
        unsigned int hmask = net->xfrm.policy_idx_hmask;
        unsigned int nhashmask = xfrm_new_hash_mask(hmask);
        unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head);
        struct hlist_head *oidx = net->xfrm.policy_byidx;
        struct hlist_head *nidx = xfrm_hash_alloc(nsize);
        int i;

        if (!nidx)
                return;

        write_lock_bh(&xfrm_policy_lock);

        for (i = hmask; i >= 0; i--)
                xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);

        net->xfrm.policy_byidx = nidx;
        net->xfrm.policy_idx_hmask = nhashmask;

        write_unlock_bh(&xfrm_policy_lock);

        xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
}

static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total)
{
        unsigned int cnt = net->xfrm.policy_count[dir];
        unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;

        if (total)
                *total += cnt;

        if ((hmask + 1) < xfrm_policy_hashmax &&
            cnt > hmask)
                return 1;

        return 0;
}

static inline int xfrm_byidx_should_resize(struct net *net, int total)
{
        unsigned int hmask = net->xfrm.policy_idx_hmask;

        if ((hmask + 1) < xfrm_policy_hashmax &&
            total > hmask)
                return 1;

        return 0;
}

void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
{
        read_lock_bh(&xfrm_policy_lock);
        si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
        si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
        si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
        si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX];
        si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX];
        si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
        si->spdhcnt = net->xfrm.policy_idx_hmask;
        si->spdhmcnt = xfrm_policy_hashmax;
        read_unlock_bh(&xfrm_policy_lock);
}
EXPORT_SYMBOL(xfrm_spd_getinfo);

static DEFINE_MUTEX(hash_resize_mutex);
static void xfrm_hash_resize(struct work_struct *work)
{
        struct net *net = container_of(work, struct net, xfrm.policy_hash_work);
        int dir, total;

        mutex_lock(&hash_resize_mutex);

        total = 0;
        for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
                if (xfrm_bydst_should_resize(net, dir, &total))
                        xfrm_bydst_resize(net, dir);
        }
        if (xfrm_byidx_should_resize(net, total))
                xfrm_byidx_resize(net, total);

        mutex_unlock(&hash_resize_mutex);
}

/* Generate new index... KAME seems to generate them ordered by cost
 * of an absolute inpredictability of ordering of rules. This will not pass. */
static u32 xfrm_gen_index(struct net *net, int dir)
{
        static u32 idx_generator;

        for (;;) {
                struct hlist_node *entry;
                struct hlist_head *list;
                struct xfrm_policy *p;
                u32 idx;
                int found;

                idx = (idx_generator | dir);
                idx_generator += 8;
                if (idx == 0)
                        idx = 8;
                list = net->xfrm.policy_byidx + idx_hash(net, idx);
                found = 0;
                hlist_for_each_entry(p, entry, list, byidx) {
                        if (p->index == idx) {
                                found = 1;
                                break;
                        }
                }
                if (!found)
                        return idx;
        }
}

static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2)
{
        u32 *p1 = (u32 *) s1;
        u32 *p2 = (u32 *) s2;
        int len = sizeof(struct xfrm_selector) / sizeof(u32);
        int i;

        for (i = 0; i < len; i++) {
                if (p1[i] != p2[i])
                        return 1;
        }

        return 0;
}

int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
{
        struct net *net = xp_net(policy);
        struct xfrm_policy *pol;
        struct xfrm_policy *delpol;
        struct hlist_head *chain;
        struct hlist_node *entry, *newpos;
        u32 mark = policy->mark.v & policy->mark.m;

        write_lock_bh(&xfrm_policy_lock);
        chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
        delpol = NULL;
        newpos = NULL;
        hlist_for_each_entry(pol, entry, chain, bydst) {
                if (pol->type == policy->type &&
                    !selector_cmp(&pol->selector, &policy->selector) &&
                    (mark & pol->mark.m) == pol->mark.v &&
                    xfrm_sec_ctx_match(pol->security, policy->security) &&
                    !WARN_ON(delpol)) {
                        if (excl) {
                                write_unlock_bh(&xfrm_policy_lock);
                                return -EEXIST;
                        }
                        delpol = pol;
                        if (policy->priority > pol->priority)
                                continue;
                } else if (policy->priority >= pol->priority) {
                        newpos = &pol->bydst;
                        continue;
                }
                if (delpol)
                        break;
        }
        if (newpos)
                hlist_add_after(newpos, &policy->bydst);
        else
                hlist_add_head(&policy->bydst, chain);
        xfrm_pol_hold(policy);
        net->xfrm.policy_count[dir]++;
        atomic_inc(&flow_cache_genid);
        if (delpol)
                __xfrm_policy_unlink(delpol, dir);
        policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
        hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
        policy->curlft.add_time = get_seconds();
        policy->curlft.use_time = 0;
        if (!mod_timer(&policy->timer, jiffies + HZ))
                xfrm_pol_hold(policy);
        list_add(&policy->walk.all, &net->xfrm.policy_all);
        write_unlock_bh(&xfrm_policy_lock);

        if (delpol)
                xfrm_policy_kill(delpol);
        else if (xfrm_bydst_should_resize(net, dir, NULL))
                schedule_work(&net->xfrm.policy_hash_work);

        return 0;
}
EXPORT_SYMBOL(xfrm_policy_insert);

struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
                                          int dir, struct xfrm_selector *sel,
                                          struct xfrm_sec_ctx *ctx, int delete,
                                          int *err)
{
        struct xfrm_policy *pol, *ret;
        struct hlist_head *chain;
        struct hlist_node *entry;

