diff options
Diffstat (limited to 'net/xfrm/xfrm_policy.c')
| -rw-r--r-- | net/xfrm/xfrm_policy.c | 2330 |
1 files changed, 1439 insertions, 891 deletions
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9fc4c315f6c..0525d78ba32 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -26,6 +26,7 @@ #include <linux/cache.h> #include <linux/audit.h> #include <net/dst.h> +#include <net/flow.h> #include <net/xfrm.h> #include <net/ip.h> #ifdef CONFIG_XFRM_STATISTICS @@ -34,58 +35,52 @@ #include "xfrm_hash.h" -int sysctl_xfrm_larval_drop __read_mostly; +#define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10)) +#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) +#define XFRM_MAX_QUEUE_LEN 100 -#ifdef CONFIG_XFRM_STATISTICS -DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics) __read_mostly; -EXPORT_SYMBOL(xfrm_statistics); -#endif - -DEFINE_MUTEX(xfrm_cfg_mutex); -EXPORT_SYMBOL(xfrm_cfg_mutex); - -static DEFINE_RWLOCK(xfrm_policy_lock); - -unsigned int xfrm_policy_count[XFRM_POLICY_MAX*2]; -EXPORT_SYMBOL(xfrm_policy_count); - -static DEFINE_RWLOCK(xfrm_policy_afinfo_lock); -static struct xfrm_policy_afinfo *xfrm_policy_afinfo[NPROTO]; +static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); +static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] + __read_mostly; static struct kmem_cache *xfrm_dst_cache __read_mostly; -static struct work_struct xfrm_policy_gc_work; -static HLIST_HEAD(xfrm_policy_gc_list); -static DEFINE_SPINLOCK(xfrm_policy_gc_lock); - -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 void xfrm_policy_queue_process(unsigned long arg); -static inline int -__xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl) +static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, + int dir); + +static inline bool +__xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { - return addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) && - addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) && - !((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) && - !((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) && - (fl->proto == sel->proto || !sel->proto) && - (fl->oif == sel->ifindex || !sel->ifindex); + 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(struct xfrm_selector *sel, struct flowi *fl) +static inline bool +__xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { - return addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) && - addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) && - !((xfrm_flowi_dport(fl) ^ sel->dport) & sel->dport_mask) && - !((xfrm_flowi_sport(fl) ^ sel->sport) & sel->sport_mask) && - (fl->proto == sel->proto || !sel->proto) && - (fl->oif == sel->ifindex || !sel->ifindex); + 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(struct xfrm_selector *sel, struct flowi *fl, - unsigned short family) +bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, + unsigned short family) { switch (family) { case AF_INET: @@ -93,28 +88,74 @@ int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, case AF_INET6: return __xfrm6_selector_match(sel, fl); } - return 0; + return false; +} + +static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) +{ + struct xfrm_policy_afinfo *afinfo; + + if (unlikely(family >= NPROTO)) + return NULL; + rcu_read_lock(); + afinfo = rcu_dereference(xfrm_policy_afinfo[family]); + if (unlikely(!afinfo)) + rcu_read_unlock(); + return afinfo; +} + +static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo) +{ + rcu_read_unlock(); +} + +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 xfrm_policy_afinfo *afinfo; struct dst_entry *dst; - if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) + if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) { saddr = x->coaddr; - if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) + daddr = prev_daddr; + } + if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) { + saddr = prev_saddr; daddr = x->coaddr; + } - afinfo = xfrm_policy_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return ERR_PTR(-EAFNOSUPPORT); + 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)); + } - dst = afinfo->dst_lookup(tos, saddr, daddr); - xfrm_policy_put_afinfo(afinfo); return dst; } @@ -128,7 +169,7 @@ static inline unsigned long make_jiffies(long secs) static void xfrm_policy_timer(unsigned long data) { - struct xfrm_policy *xp = (struct xfrm_policy*)data; + struct xfrm_policy *xp = (struct xfrm_policy *)data; unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -136,7 +177,7 @@ static void xfrm_policy_timer(unsigned long data) read_lock(&xp->lock); - if (xp->dead) + if (unlikely(xp->walk.dead)) goto out; dir = xfrm_policy_id2dir(xp->index); @@ -196,24 +237,59 @@ expired: 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(gfp_t gfp) +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); + skb_queue_head_init(&policy->polq.hold_queue); setup_timer(&policy->timer, xfrm_policy_timer, (unsigned long)policy); + setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process, + (unsigned long)policy); + policy->flo.ops = &xfrm_policy_fc_ops; } return policy; } @@ -223,49 +299,22 @@ EXPORT_SYMBOL(xfrm_policy_alloc); void xfrm_policy_destroy(struct xfrm_policy *policy) { - BUG_ON(!policy->dead); + BUG_ON(!policy->walk.dead); - BUG_ON(policy->bundles); - - if (del_timer(&policy->timer)) + if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); - security_xfrm_policy_free(policy); + security_xfrm_policy_free(policy->security); kfree(policy); } EXPORT_SYMBOL(xfrm_policy_destroy); -static void xfrm_policy_gc_kill(struct xfrm_policy *policy) -{ - struct dst_entry *dst; - - while ((dst = policy->bundles) != NULL) { - policy->bundles = dst->next; - dst_free(dst); - } - - if (del_timer(&policy->timer)) - atomic_dec(&policy->refcnt); - - if (atomic_read(&policy->refcnt) > 1) - flow_cache_flush(); - - xfrm_pol_put(policy); -} - -static void xfrm_policy_gc_task(struct work_struct *work) +static void xfrm_queue_purge(struct sk_buff_head *list) { - struct xfrm_policy *policy; - struct hlist_node *entry, *tmp; - struct hlist_head gc_list; - - spin_lock_bh(&xfrm_policy_gc_lock); - gc_list.first = xfrm_policy_gc_list.first; - INIT_HLIST_HEAD(&xfrm_policy_gc_list); - spin_unlock_bh(&xfrm_policy_gc_lock); + struct sk_buff *skb; - hlist_for_each_entry_safe(policy, entry, tmp, &gc_list, bydst) - xfrm_policy_gc_kill(policy); + while ((skb = skb_dequeue(list)) != NULL) + kfree_skb(skb); } /* Rule must be locked. Release descentant resources, announce @@ -274,84 +323,75 @@ static void xfrm_policy_gc_task(struct work_struct *work) static void xfrm_policy_kill(struct xfrm_policy *policy) { - int dead; + policy->walk.dead = 1; - write_lock_bh(&policy->lock); - dead = policy->dead; - policy->dead = 1; - write_unlock_bh(&policy->lock); + atomic_inc(&policy->genid); - if (unlikely(dead)) { - WARN_ON(1); - return; - } + if (del_timer(&policy->polq.hold_timer)) + xfrm_pol_put(policy); + xfrm_queue_purge(&policy->polq.hold_queue); - spin_lock(&xfrm_policy_gc_lock); - hlist_add_head(&policy->bydst, &xfrm_policy_gc_list); - spin_unlock(&xfrm_policy_gc_lock); + if (del_timer(&policy->timer)) + xfrm_pol_put(policy); - schedule_work(&xfrm_policy_gc_work); + xfrm_pol_put(policy); } -struct xfrm_policy_hash { - struct hlist_head *table; - unsigned int hmask; -}; - -static struct hlist_head xfrm_policy_inexact[XFRM_POLICY_MAX*2]; -static struct xfrm_policy_hash xfrm_policy_bydst[XFRM_POLICY_MAX*2] __read_mostly; -static struct hlist_head *xfrm_policy_byidx __read_mostly; -static unsigned int xfrm_idx_hmask __read_mostly; static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; -static inline unsigned int idx_hash(u32 index) +static inline unsigned int idx_hash(struct net *net, u32 index) { - return __idx_hash(index, xfrm_idx_hmask); + return __idx_hash(index, net->xfrm.policy_idx_hmask); } -static struct hlist_head *policy_hash_bysel(struct xfrm_selector *sel, unsigned short family, int dir) +static struct hlist_head *policy_hash_bysel(struct net *net, + const struct xfrm_selector *sel, + unsigned short family, int dir) { - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash = __sel_hash(sel, family, hmask); return (hash == hmask + 1 ? - &xfrm_policy_inexact[dir] : - xfrm_policy_bydst[dir].table + hash); + &net->xfrm.policy_inexact[dir] : + net->xfrm.policy_bydst[dir].table + hash); } -static struct hlist_head *policy_hash_direct(xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, int dir) +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 = xfrm_policy_bydst[dir].hmask; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash = __addr_hash(daddr, saddr, family, hmask); - return xfrm_policy_bydst[dir].table + hash; + 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 hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; redo: - hlist_for_each_entry_safe(pol, entry, tmp, list, bydst) { + hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask); if (!entry0) { - hlist_del(entry); + hlist_del(&pol->bydst); hlist_add_head(&pol->bydst, ndsttable+h); h0 = h; } else { if (h != h0) continue; - hlist_del(entry); + hlist_del(&pol->bydst); hlist_add_after(entry0, &pol->bydst); } - entry0 = entry; + entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; @@ -363,10 +403,10 @@ static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct xfrm_policy *pol; - hlist_for_each_entry_safe(pol, entry, tmp, list, byidx) { + hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); @@ -379,60 +419,60 @@ static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) return ((old_hmask + 1) << 1) - 1; } -static void xfrm_bydst_resize(int dir) +static void xfrm_bydst_resize(struct net *net, int dir) { - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + 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 = xfrm_policy_bydst[dir].table; + 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); + write_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(odst + i, ndst, nhashmask); - xfrm_policy_bydst[dir].table = ndst; - xfrm_policy_bydst[dir].hmask = nhashmask; + net->xfrm.policy_bydst[dir].table = ndst; + net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } -static void xfrm_byidx_resize(int total) +static void xfrm_byidx_resize(struct net *net, int total) { - unsigned int hmask = xfrm_idx_hmask; + 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 = xfrm_policy_byidx; + 