blob: a6b58df7a70f614084f38f3591592650db5829c7 [file] [log] [blame]
/*
* 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/cpu.h>
#include <linux/audit.h>
#include <linux/rhashtable.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/xfrm.h>
#include <net/ip.h>
#ifdef CONFIG_XFRM_STATISTICS
#include <net/snmp.h>
#endif
#include "xfrm_hash.h"
#define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10))
#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
#define XFRM_MAX_QUEUE_LEN 100
struct xfrm_flo {
struct dst_entry *dst_orig;
u8 flags;
};
/* prefixes smaller than this are stored in lists, not trees. */
#define INEXACT_PREFIXLEN_IPV4 16
#define INEXACT_PREFIXLEN_IPV6 48
struct xfrm_pol_inexact_node {
struct rb_node node;
union {
xfrm_address_t addr;
struct rcu_head rcu;
};
u8 prefixlen;
struct rb_root root;
/* the policies matching this node, can be empty list */
struct hlist_head hhead;
};
/* xfrm inexact policy search tree:
* xfrm_pol_inexact_bin = hash(dir,type,family,if_id);
* |
* +---- root_d: sorted by daddr:prefix
* | |
* | xfrm_pol_inexact_node
* | |
* | +- root: sorted by saddr/prefix
* | | |
* | | xfrm_pol_inexact_node
* | | |
* | | + root: unused
* | | |
* | | + hhead: saddr:daddr policies
* | |
* | +- coarse policies and all any:daddr policies
* |
* +---- root_s: sorted by saddr:prefix
* | |
* | xfrm_pol_inexact_node
* | |
* | + root: unused
* | |
* | + hhead: saddr:any policies
* |
* +---- coarse policies and all any:any policies
*
* Lookups return four candidate lists:
* 1. any:any list from top-level xfrm_pol_inexact_bin
* 2. any:daddr list from daddr tree
* 3. saddr:daddr list from 2nd level daddr tree
* 4. saddr:any list from saddr tree
*
* This result set then needs to be searched for the policy with
* the lowest priority. If two results have same prio, youngest one wins.
*/
struct xfrm_pol_inexact_key {
possible_net_t net;
u32 if_id;
u16 family;
u8 dir, type;
};
struct xfrm_pol_inexact_bin {
struct xfrm_pol_inexact_key k;
struct rhash_head head;
/* list containing '*:*' policies */
struct hlist_head hhead;
seqcount_t count;
/* tree sorted by daddr/prefix */
struct rb_root root_d;
/* tree sorted by saddr/prefix */
struct rb_root root_s;
/* slow path below */
struct list_head inexact_bins;
struct rcu_head rcu;
};
enum xfrm_pol_inexact_candidate_type {
XFRM_POL_CAND_BOTH,
XFRM_POL_CAND_SADDR,
XFRM_POL_CAND_DADDR,
XFRM_POL_CAND_ANY,
XFRM_POL_CAND_MAX,
};
struct xfrm_pol_inexact_candidates {
struct hlist_head *res[XFRM_POL_CAND_MAX];
};
static DEFINE_SPINLOCK(xfrm_if_cb_lock);
static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
__read_mostly;
static struct kmem_cache *xfrm_dst_cache __ro_after_init;
static __read_mostly seqcount_t xfrm_policy_hash_generation;
static struct rhashtable xfrm_policy_inexact_table;
static const struct rhashtable_params xfrm_pol_inexact_params;
static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
static int stale_bundle(struct dst_entry *dst);
static int xfrm_bundle_ok(struct xfrm_dst *xdst);
static void xfrm_policy_queue_process(struct timer_list *t);
static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
int dir);
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir,
u32 if_id);
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup_rcu(struct net *net,
u8 type, u16 family, u8 dir, u32 if_id);
static struct xfrm_policy *
xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
bool excl);
static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
struct xfrm_policy *policy);
static bool
xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
struct xfrm_pol_inexact_bin *b,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr);
static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy)
{
return refcount_inc_not_zero(&policy->refcnt);
}
static inline bool
__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 bool
__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);
}
bool 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 false;
}
static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family)
{
const struct xfrm_policy_afinfo *afinfo;
if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo)))
return NULL;
rcu_read_lock();
afinfo = rcu_dereference(xfrm_policy_afinfo[family]);
if (unlikely(!afinfo))
rcu_read_unlock();
return afinfo;
}
/* Called with rcu_read_lock(). */
static const struct xfrm_if_cb *xfrm_if_get_cb(void)
{
return rcu_dereference(xfrm_if_cb);
}
struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr,
int family, u32 mark)
{
const 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, oif, saddr, daddr, mark);
rcu_read_unlock();
return dst;
}
EXPORT_SYMBOL(__xfrm_dst_lookup);
static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
int tos, int oif,
xfrm_address_t *prev_saddr,
xfrm_address_t *prev_daddr,
int family, u32 mark)
{
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, oif, saddr, daddr, family, mark);
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(struct timer_list *t)
{
struct xfrm_policy *xp = from_timer(xp, t, timer);
time64_t now = ktime_get_real_seconds();
time64_t next = TIME64_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) {
time64_t 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) {
time64_t 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) {
time64_t 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) {
time64_t 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 != TIME64_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);
}
/* 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_inexact_list);
INIT_HLIST_NODE(&policy->bydst);
INIT_HLIST_NODE(&policy->byidx);
rwlock_init(&policy->lock);
refcount_set(&policy->refcnt, 1);
skb_queue_head_init(&policy->polq.hold_queue);
timer_setup(&policy->timer, xfrm_policy_timer, 0);
timer_setup(&policy->polq.hold_timer,
xfrm_policy_queue_process, 0);
}
return policy;
}
EXPORT_SYMBOL(xfrm_policy_alloc);
static void xfrm_policy_destroy_rcu(struct rcu_head *head)
{
struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu);
security_xfrm_policy_free(policy->security);
kfree(policy);
}
/* 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) || del_timer(&policy->polq.hold_timer))
BUG();
call_rcu(&policy->rcu, xfrm_policy_destroy_rcu);
}
EXPORT_SYMBOL(xfrm_policy_destroy);
/* Rule must be locked. Release descendant 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->polq.hold_timer))
xfrm_pol_put(policy);
skb_queue_purge(&policy->polq.hold_queue);
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);
}