        *err = 0;
        write_lock_bh(&xfrm_policy_lock);
        chain = policy_hash_bysel(net, sel, sel->family, dir);
        ret = NULL;
        hlist_for_each_entry(pol, entry, chain, bydst) {
                if (pol->type == type &&
                    (mark & pol->mark.m) == pol->mark.v &&
                    !selector_cmp(sel, &pol->selector) &&
                    xfrm_sec_ctx_match(ctx, pol->security)) {
                        xfrm_pol_hold(pol);
                        if (delete) {
                                *err = security_xfrm_policy_delete(
                                                                pol->security);
                                if (*err) {
                                        write_unlock_bh(&xfrm_policy_lock);
                                        return pol;
                                }
                                __xfrm_policy_unlink(pol, dir);
                        }
                        ret = pol;
                        break;
                }
        }
        write_unlock_bh(&xfrm_policy_lock);

        if (ret && delete)
                xfrm_policy_kill(ret);
        return ret;
}
EXPORT_SYMBOL(xfrm_policy_bysel_ctx);

struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
                                     int dir, u32 id, int delete, int *err)
{
        struct xfrm_policy *pol, *ret;
        struct hlist_head *chain;
        struct hlist_node *entry;

        *err = -ENOENT;
        if (xfrm_policy_id2dir(id) != dir)
                return NULL;

        *err = 0;
        write_lock_bh(&xfrm_policy_lock);
        chain = net->xfrm.policy_byidx + idx_hash(net, id);
        ret = NULL;
        hlist_for_each_entry(pol, entry, chain, byidx) {
                if (pol->type == type && pol->index == id &&
                    (mark & pol->mark.m) == pol->mark.v) {
                        xfrm_pol_hold(pol);
                        if (delete) {
                                *err = security_xfrm_policy_delete(
                                                                pol->security);
                                if (*err) {
                                        write_unlock_bh(&xfrm_policy_lock);
                                        return pol;
                                }
                                __xfrm_policy_unlink(pol, dir);
                        }
                        ret = pol;
                        break;
                }
        }
        write_unlock_bh(&xfrm_policy_lock);

        if (ret && delete)
                xfrm_policy_kill(ret);
        return ret;
}
EXPORT_SYMBOL(xfrm_policy_byid);

#ifdef CONFIG_SECURITY_NETWORK_XFRM
static inline int
xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
{
        int dir, err = 0;

        for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
                struct xfrm_policy *pol;
                struct hlist_node *entry;
                int i;

                hlist_for_each_entry(pol, entry,
                                     &net->xfrm.policy_inexact[dir], bydst) {
                        if (pol->type != type)
                                continue;
                        err = security_xfrm_policy_delete(pol->security);
                        if (err) {
                                xfrm_audit_policy_delete(pol, 0,
                                                         audit_info->loginuid,
                                                         audit_info->sessionid,
                                                         audit_info->secid);
                                return err;
                        }
                }
                for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
                        hlist_for_each_entry(pol, entry,
                                             net->xfrm.policy_bydst[dir].table + i,
                                             bydst) {
                                if (pol->type != type)
                                        continue;
                                err = security_xfrm_policy_delete(
                                                                pol->security);
                                if (err) {
                                        xfrm_audit_policy_delete(pol, 0,
                                                        audit_info->loginuid,
                                                        audit_info->sessionid,
                                                        audit_info->secid);
                                        return err;
                                }
                        }
                }
        }
        return err;
}
#else
static inline int
xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
{
        return 0;
}
#endif

int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
{
        int dir, err = 0, cnt = 0;

        write_lock_bh(&xfrm_policy_lock);

        err = xfrm_policy_flush_secctx_check(net, type, audit_info);
        if (err)
                goto out;

        for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
                struct xfrm_policy *pol;
                struct hlist_node *entry;
                int i;

        again1:
                hlist_for_each_entry(pol, entry,
                                     &net->xfrm.policy_inexact[dir], bydst) {
                        if (pol->type != type)
                                continue;
                        __xfrm_policy_unlink(pol, dir);
                        write_unlock_bh(&xfrm_policy_lock);
                        cnt++;

                        xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
                                                 audit_info->sessionid,
                                                 audit_info->secid);

                        xfrm_policy_kill(pol);

                        write_lock_bh(&xfrm_policy_lock);
                        goto again1;
                }

                for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) {
        again2:
                        hlist_for_each_entry(pol, entry,
                                             net->xfrm.policy_bydst[dir].table + i,
                                             bydst) {
                                if (pol->type != type)
                                        continue;
                                __xfrm_policy_unlink(pol, dir);
                                write_unlock_bh(&xfrm_policy_lock);
                                cnt++;

                                xfrm_audit_policy_delete(pol, 1,
                                                         audit_info->loginuid,
                                                         audit_info->sessionid,
                                                         audit_info->secid);
                                xfrm_policy_kill(pol);

                                write_lock_bh(&xfrm_policy_lock);
                                goto again2;
                        }
                }