/* calculate policy hash thresholds */
static void __get_hash_thresh(struct net *net,
unsigned short family, int dir,
u8 *dbits, u8 *sbits)
{
switch (family) {
case AF_INET:
*dbits = net->xfrm.policy_bydst[dir].dbits4;
*sbits = net->xfrm.policy_bydst[dir].sbits4;
break;
case AF_INET6:
*dbits = net->xfrm.policy_bydst[dir].dbits6;
*sbits = net->xfrm.policy_bydst[dir].sbits6;
break;
default:
*dbits = 0;
*sbits = 0;
}
}
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;
u8 dbits;
u8 sbits;
__get_hash_thresh(net, family, dir, &dbits, &sbits);
hash = __sel_hash(sel, family, hmask, dbits, sbits);
if (hash == hmask + 1)
return NULL;
return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + 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;
u8 dbits;
u8 sbits;
__get_hash_thresh(net, family, dir, &dbits, &sbits);
hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits);
return rcu_dereference_check(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash;
}
static void xfrm_dst_hash_transfer(struct net *net,
struct hlist_head *list,
struct hlist_head *ndsttable,
unsigned int nhashmask,
int dir)
{
struct hlist_node *tmp, *entry0 = NULL;
struct xfrm_policy *pol;
unsigned int h0 = 0;
u8 dbits;
u8 sbits;
redo:
hlist_for_each_entry_safe(pol, tmp, list, bydst) {
unsigned int h;
__get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
pol->family, nhashmask, dbits, sbits);
if (!entry0) {
hlist_del_rcu(&pol->bydst);
hlist_add_head_rcu(&pol->bydst, ndsttable + h);
h0 = h;
} else {
if (h != h0)
continue;
hlist_del_rcu(&pol->bydst);
hlist_add_behind_rcu(&pol->bydst, entry0);
}
entry0 = &pol->bydst;
}
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 *tmp;
struct xfrm_policy *pol;
hlist_for_each_entry_safe(pol, 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 *ndst = xfrm_hash_alloc(nsize);
struct hlist_head *odst;
int i;
if (!ndst)
return;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
write_seqcount_begin(&xfrm_policy_hash_generation);
odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock));
odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock));
for (i = hmask; i >= 0; i--)
xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
net->xfrm.policy_bydst[dir].hmask = nhashmask;
write_seqcount_end(&xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
synchronize_rcu();
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;
spin_lock_bh(&net->xfrm.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;
spin_unlock_bh(&net->xfrm.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)
{
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;
}
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; 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);
}
/* Make sure *pol can be inserted into fastbin.
* Useful to check that later insert requests will be sucessful
* (provided xfrm_policy_lock is held throughout).
*/
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
{
struct xfrm_pol_inexact_bin *bin, *prev;
struct xfrm_pol_inexact_key k = {
.family = pol->family,
.type = pol->type,
.dir = dir,
.if_id = pol->if_id,
};
struct net *net = xp_net(pol);
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
write_pnet(&k.net, net);
bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k,
xfrm_pol_inexact_params);
if (bin)
return bin;
bin = kzalloc(sizeof(*bin), GFP_ATOMIC);
if (!bin)
return NULL;
bin->k = k;
INIT_HLIST_HEAD(&bin->hhead);
bin->root_d = RB_ROOT;
bin->root_s = RB_ROOT;
seqcount_init(&bin->count);
prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
&bin->k, &bin->head,
xfrm_pol_inexact_params);
if (!prev) {
list_add(&bin->inexact_bins, &net->xfrm.inexact_bins);
return bin;
}
kfree(bin);
return IS_ERR(prev) ? NULL : prev;
}
static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr,
int family, u8 prefixlen)
{
if (xfrm_addr_any(addr, family))
return true;
if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6)
return true;
if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4)
return true;
return false;
}
static bool
xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy)
{
const xfrm_address_t *addr;
bool saddr_any, daddr_any;
u8 prefixlen;
addr = &policy->selector.saddr;
prefixlen = policy->selector.prefixlen_s;
saddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
policy->family,
prefixlen);
addr = &policy->selector.daddr;
prefixlen = policy->selector.prefixlen_d;
daddr_any = xfrm_pol_inexact_addr_use_any_list(addr,
policy->family,
prefixlen);
return saddr_any && daddr_any;
}
static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node,
const xfrm_address_t *addr, u8 prefixlen)
{
node->addr = *addr;
node->prefixlen = prefixlen;
}
static struct xfrm_pol_inexact_node *
xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen)
{
struct xfrm_pol_inexact_node *node;
node = kzalloc(sizeof(*node), GFP_ATOMIC);
if (node)
xfrm_pol_inexact_node_init(node, addr, prefixlen);
return node;
}
static int xfrm_policy_addr_delta(const xfrm_address_t *a,
const xfrm_address_t *b,
u8 prefixlen, u16 family)
{
unsigned int pdw, pbi;
int delta = 0;
switch (family) {
case AF_INET:
if (sizeof(long) == 4 && prefixlen == 0)
return ntohl(a->a4) - ntohl(b->a4);
return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) -
(ntohl(b->a4) & ((~0UL << (32 - prefixlen))));
case AF_INET6:
pdw = prefixlen >> 5;
pbi = prefixlen & 0x1f;
if (pdw) {
delta = memcmp(a->a6, b->a6, pdw << 2);
if (delta)
return delta;
}
if (pbi) {
u32 mask = ~0u << (32 - pbi);
delta = (ntohl(a->a6[pdw]) & mask) -
(ntohl(b->a6[pdw]) & mask);
}
break;
default:
break;
}
return delta;
}
static void xfrm_policy_inexact_list_reinsert(struct net *net,
struct xfrm_pol_inexact_node *n,
u16 family)
{
unsigned int matched_s, matched_d;
struct xfrm_policy *policy, *p;
matched_s = 0;
matched_d = 0;
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
struct hlist_node *newpos = NULL;
bool matches_s, matches_d;
if (!policy->bydst_reinsert)
continue;
WARN_ON_ONCE(policy->family != family);
policy->bydst_reinsert = false;
hlist_for_each_entry(p, &n->hhead, bydst) {
if (policy->priority > p->priority)
newpos = &p->bydst;
else if (policy->priority == p->priority &&
policy->pos > p->pos)
newpos = &p->bydst;
else
break;
}
if (newpos)
hlist_add_behind_rcu(&policy->bydst, newpos);
else
hlist_add_head_rcu(&policy->bydst, &n->hhead);
/* paranoia checks follow.
* Check that the reinserted policy matches at least
* saddr or daddr for current node prefix.
*
* Matching both is fine, matching saddr in one policy
* (but not daddr) and then matching only daddr in another
* is a bug.
*/
matches_s = xfrm_policy_addr_delta(&policy->selector.saddr,
&n->addr,
n->prefixlen,
family) == 0;
matches_d = xfrm_policy_addr_delta(&policy->selector.daddr,
&n->addr,
n->prefixlen,
family) == 0;
if (matches_s && matches_d)
continue;
WARN_ON_ONCE(!matches_s && !matches_d);
if (matches_s)
matched_s++;
if (matches_d)
matched_d++;
WARN_ON_ONCE(matched_s && matched_d);
}
}
static void xfrm_policy_inexact_node_reinsert(struct net *net,
struct xfrm_pol_inexact_node *n,
struct rb_root *new,
u16 family)
{
struct xfrm_pol_inexact_node *node;
struct rb_node **p, *parent;
/* we should not have another subtree here */
WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root));
restart:
parent = NULL;
p = &new->rb_node;
while (*p) {
u8 prefixlen;
int delta;
parent = *p;
node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
prefixlen = min(node->prefixlen, n->prefixlen);
delta = xfrm_policy_addr_delta(&n->addr, &node->addr,
prefixlen, family);
if (delta < 0) {
p = &parent->rb_left;
} else if (delta > 0) {
p = &parent->rb_right;
} else {
struct xfrm_policy *tmp;
hlist_for_each_entry(tmp, &n->hhead, bydst) {
tmp->bydst_reinsert = true;
hlist_del_rcu(&tmp->bydst);
}
xfrm_policy_inexact_list_reinsert(net, node, family);
if (node->prefixlen == n->prefixlen) {
kfree_rcu(n, rcu);
return;
}
rb_erase(*p, new);
kfree_rcu(n, rcu);
n = node;
n->prefixlen = prefixlen;
goto restart;
}
}
rb_link_node_rcu(&n->node, parent, p);
rb_insert_color(&n->node, new);
}
/* merge nodes v and n */
static void xfrm_policy_inexact_node_merge(struct net *net,
struct xfrm_pol_inexact_node *v,
struct xfrm_pol_inexact_node *n,
u16 family)
{
struct xfrm_pol_inexact_node *node;
struct xfrm_policy *tmp;
struct rb_node *rnode;
/* To-be-merged node v has a subtree.
*
* Dismantle it and insert its nodes to n->root.
*/
while ((rnode = rb_first(&v->root)) != NULL) {
node = rb_entry(rnode, struct xfrm_pol_inexact_node, node);
rb_erase(&node->node, &v->root);
xfrm_policy_inexact_node_reinsert(net, node, &n->root,
family);
}
hlist_for_each_entry(tmp, &v->hhead, bydst) {
tmp->bydst_reinsert = true;
hlist_del_rcu(&tmp->bydst);
}
xfrm_policy_inexact_list_reinsert(net, n, family);
}
static struct xfrm_pol_inexact_node *
xfrm_policy_inexact_insert_node(struct net *net,
struct rb_root *root,
xfrm_address_t *addr,
u16 family, u8 prefixlen, u8 dir)
{
struct xfrm_pol_inexact_node *cached = NULL;
struct rb_node **p, *parent = NULL;
struct xfrm_pol_inexact_node *node;
p = &root->rb_node;
while (*p) {
int delta;
parent = *p;
node = rb_entry(*p, struct xfrm_pol_inexact_node, node);
delta = xfrm_policy_addr_delta(addr, &node->addr,
node->prefixlen,
family);
if (delta == 0 && prefixlen >= node->prefixlen) {
WARN_ON_ONCE(cached); /* ipsec policies got lost */
return node;
}
if (delta < 0)
p = &parent->rb_left;
else
p = &parent->rb_right;
if (prefixlen < node->prefixlen) {
delta = xfrm_policy_addr_delta(addr, &node->addr,
prefixlen,
family);
if (delta)
continue;
/* This node is a subnet of the new prefix. It needs
* to be removed and re-inserted with the smaller
* prefix and all nodes that are now also covered
* by the reduced prefixlen.
*/
rb_erase(&node->node, root);
if (!cached) {
xfrm_pol_inexact_node_init(node, addr,
prefixlen);
cached = node;
} else {
/* This node also falls within the new
* prefixlen. Merge the to-be-reinserted
* node and this one.
*/
xfrm_policy_inexact_node_merge(net, node,
cached, family);
kfree_rcu(node, rcu);
}
/* restart */
p = &root->rb_node;
parent = NULL;
}
}
node = cached;
if (!node) {
node = xfrm_pol_inexact_node_alloc(addr, prefixlen);
if (!node)
return NULL;
}
rb_link_node_rcu(&node->node, parent, p);
rb_insert_color(&node->node, root);
return node;
}
static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm)
{
struct xfrm_pol_inexact_node *node;
struct rb_node *rn = rb_first(r);
while (rn) {
node = rb_entry(rn, struct xfrm_pol_inexact_node, node);
xfrm_policy_inexact_gc_tree(&node->root, rm);
rn = rb_next(rn);
if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) {
WARN_ON_ONCE(rm);
continue;
}
rb_erase(&node->node, r);
kfree_rcu(node, rcu);
}
}
static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit)
{
write_seqcount_begin(&b->count);
xfrm_policy_inexact_gc_tree(&b->root_d, net_exit);
xfrm_policy_inexact_gc_tree(&b->root_s, net_exit);
write_seqcount_end(&b->count);
if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) ||
!hlist_empty(&b->hhead)) {
WARN_ON_ONCE(net_exit);
return;
}
if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head,
xfrm_pol_inexact_params) == 0) {
list_del(&b->inexact_bins);
kfree_rcu(b, rcu);
}
}
static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
{
struct net *net = read_pnet(&b->k.net);
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
__xfrm_policy_inexact_prune_bin(b, false);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
}
static void __xfrm_policy_inexact_flush(struct net *net)
{
struct xfrm_pol_inexact_bin *bin, *t;
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins)
__xfrm_policy_inexact_prune_bin(bin, false);
}
static struct hlist_head *
xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin,
struct xfrm_policy *policy, u8 dir)
{
struct xfrm_pol_inexact_node *n;
struct net *net;
net = xp_net(policy);
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
if (xfrm_policy_inexact_insert_use_any_list(policy))
return &bin->hhead;
if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr,
policy->family,
policy->selector.prefixlen_d)) {
write_seqcount_begin(&bin->count);
n = xfrm_policy_inexact_insert_node(net,
&bin->root_s,
&policy->selector.saddr,
policy->family,
policy->selector.prefixlen_s,
dir);
write_seqcount_end(&bin->count);
if (!n)
return NULL;
return &n->hhead;
}
/* daddr is fixed */
write_seqcount_begin(&bin->count);
n = xfrm_policy_inexact_insert_node(net,
&bin->root_d,
&policy->selector.daddr,
policy->family,
policy->selector.prefixlen_d, dir);
write_seqcount_end(&bin->count);
if (!n)
return NULL;
/* saddr is wildcard */
if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr,
policy->family,
policy->selector.prefixlen_s))
return &n->hhead;