        }
        if (!cnt)
                err = -ESRCH;
out:
        write_unlock_bh(&xfrm_policy_lock);
        return err;
}
EXPORT_SYMBOL(xfrm_policy_flush);

int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
                     int (*func)(struct xfrm_policy *, int, int, void*),
                     void *data)
{
        struct xfrm_policy *pol;
        struct xfrm_policy_walk_entry *x;
        int error = 0;

        if (walk->type >= XFRM_POLICY_TYPE_MAX &&
            walk->type != XFRM_POLICY_TYPE_ANY)
                return -EINVAL;

        if (list_empty(&walk->walk.all) && walk->seq != 0)
                return 0;

        write_lock_bh(&xfrm_policy_lock);
        if (list_empty(&walk->walk.all))
                x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
        else
                x = list_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all);
        list_for_each_entry_from(x, &net->xfrm.policy_all, all) {
                if (x->dead)
                        continue;
                pol = container_of(x, struct xfrm_policy, walk);
                if (walk->type != XFRM_POLICY_TYPE_ANY &&
                    walk->type != pol->type)
                        continue;
                error = func(pol, xfrm_policy_id2dir(pol->index),
                             walk->seq, data);
                if (error) {
                        list_move_tail(&walk->walk.all, &x->all);
                        goto out;
                }
                walk->seq++;
        }
        if (walk->seq == 0) {
                error = -ENOENT;
                goto out;
        }
        list_del_init(&walk->walk.all);
out:
        write_unlock_bh(&xfrm_policy_lock);
        return error;
}
EXPORT_SYMBOL(xfrm_policy_walk);

void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type)
{
        INIT_LIST_HEAD(&walk->walk.all);
        walk->walk.dead = 1;
        walk->type = type;
        walk->seq = 0;
}
EXPORT_SYMBOL(xfrm_policy_walk_init);

void xfrm_policy_walk_done(struct xfrm_policy_walk *walk)
{
        if (list_empty(&walk->walk.all))
                return;

        write_lock_bh(&xfrm_policy_lock);
        list_del(&walk->walk.all);
        write_unlock_bh(&xfrm_policy_lock);
}
EXPORT_SYMBOL(xfrm_policy_walk_done);

/*
 * Find policy to apply to this flow.
 *
 * Returns 0 if policy found, else an -errno.
 */
static int xfrm_policy_match(const struct xfrm_policy *pol,
                             const struct flowi *fl,
                             u8 type, u16 family, int dir)
{
        const struct xfrm_selector *sel = &pol->selector;
        int match, ret = -ESRCH;

        if (pol->family != family ||
            (fl->flowi_mark & pol->mark.m) != pol->mark.v ||
            pol->type != type)
                return ret;

        match = xfrm_selector_match(sel, fl, family);
        if (match)
                ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid,
                                                  dir);

        return ret;
}

static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
                                                     const struct flowi *fl,
                                                     u16 family, u8 dir)
{
        int err;
        struct xfrm_policy *pol, *ret;
        const xfrm_address_t *daddr, *saddr;
        struct hlist_node *entry;
        struct hlist_head *chain;
        u32 priority = ~0U;

        daddr = xfrm_flowi_daddr(fl, family);
        saddr = xfrm_flowi_saddr(fl, family);
        if (unlikely(!daddr || !saddr))
                return NULL;

        read_lock_bh(&xfrm_policy_lock);
        chain = policy_hash_direct(net, daddr, saddr, family, dir);
        ret = NULL;
        hlist_for_each_entry(pol, entry, chain, bydst) {
                err = xfrm_policy_match(pol, fl, type, family, dir);
                if (err) {
                        if (err == -ESRCH)
                                continue;
                        else {
                                ret = ERR_PTR(err);
                                goto fail;
                        }
                } else {
                        ret = pol;
                        priority = ret->priority;
                        break;
                }
        }
        chain = &net->xfrm.policy_inexact[dir];
        hlist_for_each_entry(pol, entry, chain, bydst) {
                err = xfrm_policy_match(pol, fl, type, family, dir);
                if (err) {
                        if (err == -ESRCH)
                                continue;
                        else {
                                ret = ERR_PTR(err);
                                goto fail;
                        }
                } else if (pol->priority < priority) {
                        ret = pol;
                        break;
                }
        }
        if (ret)
                xfrm_pol_hold(ret);
fail:
        read_unlock_bh(&xfrm_policy_lock);

        return ret;
}

static struct xfrm_policy *
__xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir)
{
#ifdef CONFIG_XFRM_SUB_POLICY
        struct xfrm_policy *pol;

        pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
        if (pol != NULL)
                return pol;
#endif
        return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
}

static struct flow_cache_object *
xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family,
                   u8 dir, struct flow_cache_object *old_obj, void *ctx)
{
        struct xfrm_policy *pol;

        if (old_obj)
                xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo));

        pol = __xfrm_policy_lookup(net, fl, family, dir);
        if (IS_ERR_OR_NULL(pol))
                return ERR_CAST(pol);

        /* Resolver returns two references:
         * one for cache and one for caller of flow_cache_lookup() */
        xfrm_pol_hold(pol);

        return &pol->flo;
}

static inline int policy_to_flow_dir(int dir)
{
        if (XFRM_POLICY_IN == FLOW_DIR_IN &&
            XFRM_POLICY_OUT == FLOW_DIR_OUT &&
            XFRM_POLICY_FWD == FLOW_DIR_FWD)
                return dir;
        switch (dir) {
        default:
        case XFRM_POLICY_IN:
                return FLOW_DIR_IN;
        case XFRM_POLICY_OUT:
                return FLOW_DIR_OUT;
        case XFRM_POLICY_FWD:
                return FLOW_DIR_FWD;
        }
}

static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
                                                 const struct flowi *fl)
{
        struct xfrm_policy *pol;