write_seqcount_begin(&bin->count);
n = xfrm_policy_inexact_insert_node(net,
&n->root,
&policy->selector.saddr,
policy->family,
policy->selector.prefixlen_s, dir);
write_seqcount_end(&bin->count);
if (!n)
return NULL;
return &n->hhead;
}
static struct xfrm_policy *
xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
{
struct xfrm_pol_inexact_bin *bin;
struct xfrm_policy *delpol;
struct hlist_head *chain;
struct net *net;
bin = xfrm_policy_inexact_alloc_bin(policy, dir);
if (!bin)
return ERR_PTR(-ENOMEM);
net = xp_net(policy);
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir);
if (!chain) {
__xfrm_policy_inexact_prune_bin(bin, false);
return ERR_PTR(-ENOMEM);
}
delpol = xfrm_policy_insert_list(chain, policy, excl);
if (delpol && excl) {
__xfrm_policy_inexact_prune_bin(bin, false);
return ERR_PTR(-EEXIST);
}
chain = &net->xfrm.policy_inexact[dir];
xfrm_policy_insert_inexact_list(chain, policy);
if (delpol)
__xfrm_policy_inexact_prune_bin(bin, false);
return delpol;
}
static void xfrm_hash_rebuild(struct work_struct *work)
{
struct net *net = container_of(work, struct net,
xfrm.policy_hthresh.work);
unsigned int hmask;
struct xfrm_policy *pol;
struct xfrm_policy *policy;
struct hlist_head *chain;
struct hlist_head *odst;
struct hlist_node *newpos;
int i;
int dir;
unsigned seq;
u8 lbits4, rbits4, lbits6, rbits6;
mutex_lock(&hash_resize_mutex);
/* read selector prefixlen thresholds */
do {
seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
lbits4 = net->xfrm.policy_hthresh.lbits4;
rbits4 = net->xfrm.policy_hthresh.rbits4;
lbits6 = net->xfrm.policy_hthresh.lbits6;
rbits6 = net->xfrm.policy_hthresh.rbits6;
} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
write_seqcount_begin(&xfrm_policy_hash_generation);
/* make sure that we can insert the indirect policies again before
* we start with destructive action.
*/
list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
struct xfrm_pol_inexact_bin *bin;
u8 dbits, sbits;
dir = xfrm_policy_id2dir(policy->index);
if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
continue;
if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
if (policy->family == AF_INET) {
dbits = rbits4;
sbits = lbits4;
} else {
dbits = rbits6;
sbits = lbits6;
}
} else {
if (policy->family == AF_INET) {
dbits = lbits4;
sbits = rbits4;
} else {
dbits = lbits6;
sbits = rbits6;
}
}
if (policy->selector.prefixlen_d < dbits ||
policy->selector.prefixlen_s < sbits)
continue;
bin = xfrm_policy_inexact_alloc_bin(policy, dir);
if (!bin)
goto out_unlock;
if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir))
goto out_unlock;
}
/* reset the bydst and inexact table in all directions */
for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
struct hlist_node *n;
hlist_for_each_entry_safe(policy, n,
&net->xfrm.policy_inexact[dir],
bydst_inexact_list)
hlist_del_init(&policy->bydst_inexact_list);
hmask = net->xfrm.policy_bydst[dir].hmask;
odst = net->xfrm.policy_bydst[dir].table;
for (i = hmask; i >= 0; i--)
INIT_HLIST_HEAD(odst + i);
if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
/* dir out => dst = remote, src = local */
net->xfrm.policy_bydst[dir].dbits4 = rbits4;
net->xfrm.policy_bydst[dir].sbits4 = lbits4;
net->xfrm.policy_bydst[dir].dbits6 = rbits6;
net->xfrm.policy_bydst[dir].sbits6 = lbits6;
} else {
/* dir in/fwd => dst = local, src = remote */
net->xfrm.policy_bydst[dir].dbits4 = lbits4;
net->xfrm.policy_bydst[dir].sbits4 = rbits4;
net->xfrm.policy_bydst[dir].dbits6 = lbits6;
net->xfrm.policy_bydst[dir].sbits6 = rbits6;
}
}
/* re-insert all policies by order of creation */
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
if (policy->walk.dead)
continue;
dir = xfrm_policy_id2dir(policy->index);
if (dir >= XFRM_POLICY_MAX) {
/* skip socket policies */
continue;
}
newpos = NULL;
chain = policy_hash_bysel(net, &policy->selector,
policy->family, dir);
hlist_del_rcu(&policy->bydst);
if (!chain) {
void *p = xfrm_policy_inexact_insert(policy, dir, 0);
WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p));
continue;
}
hlist_for_each_entry(pol, chain, bydst) {
if (policy->priority >= pol->priority)
newpos = &pol->bydst;
else
break;
}
if (newpos)
hlist_add_behind_rcu(&policy->bydst, newpos);
else
hlist_add_head_rcu(&policy->bydst, chain);
}
out_unlock:
__xfrm_policy_inexact_flush(net);
write_seqcount_end(&xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
}
void xfrm_policy_hash_rebuild(struct net *net)
{
schedule_work(&net->xfrm.policy_hthresh.work);
}
EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
/* 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, u32 index)
{
static u32 idx_generator;
for (;;) {
struct hlist_head *list;
struct xfrm_policy *p;
u32 idx;
int found;
if (!index) {
idx = (idx_generator | dir);
idx_generator += 8;
} else {
idx = index;
index = 0;
}
if (idx == 0)
idx = 8;
list = net->xfrm.policy_byidx + idx_hash(net, idx);
found = 0;
hlist_for_each_entry(p, 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;
}
static void xfrm_policy_requeue(struct xfrm_policy *old,
struct xfrm_policy *new)
{
struct xfrm_policy_queue *pq = &old->polq;
struct sk_buff_head list;
if (skb_queue_empty(&pq->hold_queue))
return;
__skb_queue_head_init(&list);
spin_lock_bh(&pq->hold_queue.lock);
skb_queue_splice_init(&pq->hold_queue, &list);
if (del_timer(&pq->hold_timer))
xfrm_pol_put(old);
spin_unlock_bh(&pq->hold_queue.lock);
pq = &new->polq;
spin_lock_bh(&pq->hold_queue.lock);
skb_queue_splice(&list, &pq->hold_queue);
pq->timeout = XFRM_QUEUE_TMO_MIN;
if (!mod_timer(&pq->hold_timer, jiffies))
xfrm_pol_hold(new);
spin_unlock_bh(&pq->hold_queue.lock);
}
static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
struct xfrm_policy *pol)
{
u32 mark = policy->mark.v & policy->mark.m;
if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
return true;
if ((mark & pol->mark.m) == pol->mark.v &&
policy->priority == pol->priority)
return true;
return false;
}
static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed)
{
const struct xfrm_pol_inexact_key *k = data;
u32 a = k->type << 24 | k->dir << 16 | k->family;
return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)),
seed);
}
static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed)
{
const struct xfrm_pol_inexact_bin *b = data;
return xfrm_pol_bin_key(&b->k, 0, seed);
}
static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct xfrm_pol_inexact_key *key = arg->key;
const struct xfrm_pol_inexact_bin *b = ptr;
int ret;
if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net)))
return -1;
ret = b->k.dir ^ key->dir;
if (ret)
return ret;
ret = b->k.type ^ key->type;
if (ret)
return ret;
ret = b->k.family ^ key->family;
if (ret)
return ret;
return b->k.if_id ^ key->if_id;
}
static const struct rhashtable_params xfrm_pol_inexact_params = {
.head_offset = offsetof(struct xfrm_pol_inexact_bin, head),
.hashfn = xfrm_pol_bin_key,
.obj_hashfn = xfrm_pol_bin_obj,
.obj_cmpfn = xfrm_pol_bin_cmp,
.automatic_shrinking = true,
};
static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
struct xfrm_policy *policy)
{
struct xfrm_policy *pol, *delpol = NULL;
struct hlist_node *newpos = NULL;
int i = 0;
hlist_for_each_entry(pol, chain, bydst_inexact_list) {
if (pol->type == policy->type &&
pol->if_id == policy->if_id &&
!selector_cmp(&pol->selector, &policy->selector) &&
xfrm_policy_mark_match(policy, pol) &&
xfrm_sec_ctx_match(pol->security, policy->security) &&
!WARN_ON(delpol)) {
delpol = pol;
if (policy->priority > pol->priority)
continue;
} else if (policy->priority >= pol->priority) {
newpos = &pol->bydst_inexact_list;
continue;
}
if (delpol)
break;
}
if (newpos)
hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
else
hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
hlist_for_each_entry(pol, chain, bydst_inexact_list) {
pol->pos = i;
i++;
}
}
static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
struct xfrm_policy *policy,
bool excl)
{
struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == policy->type &&
pol->if_id == policy->if_id &&
!selector_cmp(&pol->selector, &policy->selector) &&
xfrm_policy_mark_match(policy, pol) &&
xfrm_sec_ctx_match(pol->security, policy->security) &&
!WARN_ON(delpol)) {
if (excl)
return ERR_PTR(-EEXIST);
delpol = pol;
if (policy->priority > pol->priority)
continue;
} else if (policy->priority >= pol->priority) {
newpos = pol;
continue;
}
if (delpol)
break;
}
if (newpos)
hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
else
hlist_add_head_rcu(&policy->bydst, chain);
return delpol;
}
int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
{
struct net *net = xp_net(policy);
struct xfrm_policy *delpol;
struct hlist_head *chain;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
if (chain)
delpol = xfrm_policy_insert_list(chain, policy, excl);
else
delpol = xfrm_policy_inexact_insert(policy, dir, excl);
if (IS_ERR(delpol)) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
return PTR_ERR(delpol);
}
__xfrm_policy_link(policy, dir);
/* After previous checking, family can either be AF_INET or AF_INET6 */
if (policy->family == AF_INET)
rt_genid_bump_ipv4(net);
else
rt_genid_bump_ipv6(net);
if (delpol) {
xfrm_policy_requeue(delpol, policy);
__xfrm_policy_unlink(delpol, dir);
}
policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
policy->curlft.add_time = ktime_get_real_seconds();
policy->curlft.use_time = 0;
if (!mod_timer(&policy->timer, jiffies + HZ))
xfrm_pol_hold(policy);
spin_unlock_bh(&net->xfrm.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);
static struct xfrm_policy *
__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id,
u8 type, int dir,
struct xfrm_selector *sel,
struct xfrm_sec_ctx *ctx)
{
struct xfrm_policy *pol;
if (!chain)
return NULL;
hlist_for_each_entry(pol, chain, bydst) {
if (pol->type == type &&
pol->if_id == if_id &&
(mark & pol->mark.m) == pol->mark.v &&
!selector_cmp(sel, &pol->selector) &&
xfrm_sec_ctx_match(ctx, pol->security))
return pol;
}
return NULL;
}
struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
u8 type, int dir,
struct xfrm_selector *sel,
struct xfrm_sec_ctx *ctx, int delete,
int *err)
{
struct xfrm_pol_inexact_bin *bin = NULL;
struct xfrm_policy *pol, *ret = NULL;
struct hlist_head *chain;
*err = 0;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, sel, sel->family, dir);
if (!chain) {
struct xfrm_pol_inexact_candidates cand;
int i;
bin = xfrm_policy_inexact_lookup(net, type,
sel->family, dir, if_id);
if (!bin) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
return NULL;
}
if (!xfrm_policy_find_inexact_candidates(&cand, bin,
&sel->saddr,
&sel->daddr)) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
return NULL;
}
pol = NULL;
for (i = 0; i < ARRAY_SIZE(cand.res); i++) {
struct xfrm_policy *tmp;
tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark,
if_id, type, dir,
sel, ctx);
if (!tmp)
continue;
if (!pol || tmp->pos < pol->pos)
pol = tmp;
}
} else {
pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir,
sel, ctx);
}
if (pol) {
xfrm_pol_hold(pol);
if (delete) {
*err = security_xfrm_policy_delete(pol->security);
if (*err) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
__xfrm_policy_unlink(pol, dir);
}
ret = pol;
}
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
if (ret && delete)
xfrm_policy_kill(ret);
if (bin && delete)
xfrm_policy_inexact_prune_bin(bin);
return ret;
}
EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
u8 type, int dir, u32 id, int delete,
int *err)
{
struct xfrm_policy *pol, *ret;
struct hlist_head *chain;
*err = -ENOENT;
if (xfrm_policy_id2dir(id) != dir)
return NULL;
*err = 0;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = net->xfrm.policy_byidx + idx_hash(net, id);
ret = NULL;
hlist_for_each_entry(pol, chain, byidx) {
if (pol->type == type && pol->index == id &&
pol->if_id == if_id &&
(mark & pol->mark.m) == pol->mark.v) {
xfrm_pol_hold(pol);
if (delete) {
*err = security_xfrm_policy_delete(
pol->security);
if (*err) {
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
return pol;
}
__xfrm_policy_unlink(pol, dir);
}
ret = pol;
break;
}
}
spin_unlock_bh(&net->xfrm.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, bool task_valid)
{
struct xfrm_policy *pol;
int err = 0;
list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