        read_lock_bh(&xfrm_policy_lock);
        if ((pol = sk->sk_policy[dir]) != NULL) {
                int match = xfrm_selector_match(&pol->selector, fl,
                                                sk->sk_family);
                int err = 0;

                if (match) {
                        if ((sk->sk_mark & pol->mark.m) != pol->mark.v) {
                                pol = NULL;
                                goto out;
                        }
                        err = security_xfrm_policy_lookup(pol->security,
                                                      fl->flowi_secid,
                                                      policy_to_flow_dir(dir));
                        if (!err)
                                xfrm_pol_hold(pol);
                        else if (err == -ESRCH)
                                pol = NULL;
                        else
                                pol = ERR_PTR(err);
                } else
                        pol = NULL;
        }
out:
        read_unlock_bh(&xfrm_policy_lock);
        return pol;
}

static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
{
        struct net *net = xp_net(pol);
        struct hlist_head *chain = policy_hash_bysel(net, &pol->selector,
                                                     pol->family, dir);

        list_add(&pol->walk.all, &net->xfrm.policy_all);
        hlist_add_head(&pol->bydst, chain);
        hlist_add_head(&pol->byidx, net->xfrm.policy_byidx+idx_hash(net, pol->index));
        net->xfrm.policy_count[dir]++;
        xfrm_pol_hold(pol);

        if (xfrm_bydst_should_resize(net, dir, NULL))
                schedule_work(&net->xfrm.policy_hash_work);
}

static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
                                                int dir)
{
        struct net *net = xp_net(pol);

        if (hlist_unhashed(&pol->bydst))
                return NULL;

        hlist_del(&pol->bydst);
        hlist_del(&pol->byidx);
        list_del(&pol->walk.all);
        net->xfrm.policy_count[dir]--;

        return pol;
}

int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
{
        write_lock_bh(&xfrm_policy_lock);
        pol = __xfrm_policy_unlink(pol, dir);
        write_unlock_bh(&xfrm_policy_lock);
        if (pol) {
                xfrm_policy_kill(pol);
                return 0;
        }
        return -ENOENT;
}
EXPORT_SYMBOL(xfrm_policy_delete);

int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
{
        struct net *net = xp_net(pol);
        struct xfrm_policy *old_pol;

#ifdef CONFIG_XFRM_SUB_POLICY
        if (pol && pol->type != XFRM_POLICY_TYPE_MAIN)
                return -EINVAL;
#endif

        write_lock_bh(&xfrm_policy_lock);
        old_pol = sk->sk_policy[dir];
        sk->sk_policy[dir] = pol;
        if (pol) {
                pol->curlft.add_time = get_seconds();
                pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
                __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
        }
        if (old_pol)
                /* Unlinking succeeds always. This is the only function
                 * allowed to delete or replace socket policy.
                 */
                __xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
        write_unlock_bh(&xfrm_policy_lock);

        if (old_pol) {
                xfrm_policy_kill(old_pol);
        }
        return 0;
}

static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
{
        struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);

        if (newp) {
                newp->selector = old->selector;
                if (security_xfrm_policy_clone(old->security,
                                               &newp->security)) {
                        kfree(newp);
                        return NULL;  /* ENOMEM */
                }
                newp->lft = old->lft;
                newp->curlft = old->curlft;
                newp->mark = old->mark;
                newp->action = old->action;
                newp->flags = old->flags;
                newp->xfrm_nr = old->xfrm_nr;
                newp->index = old->index;
                newp->type = old->type;
                memcpy(newp->xfrm_vec, old->xfrm_vec,
                       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
                write_lock_bh(&xfrm_policy_lock);
                __xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
                write_unlock_bh(&xfrm_policy_lock);
                xfrm_pol_put(newp);
        }
        return newp;
}

int __xfrm_sk_clone_policy(struct sock *sk)
{
        struct xfrm_policy *p0 = sk->sk_policy[0],
                           *p1 = sk->sk_policy[1];

        sk->sk_policy[0] = sk->sk_policy[1] = NULL;
        if (p0 && (sk->sk_policy[0] = clone_policy(p0, 0)) == NULL)
                return -ENOMEM;
        if (p1 && (sk->sk_policy[1] = clone_policy(p1, 1)) == NULL)
                return -ENOMEM;
        return 0;
}

static int
xfrm_get_saddr(struct net *net, xfrm_address_t *local, xfrm_address_t *remote,
               unsigned short family)
{
        int err;
        struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);

        if (unlikely(afinfo == NULL))
                return -EINVAL;
        err = afinfo->get_saddr(net, local, remote);
        xfrm_policy_put_afinfo(afinfo);
        return err;
}

/* Resolve list of templates for the flow, given policy. */

static int
xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
                      struct xfrm_state **xfrm, unsigned short family)
{
        struct net *net = xp_net(policy);
        int nx;
        int i, error;
        xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family);
        xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
        xfrm_address_t tmp;

        for (nx=0, i = 0; i < policy->xfrm_nr; i++) {
                struct xfrm_state *x;
                xfrm_address_t *remote = daddr;
                xfrm_address_t *local  = saddr;
                struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i];

                if (tmpl->mode == XFRM_MODE_TUNNEL ||
                    tmpl->mode == XFRM_MODE_BEET) {
                        remote = &tmpl->id.daddr;
                        local = &tmpl->saddr;
                        if (xfrm_addr_any(local, tmpl->encap_family)) {
                                error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family);
                                if (error)
                                        goto fail;
                                local = &tmp;
                        }
                }

                x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family);