if (pol->walk.dead ||
xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
pol->type != type)
continue;
err = security_xfrm_policy_delete(pol->security);
if (err) {
xfrm_audit_policy_delete(pol, 0, task_valid);
return err;
}
}
return err;
}
#else
static inline int
xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
{
return 0;
}
#endif
int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
{
int dir, err = 0, cnt = 0;
struct xfrm_policy *pol;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
err = xfrm_policy_flush_secctx_check(net, type, task_valid);
if (err)
goto out;
again:
list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
dir = xfrm_policy_id2dir(pol->index);
if (pol->walk.dead ||
dir >= XFRM_POLICY_MAX ||
pol->type != type)
continue;
__xfrm_policy_unlink(pol, dir);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
cnt++;
xfrm_audit_policy_delete(pol, 1, task_valid);
xfrm_policy_kill(pol);
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
goto again;
}
if (cnt)
__xfrm_policy_inexact_flush(net);
else
err = -ESRCH;
out:
spin_unlock_bh(&net->xfrm.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;
spin_lock_bh(&net->xfrm.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_first_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:
spin_unlock_bh(&net->xfrm.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, struct net *net)
{
if (list_empty(&walk->walk.all))
return;
spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
list_del(&walk->walk.all);
spin_unlock_bh(&net->xfrm.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, u32 if_id)
{
const struct xfrm_selector *sel = &pol->selector;
int ret = -ESRCH;
bool match;
if (pol->family != family ||
pol->if_id != if_id ||
(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_pol_inexact_node *
xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
seqcount_t *count,
const xfrm_address_t *addr, u16 family)
{
const struct rb_node *parent;
int seq;
again:
seq = read_seqcount_begin(count);
parent = rcu_dereference_raw(r->rb_node);
while (parent) {
struct xfrm_pol_inexact_node *node;
int delta;
node = rb_entry(parent, struct xfrm_pol_inexact_node, node);
delta = xfrm_policy_addr_delta(addr, &node->addr,
node->prefixlen, family);
if (delta < 0) {
parent = rcu_dereference_raw(parent->rb_left);
continue;
} else if (delta > 0) {
parent = rcu_dereference_raw(parent->rb_right);
continue;
}
return node;
}
if (read_seqcount_retry(count, seq))
goto again;
return NULL;
}
static bool
xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
struct xfrm_pol_inexact_bin *b,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
struct xfrm_pol_inexact_node *n;
u16 family;
if (!b)
return false;
family = b->k.family;
memset(cand, 0, sizeof(*cand));
cand->res[XFRM_POL_CAND_ANY] = &b->hhead;
n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr,
family);
if (n) {
cand->res[XFRM_POL_CAND_DADDR] = &n->hhead;
n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr,
family);
if (n)
cand->res[XFRM_POL_CAND_BOTH] = &n->hhead;
}
n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr,
family);
if (n)
cand->res[XFRM_POL_CAND_SADDR] = &n->hhead;
return true;
}
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family,
u8 dir, u32 if_id)
{
struct xfrm_pol_inexact_key k = {
.family = family,
.type = type,
.dir = dir,
.if_id = if_id,
};
write_pnet(&k.net, net);
return rhashtable_lookup(&xfrm_policy_inexact_table, &k,
xfrm_pol_inexact_params);
}
static struct xfrm_pol_inexact_bin *
xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family,
u8 dir, u32 if_id)
{
struct xfrm_pol_inexact_bin *bin;
lockdep_assert_held(&net->xfrm.xfrm_policy_lock);
rcu_read_lock();
bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
rcu_read_unlock();
return bin;
}
static struct xfrm_policy *
__xfrm_policy_eval_candidates(struct hlist_head *chain,
struct xfrm_policy *prefer,
const struct flowi *fl,
u8 type, u16 family, int dir, u32 if_id)
{
u32 priority = prefer ? prefer->priority : ~0u;
struct xfrm_policy *pol;
if (!chain)
return NULL;
hlist_for_each_entry_rcu(pol, chain, bydst) {
int err;
if (pol->priority > priority)
break;
err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
if (err) {
if (err != -ESRCH)
return ERR_PTR(err);
continue;
}
if (prefer) {
/* matches. Is it older than *prefer? */
if (pol->priority == priority &&
prefer->pos < pol->pos)
return prefer;
}
return pol;
}
return NULL;
}
static struct xfrm_policy *
xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand,
struct xfrm_policy *prefer,
const struct flowi *fl,
u8 type, u16 family, int dir, u32 if_id)
{
struct xfrm_policy *tmp;
int i;
for (i = 0; i < ARRAY_SIZE(cand->res); i++) {
tmp = __xfrm_policy_eval_candidates(cand->res[i],
prefer,
fl, type, family, dir,
if_id);
if (!tmp)
continue;
if (IS_ERR(tmp))
return tmp;
prefer = tmp;
}
return prefer;
}
static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
const struct flowi *fl,
u16 family, u8 dir,
u32 if_id)
{
struct xfrm_pol_inexact_candidates cand;
const xfrm_address_t *daddr, *saddr;
struct xfrm_pol_inexact_bin *bin;
struct xfrm_policy *pol, *ret;
struct hlist_head *chain;
unsigned int sequence;
int err;
daddr = xfrm_flowi_daddr(fl, family);
saddr = xfrm_flowi_saddr(fl, family);
if (unlikely(!daddr || !saddr))
return NULL;
rcu_read_lock();
retry:
do {
sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
chain = policy_hash_direct(net, daddr, saddr, family, dir);
} while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence));
ret = NULL;
hlist_for_each_entry_rcu(pol, chain, bydst) {
err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
if (err) {
if (err == -ESRCH)
continue;
else {
ret = ERR_PTR(err);
goto fail;
}
} else {
ret = pol;
break;
}
}
bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
daddr))
goto skip_inexact;
pol = xfrm_policy_eval_candidates(&cand, ret, fl, type,
family, dir, if_id);
if (pol) {
ret = pol;
if (IS_ERR(pol))
goto fail;
}
skip_inexact:
if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence))
goto retry;
if (ret && !xfrm_pol_hold_rcu(ret))
goto retry;
fail:
rcu_read_unlock();
return ret;
}
static struct xfrm_policy *xfrm_policy_lookup(struct net *net,
const struct flowi *fl,
u16 family, u8 dir, u32 if_id)
{
#ifdef CONFIG_XFRM_SUB_POLICY
struct xfrm_policy *pol;
pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family,
dir, if_id);
if (pol != NULL)
return pol;
#endif
return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family,
dir, if_id);
}
static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
const struct flowi *fl,
u16 family, u32 if_id)
{
struct xfrm_policy *pol;
rcu_read_lock();
again:
pol = rcu_dereference(sk->sk_policy[dir]);
if (pol != NULL) {
bool match;
int err = 0;
if (pol->family != family) {
pol = NULL;
goto out;
}
match = xfrm_selector_match(&pol->selector, fl, family);
if (match) {
if ((sk->sk_mark & pol->mark.m) != pol->mark.v ||
pol->if_id != if_id) {
pol = NULL;
goto out;
}
err = security_xfrm_policy_lookup(pol->security,
fl->flowi_secid,
dir);
if (!err) {
if (!xfrm_pol_hold_rcu(pol))
goto again;
} else if (err == -ESRCH) {
pol = NULL;
} else {
pol = ERR_PTR(err);
}
} else
pol = NULL;
}
out:
rcu_read_unlock();
return pol;
}
static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
{
struct net *net = xp_net(pol);
list_add(&pol->walk.all, &net->xfrm.policy_all);
net->xfrm.policy_count[dir]++;
xfrm_pol_hold(pol);
}
static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
int dir)
{
struct net *net = xp_net(pol);
if (list_empty(&pol->walk.all))
return NULL;
/* Socket policies are not hashed. */
if (!hlist_unhashed(&pol->bydst)) {
hlist_del_rcu(&pol->bydst);
hlist_del_init(&pol->bydst_inexact_list);
hlist_del(&pol->byidx);
}
list_del_init(&pol->walk.all);
net->xfrm.policy_count[dir]--;
return pol;
}
static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir)
{
__xfrm_policy_link(pol, XFRM_POLICY_MAX + dir);
}
static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir)
{
__xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir);
}
int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
{
struct net *net = xp_net(pol);
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
pol = __xfrm_policy_unlink(pol, dir);
spin_unlock_bh(&net->xfrm.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 = sock_net(sk);
struct xfrm_policy *old_pol;
#ifdef CONFIG_XFRM_SUB_POLICY
if (pol && pol->type != XFRM_POLICY_TYPE_MAIN)
return -EINVAL;
#endif
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
old_pol = rcu_dereference_protected(sk->sk_policy[dir],
lockdep_is_held(&net->xfrm.xfrm_policy_lock));
if (pol) {
pol->curlft.add_time = ktime_get_real_seconds();
pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
xfrm_sk_policy_link(pol, dir);
}
rcu_assign_pointer(sk->sk_policy[dir], pol);
if (old_pol) {
if (pol)
xfrm_policy_requeue(old_pol, pol);
/* Unlinking succeeds always. This is the only function
* allowed to delete or replace socket policy.
*/
xfrm_sk_policy_unlink(old_pol, dir);
}
spin_unlock_bh(&net->xfrm.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);
struct net *net = xp_net(old);
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->if_id = old->if_id;
newp->action = old->action;
newp->flags = old->flags;
newp->xfrm_nr = old->xfrm_nr;
newp->index = old->index;
newp->type = old->type;
newp->family = old->family;
memcpy(newp->xfrm_vec, old->xfrm_vec,
newp->xfrm_nr*sizeof(struct xfrm_tmpl));
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_sk_policy_link(newp, dir);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
xfrm_pol_put(newp);
}
return newp;
}
int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
{
const struct xfrm_policy *p;
struct xfrm_policy *np;
int i, ret = 0;
rcu_read_lock();
for (i = 0; i < 2; i++) {
p = rcu_dereference(osk->sk_policy[i]);
if (p) {
np = clone_policy(p, i);
if (unlikely(!np)) {
ret = -ENOMEM;
break;
}
rcu_assign_pointer(sk->sk_policy[i], np);
}
}
rcu_read_unlock();
return ret;
}
static int
xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
xfrm_address_t *remote, unsigned short family, u32 mark)
{
int err;
const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
if (unlikely(afinfo == NULL))
return -EINVAL;
err = afinfo->get_saddr(net, oif, local, remote, mark);
rcu_read_unlock();
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, fl->flowi_oif,
&tmp, remote,
tmpl->encap_family, 0);
if (error)
goto fail;
local = &tmp;
}
}
x = xfrm_state_find(remote, local, fl, tmpl, policy, &error,
family, policy->if_id);
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;
}
static int xfrm_get_tos(const struct flowi *fl, int family)
{
const struct xfrm_policy_afinfo *afinfo;
int tos;
afinfo = xfrm_policy_get_afinfo(family);
if (!afinfo)
return 0;
tos = afinfo->get_tos(fl);
rcu_read_unlock();
return tos;
}
static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
{
const 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, 1, DST_OBSOLETE_NONE, 0);
if (likely(xdst)) {
struct dst_entry *dst = &xdst->u.dst;
memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst));
} else
xdst = ERR_PTR(-ENOBUFS);
rcu_read_unlock();
return xdst;
}
static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
const 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);
rcu_read_unlock();
return err;
}
static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
const 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);
rcu_read_unlock();
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,
struct xfrm_dst **bundle,
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 xfrm_dst *xdst_prev = NULL;
struct xfrm_dst *xdst0 = 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);
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;
}
bundle[i] = xdst;
if (!xdst_prev)
xdst0 = xdst;
else
/* Ref count is taken during xfrm_alloc_dst()
* No need to do dst_clone() on dst1
*/
xfrm_dst_set_child(xdst_prev, &xdst->u.dst);
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;
xdst->route = dst;
dst_copy_metrics(dst1, dst);
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
__u32 mark = 0;
if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
family = xfrm[i]->props.family;
dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
&saddr, &daddr, family, mark);