                if (x && x->km.state == XFRM_STATE_VALID) {
                        xfrm[nx++] = x;
                        daddr = remote;
                        saddr = local;
                        continue;
                }
                if (x) {
                        error = (x->km.state == XFRM_STATE_ERROR ?
                                 -EINVAL : -EAGAIN);
                        xfrm_state_put(x);
                }
                else if (error == -ESRCH)
                        error = -EAGAIN;

                if (!tmpl->optional)
                        goto fail;
        }
        return nx;

fail:
        for (nx--; nx>=0; nx--)
                xfrm_state_put(xfrm[nx]);
        return error;
}

static int
xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
                  struct xfrm_state **xfrm, unsigned short family)
{
        struct xfrm_state *tp[XFRM_MAX_DEPTH];
        struct xfrm_state **tpp = (npols > 1) ? tp : xfrm;
        int cnx = 0;
        int error;
        int ret;
        int i;

        for (i = 0; i < npols; i++) {
                if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) {
                        error = -ENOBUFS;
                        goto fail;
                }

                ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family);
                if (ret < 0) {
                        error = ret;
                        goto fail;
                } else
                        cnx += ret;
        }

        /* found states are sorted for outbound processing */
        if (npols > 1)
                xfrm_state_sort(xfrm, tpp, cnx, family);

        return cnx;

 fail:
        for (cnx--; cnx>=0; cnx--)
                xfrm_state_put(tpp[cnx]);
        return error;

}

/* Check that the bundle accepts the flow and its components are
 * still valid.
 */

static inline int xfrm_get_tos(const struct flowi *fl, int family)
{
        struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
        int tos;

        if (!afinfo)
                return -EINVAL;

        tos = afinfo->get_tos(fl);

        xfrm_policy_put_afinfo(afinfo);

        return tos;
}

static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *flo)
{
        struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
        struct dst_entry *dst = &xdst->u.dst;

        if (xdst->route == NULL) {
                /* Dummy bundle - if it has xfrms we were not
                 * able to build bundle as template resolution failed.
                 * It means we need to try again resolving. */
                if (xdst->num_xfrms > 0)
                        return NULL;
        } else {
                /* Real bundle */
                if (stale_bundle(dst))
                        return NULL;
        }

        dst_hold(dst);
        return flo;
}

static int xfrm_bundle_flo_check(struct flow_cache_object *flo)
{
        struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
        struct dst_entry *dst = &xdst->u.dst;

        if (!xdst->route)
                return 0;
        if (stale_bundle(dst))
                return 0;

        return 1;
}

static void xfrm_bundle_flo_delete(struct flow_cache_object *flo)
{
        struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
        struct dst_entry *dst = &xdst->u.dst;

        dst_free(dst);
}

static const struct flow_cache_ops xfrm_bundle_fc_ops = {
        .get = xfrm_bundle_flo_get,
        .check = xfrm_bundle_flo_check,
        .delete = xfrm_bundle_flo_delete,
};

static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
{
        struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
        struct dst_ops *dst_ops;
        struct xfrm_dst *xdst;

        if (!afinfo)
                return ERR_PTR(-EINVAL);

        switch (family) {
        case AF_INET:
                dst_ops = &net->xfrm.xfrm4_dst_ops;
                break;
#if IS_ENABLED(CONFIG_IPV6)
        case AF_INET6:
                dst_ops = &net->xfrm.xfrm6_dst_ops;
                break;
#endif
        default:
                BUG();
        }
        xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);

        if (likely(xdst)) {
                memset(&xdst->u.rt6.rt6i_table, 0,
                        sizeof(*xdst) - sizeof(struct dst_entry));
                xdst->flo.ops = &xfrm_bundle_fc_ops;
        } else
                xdst = ERR_PTR(-ENOBUFS);

        xfrm_policy_put_afinfo(afinfo);

        return xdst;
}

static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
                                 int nfheader_len)
{
        struct xfrm_policy_afinfo *afinfo =
                xfrm_policy_get_afinfo(dst->ops->family);
        int err;

        if (!afinfo)
                return -EINVAL;

        err = afinfo->init_path(path, dst, nfheader_len);

        xfrm_policy_put_afinfo(afinfo);

        return err;
}

static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
                                const struct flowi *fl)
{
        struct xfrm_policy_afinfo *afinfo =
                xfrm_policy_get_afinfo(xdst->u.dst.ops->family);
        int err;

        if (!afinfo)
                return -EINVAL;

        err = afinfo->fill_dst(xdst, dev, fl);

        xfrm_policy_put_afinfo(afinfo);

        return err;
}


/* Allocate chain of dst_entry's, attach known xfrm's, calculate
 * all the metrics... Shortly, bundle a bundle.
 */

static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
                                            struct xfrm_state **xfrm, int nx,
                                            const struct flowi *fl,
                                            struct dst_entry *dst)
{
        struct net *net = xp_net(policy);
        unsigned long now = jiffies;
        struct net_device *dev;
        struct xfrm_mode *inner_mode;
        struct dst_entry *dst_prev = NULL;
        struct dst_entry *dst0 = NULL;
        int i = 0;
        int err;
        int header_len = 0;
        int nfheader_len = 0;
        int trailer_len = 0;
        int tos;
        int family = policy->selector.family;
        xfrm_address_t saddr, daddr;

        xfrm_flowi_addr_get(fl, &saddr, &daddr, family);

        tos = xfrm_get_tos(fl, family);
        err = tos;
        if (tos < 0)
                goto put_states;