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 = DST_OBSOLETE_FORCE_CHK;
dst1->flags |= DST_HOST;
dst1->lastuse = now;
dst1->input = dst_discard;
dst1->output = inner_mode->afinfo->output;
xdst_prev = xdst;
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;
}
xfrm_dst_set_child(xdst_prev, dst);
xdst0->path = dst;
err = -ENODEV;
dev = dst->dev;
if (!dev)
goto free_dst;
xfrm_init_path(xdst0, dst, nfheader_len);
xfrm_init_pmtu(bundle, nx);
for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst;
xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) {
err = xfrm_fill_dst(xdst_prev, dev, fl);
if (err)
goto free_dst;
xdst_prev->u.dst.header_len = header_len;
xdst_prev->u.dst.trailer_len = trailer_len;
header_len -= xdst_prev->u.dst.xfrm->props.header_len;
trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len;
}
return &xdst0->u.dst;
put_states:
for (; i < nx; i++)
xfrm_state_put(xfrm[i]);
free_dst:
if (xdst0)
dst_release_immediate(&xdst0->u.dst);
return ERR_PTR(err);
}
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,
pols[0]->if_id);
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 xfrm_dst *bundle[XFRM_MAX_DEPTH];
struct xfrm_dst *xdst;
struct dst_entry *dst;
int err;
/* Try to instantiate a bundle */
err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
if (err <= 0) {
if (err == 0)
return NULL;
if (err != -EAGAIN)
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
return ERR_PTR(err);
}
dst = xfrm_bundle_create(pols[0], xfrm, bundle, 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;
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 void xfrm_policy_queue_process(struct timer_list *t)
{
struct sk_buff *skb;
struct sock *sk;
struct dst_entry *dst;
struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer);
struct net *net = xp_net(pol);
struct xfrm_policy_queue *pq = &pol->polq;
struct flowi fl;
struct sk_buff_head list;
spin_lock(&pq->hold_queue.lock);
skb = skb_peek(&pq->hold_queue);
if (!skb) {
spin_unlock(&pq->hold_queue.lock);
goto out;
}
dst = skb_dst(skb);
sk = skb->sk;
xfrm_decode_session(skb, &fl, dst->ops->family);
spin_unlock(&pq->hold_queue.lock);
dst_hold(xfrm_dst_path(dst));
dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE);
if (IS_ERR(dst))
goto purge_queue;
if (dst->flags & DST_XFRM_QUEUE) {
dst_release(dst);
if (pq->timeout >= XFRM_QUEUE_TMO_MAX)
goto purge_queue;
pq->timeout = pq->timeout << 1;
if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout))
xfrm_pol_hold(pol);
goto out;
}
dst_release(dst);
__skb_queue_head_init(&list);
spin_lock(&pq->hold_queue.lock);
pq->timeout = 0;
skb_queue_splice_init(&pq->hold_queue, &list);
spin_unlock(&pq->hold_queue.lock);
while (!skb_queue_empty(&list)) {
skb = __skb_dequeue(&list);
xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
dst_hold(xfrm_dst_path(skb_dst(skb)));
dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0);
if (IS_ERR(dst)) {
kfree_skb(skb);
continue;
}
nf_reset(skb);
skb_dst_drop(skb);
skb_dst_set(skb, dst);
dst_output(net, skb->sk, skb);
}
out:
xfrm_pol_put(pol);
return;
purge_queue:
pq->timeout = 0;
skb_queue_purge(&pq->hold_queue);
xfrm_pol_put(pol);
}
static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
unsigned long sched_next;
struct dst_entry *dst = skb_dst(skb);
struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
struct xfrm_policy *pol = xdst->pols[0];
struct xfrm_policy_queue *pq = &pol->polq;
if (unlikely(skb_fclone_busy(sk, skb))) {
kfree_skb(skb);
return 0;
}
if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) {
kfree_skb(skb);
return -EAGAIN;
}
skb_dst_force(skb);
spin_lock_bh(&pq->hold_queue.lock);
if (!pq->timeout)
pq->timeout = XFRM_QUEUE_TMO_MIN;
sched_next = jiffies + pq->timeout;
if (del_timer(&pq->hold_timer)) {
if (time_before(pq->hold_timer.expires, sched_next))
sched_next = pq->hold_timer.expires;
xfrm_pol_put(pol);
}
__skb_queue_tail(&pq->hold_queue, skb);
if (!mod_timer(&pq->hold_timer, sched_next))
xfrm_pol_hold(pol);
spin_unlock_bh(&pq->hold_queue.lock);
return 0;
}
static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
struct xfrm_flo *xflo,
const struct flowi *fl,
int num_xfrms,
u16 family)
{
int err;
struct net_device *dev;
struct dst_entry *dst;
struct dst_entry *dst1;
struct xfrm_dst *xdst;
xdst = xfrm_alloc_dst(net, family);
if (IS_ERR(xdst))
return xdst;
if (!(xflo->flags & XFRM_LOOKUP_QUEUE) ||
net->xfrm.sysctl_larval_drop ||
num_xfrms <= 0)
return xdst;
dst = xflo->dst_orig;
dst1 = &xdst->u.dst;
dst_hold(dst);
xdst->route = dst;
dst_copy_metrics(dst1, dst);
dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
dst1->flags |= DST_HOST | DST_XFRM_QUEUE;
dst1->lastuse = jiffies;
dst1->input = dst_discard;
dst1->output = xdst_queue_output;
dst_hold(dst);
xfrm_dst_set_child(xdst, dst);
xdst->path = dst;
xfrm_init_path((struct xfrm_dst *)dst1, dst, 0);
err = -ENODEV;
dev = dst->dev;
if (!dev)
goto free_dst;
err = xfrm_fill_dst(xdst, dev, fl);
if (err)
goto free_dst;
out:
return xdst;
free_dst:
dst_release(dst1);
xdst = ERR_PTR(err);
goto out;
}
static struct xfrm_dst *xfrm_bundle_lookup(struct net *net,
const struct flowi *fl,
u16 family, u8 dir,
struct xfrm_flo *xflo, u32 if_id)
{
struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
int num_pols = 0, num_xfrms = 0, err;
struct xfrm_dst *xdst;
/* Resolve policies to use if we couldn't get them from
* previous cache entry */
num_pols = 1;
pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id);
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;
xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
xflo->dst_orig);
if (IS_ERR(xdst)) {
err = PTR_ERR(xdst);
if (err == -EREMOTE) {
xfrm_pols_put(pols, num_pols);
return NULL;
}
if (err != -EAGAIN)
goto error;
goto make_dummy_bundle;
} else if (xdst == NULL) {
num_xfrms = 0;
goto make_dummy_bundle;
}
return xdst;
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_create_dummy_bundle(net, xflo, fl, num_xfrms, 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);
return xdst;
inc_error:
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
error:
xfrm_pols_put(pols, num_pols);
return ERR_PTR(err);