        dst_hold(dst);

        for (; i < nx; i++) {
                struct xfrm_dst *xdst = xfrm_alloc_dst(net, family);
                struct dst_entry *dst1 = &xdst->u.dst;

                err = PTR_ERR(xdst);
                if (IS_ERR(xdst)) {
                        dst_release(dst);
                        goto put_states;
                }

                if (xfrm[i]->sel.family == AF_UNSPEC) {
                        inner_mode = xfrm_ip2inner_mode(xfrm[i],
                                                        xfrm_af2proto(family));
                        if (!inner_mode) {
                                err = -EAFNOSUPPORT;
                                dst_release(dst);
                                goto put_states;
                        }
                } else
                        inner_mode = xfrm[i]->inner_mode;

                if (!dst_prev)
                        dst0 = dst1;
                else {
                        dst_prev->child = dst_clone(dst1);
                        dst1->flags |= DST_NOHASH;
                }

                xdst->route = dst;
                dst_copy_metrics(dst1, dst);

                if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
                        family = xfrm[i]->props.family;
                        dst = xfrm_dst_lookup(xfrm[i], tos, &saddr, &daddr,
                                              family);
                        err = PTR_ERR(dst);
                        if (IS_ERR(dst))
                                goto put_states;
                } else
                        dst_hold(dst);

                dst1->xfrm = xfrm[i];
                xdst->xfrm_genid = xfrm[i]->genid;

                dst1->obsolete = -1;
                dst1->flags |= DST_HOST;
                dst1->lastuse = now;

                dst1->input = dst_discard;
                dst1->output = inner_mode->afinfo->output;

                dst1->next = dst_prev;
                dst_prev = dst1;

                header_len += xfrm[i]->props.header_len;
                if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT)
                        nfheader_len += xfrm[i]->props.header_len;
                trailer_len += xfrm[i]->props.trailer_len;
        }

        dst_prev->child = dst;
        dst0->path = dst;

        err = -ENODEV;
        dev = dst->dev;
        if (!dev)
                goto free_dst;

        /* Copy neighbour for reachability confirmation */
        dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour_noref(dst)));

        xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len);
        xfrm_init_pmtu(dst_prev);

        for (dst_prev = dst0; dst_prev != dst; dst_prev = dst_prev->child) {
                struct xfrm_dst *xdst = (struct xfrm_dst *)dst_prev;

                err = xfrm_fill_dst(xdst, dev, fl);
                if (err)
                        goto free_dst;

                dst_prev->header_len = header_len;
                dst_prev->trailer_len = trailer_len;
                header_len -= xdst->u.dst.xfrm->props.header_len;
                trailer_len -= xdst->u.dst.xfrm->props.trailer_len;
        }

out:
        return dst0;

put_states:
        for (; i < nx; i++)
                xfrm_state_put(xfrm[i]);
free_dst:
        if (dst0)
                dst_free(dst0);
        dst0 = ERR_PTR(err);
        goto out;
}

static int inline
xfrm_dst_alloc_copy(void **target, const void *src, int size)
{
        if (!*target) {
                *target = kmalloc(size, GFP_ATOMIC);
                if (!*target)
                        return -ENOMEM;
        }
        memcpy(*target, src, size);
        return 0;
}

static int inline
xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel)
{
#ifdef CONFIG_XFRM_SUB_POLICY
        struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
        return xfrm_dst_alloc_copy((void **)&(xdst->partner),
                                   sel, sizeof(*sel));
#else
        return 0;
#endif
}

static int inline
xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl)
{
#ifdef CONFIG_XFRM_SUB_POLICY
        struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
        return xfrm_dst_alloc_copy((void **)&(xdst->origin), fl, sizeof(*fl));
#else
        return 0;
#endif
}

static int xfrm_expand_policies(const struct flowi *fl, u16 family,
                                struct xfrm_policy **pols,
                                int *num_pols, int *num_xfrms)
{
        int i;

        if (*num_pols == 0 || !pols[0]) {
                *num_pols = 0;
                *num_xfrms = 0;
                return 0;
        }
        if (IS_ERR(pols[0]))
                return PTR_ERR(pols[0]);

        *num_xfrms = pols[0]->xfrm_nr;

#ifdef CONFIG_XFRM_SUB_POLICY
        if (pols[0] && pols[0]->action == XFRM_POLICY_ALLOW &&
            pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
                pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
                                                    XFRM_POLICY_TYPE_MAIN,
                                                    fl, family,
                                                    XFRM_POLICY_OUT);
                if (pols[1]) {
                        if (IS_ERR(pols[1])) {
                                xfrm_pols_put(pols, *num_pols);
                                return PTR_ERR(pols[1]);
                        }
                        (*num_pols) ++;
                        (*num_xfrms) += pols[1]->xfrm_nr;
                }
        }
#endif
        for (i = 0; i < *num_pols; i++) {
                if (pols[i]->action != XFRM_POLICY_ALLOW) {
                        *num_xfrms = -1;
                        break;
                }
        }

        return 0;

}

static struct xfrm_dst *
xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
                               const struct flowi *fl, u16 family,
                               struct dst_entry *dst_orig)
{
        struct net *net = xp_net(pols[0]);
        struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
        struct dst_entry *dst;
        struct xfrm_dst *xdst;
        int err;

        /* Try to instantiate a bundle */
        err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
        if (err <= 0) {
                if (err != 0 && err != -EAGAIN)
                        XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
                return ERR_PTR(err);
        }

        dst = xfrm_bundle_create(pols[0], xfrm, err, fl, dst_orig);
        if (IS_ERR(dst)) {
                XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
                return ERR_CAST(dst);
        }

        xdst = (struct xfrm_dst *)dst;
        xdst->num_xfrms = err;
        if (num_pols > 1)
                err = xfrm_dst_update_parent(dst, &pols[1]->selector);
        else
                err = xfrm_dst_update_origin(dst, fl);
        if (unlikely(err)) {
                dst_free(dst);
                XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
                return ERR_PTR(err);
        }

        xdst->num_pols = num_pols;
        memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
        xdst->policy_genid = atomic_read(&pols[0]->genid);

        return xdst;
}

static struct flow_cache_object *
xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
                   struct flow_cache_object *oldflo, void *ctx)
{
        struct dst_entry *dst_orig = (struct dst_entry *)ctx;
        struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
        struct xfrm_dst *xdst, *new_xdst;
        int num_pols = 0, num_xfrms = 0, i, err, pol_dead;

        /* Check if the policies from old bundle are usable */
        xdst = NULL;
        if (oldflo) {
                xdst = container_of(oldflo, struct xfrm_dst, flo);
                num_pols = xdst->num_pols;
                num_xfrms = xdst->num_xfrms;
                pol_dead = 0;
                for (i = 0; i < num_pols; i++) {
                        pols[i] = xdst->pols[i];
                        pol_dead |= pols[i]->walk.dead;
                }
                if (pol_dead) {
                        dst_free(&xdst->u.dst);
                        xdst = NULL;
                        num_pols = 0;
                        num_xfrms = 0;
                        oldflo = NULL;
                }
        }

        /* Resolve policies to use if we couldn't get them from
         * previous cache entry */
        if (xdst == NULL) {
                num_pols = 1;
                pols[0] = __xfrm_policy_lookup(net, fl, family, dir);
                err = xfrm_expand_policies(fl, family, pols,
                                           &num_pols, &num_xfrms);
                if (err < 0)
                        goto inc_error;
                if (num_pols == 0)
                        return NULL;
                if (num_xfrms <= 0)
                        goto make_dummy_bundle;
        }

        new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig);
        if (IS_ERR(new_xdst)) {
                err = PTR_ERR(new_xdst);
                if (err != -EAGAIN)
                        goto error;
                if (oldflo == NULL)
                        goto make_dummy_bundle;
                dst_hold(&xdst->u.dst);
                return oldflo;
        } else if (new_xdst == NULL) {
                num_xfrms = 0;
                if (oldflo == NULL)
                        goto make_dummy_bundle;
                xdst->num_xfrms = 0;
                dst_hold(&xdst->u.dst);
                return oldflo;
        }

        /* Kill the previous bundle */
        if (xdst) {
                /* The policies were stolen for newly generated bundle */
                xdst->num_pols = 0;
                dst_free(&xdst->u.dst);
        }

        /* Flow cache does not have reference, it dst_free()'s,
         * but we do need to return one reference for original caller */
        dst_hold(&new_xdst->u.dst);
        return &new_xdst->flo;

make_dummy_bundle:
        /* We found policies, but there's no bundles to instantiate:
         * either because the policy blocks, has no transformations or
         * we could not build template (no xfrm_states).*/
        xdst = xfrm_alloc_dst(net, family);
        if (IS_ERR(xdst)) {
                xfrm_pols_put(pols, num_pols);
                return ERR_CAST(xdst);
        }
        xdst->num_pols = num_pols;
        xdst->num_xfrms = num_xfrms;
        memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);

        dst_hold(&xdst->u.dst);
        return &xdst->flo;

inc_error:
        XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
error:
        if (xdst != NULL)
                dst_free(&xdst->u.dst);
        else
                xfrm_pols_put(pols, num_pols);
        return ERR_PTR(err);
}

static struct dst_entry *make_blackhole(struct net *net, u16 family,
                                        struct dst_entry *dst_orig)
{
        struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
        struct dst_entry *ret;

        if (!afinfo) {
                dst_release(dst_orig);
                ret = ERR_PTR(-EINVAL);
        } else {
                ret = afinfo->blackhole_route(net, dst_orig);
        }
        xfrm_policy_put_afinfo(afinfo);

        return ret;
}

/* Main function: finds/creates a bundle for given flow.
 *
 * At the moment we eat a raw IP route. Mostly to speed up lookups
 * on interfaces with disabled IPsec.
 */
struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
                              const struct flowi *fl,
                              struct sock *sk, int flags)
{
        struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
        struct flow_cache_object *flo;
        struct xfrm_dst *xdst;
        struct dst_entry *dst, *route;
        u16 family = dst_orig->ops->family;
        u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
        int i, err, num_pols, num_xfrms = 0, drop_pols = 0;

restart:
        dst = NULL;
        xdst = NULL;
        route = NULL;

        if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
                num_pols = 1;
                pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
                err = xfrm_expand_policies(fl, family, pols,
                                           &num_pols, &num_xfrms);
                if (err < 0)
                        goto dropdst;

                if (num_pols) {
                        if (num_xfrms <= 0) {
                                drop_pols = num_pols;
                                goto no_transform;
                        }

                        xdst = xfrm_resolve_and_create_bundle(
                                        pols, num_pols, fl,
                                        family, dst_orig);
                        if (IS_ERR(xdst)) {
                                xfrm_pols_put(pols, num_pols);
                                err = PTR_ERR(xdst);
                                goto dropdst;
                        } else if (xdst == NULL) {
                                num_xfrms = 0;
                                drop_pols = num_pols;
                                goto no_transform;
                        }

                        dst_hold(&xdst->u.dst);

                        spin_lock_bh(&xfrm_policy_sk_bundle_lock);
                        xdst->u.dst.next = xfrm_policy_sk_bundles;
                        xfrm_policy_sk_bundles = &xdst->u.dst;
                        spin_unlock_bh(&xfrm_policy_sk_bundle_lock);

                        route = xdst->route;
                }
        }

        if (xdst == NULL) {
                /* To accelerate a bit...  */
                if ((dst_orig->flags & DST_NOXFRM) ||
                    !net->xfrm.policy_count[XFRM_POLICY_OUT])
                        goto nopol;

                flo = flow_cache_lookup(net, fl, family, dir,
                                        xfrm_bundle_lookup, dst_orig);
                if (flo == NULL)
                        goto nopol;
                if (IS_ERR(flo)) {
                        err = PTR_ERR(flo);
                        goto dropdst;
                }
                xdst = container_of(flo, struct xfrm_dst, flo);

                num_pols = xdst->num_pols;
                num_xfrms = xdst->num_xfrms;
                memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
                route = xdst->route;
        }

        dst = &xdst->u.dst;
        if (route == NULL && num_xfrms > 0) {
                /* The only case when xfrm_bundle_lookup() returns a
                 * bundle with null route, is when the template could
                 * not be resolved. It means policies are there, but
                 * bundle could not be created, since we don't yet
                 * have the xfrm_state's. We need to wait for KM to
                 * negotiate new SA's or bail out with error.*/
                if (net->xfrm.sysctl_larval_drop) {
                        /* EREMOTE tells the caller to generate
                         * a one-shot blackhole route. */
                        dst_release(dst);
                        xfrm_pols_put(pols, drop_pols);
                        XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);

                        return make_blackhole(net, family, dst_orig);
                }
                if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) {
                        DECLARE_WAITQUEUE(wait, current);

                        add_wait_queue(&net->xfrm.km_waitq, &wait);
                        set_current_state(TASK_INTERRUPTIBLE);
                        schedule();
                        set_current_state(TASK_RUNNING);
                        remove_wait_queue(&net->xfrm.km_waitq, &wait);

                        if (!signal_pending(current)) {
                                dst_release(dst);
                                goto restart;
                        }

                        err = -ERESTART;
                } else
                        err = -EAGAIN;

                XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
                goto error;
        }

no_transform:
        if (num_pols == 0)
                goto nopol;

        if ((flags & XFRM_LOOKUP_ICMP) &&
            !(pols[0]->flags & XFRM_POLICY_ICMP)) {
                err = -ENOENT;
                goto error;
        }

        for (i = 0; i < num_pols; i++)
                pols[i]->curlft.use_time = get_seconds();

        if (num_xfrms < 0) {
                /* Prohibit the flow */
                XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
                err = -EPERM;
                goto error;
        } else if (num_xfrms > 0) {
                /* Flow transformed */
                dst_release(dst_orig);
        } else {
                /* Flow passes untransformed */
                dst_release(dst);
                dst = dst_orig;
        }
ok:
        xfrm_pols_put(pols, drop_pols);
        return dst;

nopol:
        if (!(flags & XFRM_LOOKUP_ICMP)) {
                dst = dst_orig;
                goto ok;
        }
        err = -ENOENT;
error:
        dst_release(dst);
dropdst:
        dst_release(dst_orig);
        xfrm_pols_put(pols, drop_pols);
        return ERR_PTR(err);
}
EXPORT_SYMBOL(xfrm_lookup);

static inline int
xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
{
        struct xfrm_state *x;

        if (!skb->sp || idx < 0 || idx >= skb->sp->len)
                return 0;
        x = skb->sp->xvec[idx];
        if (!x->type->reject)
                return 0;
        return x->type->reject(x, skb, fl);
}

/* When skb is transformed back to its "native" form, we have to
 * check policy restrictions. At the moment we make this in maximally
 * stupid way. Shame on me. :-) Of course, connected sockets must
 * have policy cached at them.
 */

static inline int
xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x,
              unsigned short family)
{
        if (xfrm_state_kern(x))
                return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family);
        return  x->id.proto == tmpl->id.proto &&
                (x->id.spi == tmpl->id.spi || !tmpl->id.spi) &&
                (x->props.reqid == tmpl->reqid || !tmpl->reqid) &&
                x->props.mode == tmpl->mode &&
                (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) ||
                 !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) &&
                !(x->props.mode != XFRM_MODE_TRANSPORT &&
                  xfrm_state_addr_cmp(tmpl, x, family));
}

/*
 * 0 or more than 0 is returned when validation is succeeded (either bypass
 * because of optional transport mode, or next index of the mathced secpath
 * state with the template.
 * -1 is returned when no matching template is found.
 * Otherwise "-2 - errored_index" is returned.
 */
static inline int
xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start,
               unsigned short family)
{
        int idx = start;

        if (tmpl->optional) {
                if (tmpl->mode == XFRM_MODE_TRANSPORT)
                        return start;
        } else
                start = -1;
        for (; idx < sp->len; idx++) {
                if (xfrm_state_ok(tmpl, sp->xvec[idx], family))
                        return ++idx;
                if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) {
                        if (start == -1)
                                start = -2-idx;
                        break;
                }
        }