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); + write_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); - xfrm_policy_byidx = nidx; - xfrm_idx_hmask = nhashmask; + net->xfrm.policy_byidx = nidx; + net->xfrm.policy_idx_hmask = nhashmask; - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } -static inline int xfrm_bydst_should_resize(int dir, int *total) +static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total) { - unsigned int cnt = xfrm_policy_count[dir]; - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int cnt = net->xfrm.policy_count[dir]; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; if (total) *total += cnt; @@ -444,9 +484,9 @@ static inline int xfrm_bydst_should_resize(int dir, int *total) return 0; } -static inline int xfrm_byidx_should_resize(int total) +static inline int xfrm_byidx_should_resize(struct net *net, int total) { - unsigned int hmask = xfrm_idx_hmask; + unsigned int hmask = net->xfrm.policy_idx_hmask; if ((hmask + 1) < xfrm_policy_hashmax && total > hmask) @@ -455,61 +495,65 @@ static inline int xfrm_byidx_should_resize(int total) return 0; } -void xfrm_spd_getinfo(struct xfrmk_spdinfo *si) +void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { - read_lock_bh(&xfrm_policy_lock); - si->incnt = xfrm_policy_count[XFRM_POLICY_IN]; - si->outcnt = xfrm_policy_count[XFRM_POLICY_OUT]; - si->fwdcnt = xfrm_policy_count[XFRM_POLICY_FWD]; - si->inscnt = xfrm_policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; - si->outscnt = xfrm_policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; - si->fwdscnt = xfrm_policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; - si->spdhcnt = xfrm_idx_hmask; + read_lock_bh(&net->xfrm.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); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_spd_getinfo); static DEFINE_MUTEX(hash_resize_mutex); -static void xfrm_hash_resize(struct work_struct *__unused) +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(dir, &total)) - xfrm_bydst_resize(dir); + if (xfrm_bydst_should_resize(net, dir, &total)) + xfrm_bydst_resize(net, dir); } - if (xfrm_byidx_should_resize(total)) - xfrm_byidx_resize(total); + if (xfrm_byidx_should_resize(net, total)) + xfrm_byidx_resize(net, total); mutex_unlock(&hash_resize_mutex); } -static DECLARE_WORK(xfrm_hash_work, xfrm_hash_resize); - /* 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(u8 type, int dir) +static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { 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 (!index) { + idx = (idx_generator | dir); + idx_generator += 8; + } else { + idx = index; + index = 0; + } + if (idx == 0) idx = 8; - list = xfrm_policy_byidx + idx_hash(idx); + list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; - hlist_for_each_entry(p, entry, list, byidx) { + hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; @@ -535,25 +579,68 @@ static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s 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; + + __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); + + if (skb_queue_empty(&list)) + return; + + 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; +} + 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; - struct dst_entry *gc_list; + struct hlist_node *newpos; - write_lock_bh(&xfrm_policy_lock); - chain = policy_hash_bysel(&policy->selector, policy->family, dir); + write_lock_bh(&net->xfrm.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) { + hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && !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) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return -EEXIST; } delpol = pol; @@ -571,176 +658,146 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) else hlist_add_head(&policy->bydst, chain); xfrm_pol_hold(policy); - xfrm_policy_count[dir]++; - atomic_inc(&flow_cache_genid); + net->xfrm.policy_count[dir]++; + atomic_inc(&net->xfrm.flow_cache_genid); + + /* 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) { - hlist_del(&delpol->bydst); - hlist_del(&delpol->byidx); - xfrm_policy_count[dir]--; + xfrm_policy_requeue(delpol, policy); + __xfrm_policy_unlink(delpol, dir); } - policy->index = delpol ? delpol->index : xfrm_gen_index(policy->type, dir); - hlist_add_head(&policy->byidx, xfrm_policy_byidx+idx_hash(policy->index)); + 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 = get_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); - write_unlock_bh(&xfrm_policy_lock); + list_add(&policy->walk.all, &net->xfrm.policy_all); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); - else if (xfrm_bydst_should_resize(dir, NULL)) - schedule_work(&xfrm_hash_work); - - read_lock_bh(&xfrm_policy_lock); - gc_list = NULL; - entry = &policy->bydst; - hlist_for_each_entry_continue(policy, entry, bydst) { - struct dst_entry *dst; - - write_lock(&policy->lock); - dst = policy->bundles; - if (dst) { - struct dst_entry *tail = dst; - while (tail->next) - tail = tail->next; - tail->next = gc_list; - gc_list = dst; - - policy->bundles = NULL; - } - write_unlock(&policy->lock); - } - read_unlock_bh(&xfrm_policy_lock); - - while (gc_list) { - struct dst_entry *dst = gc_list; - - gc_list = dst->next; - dst_free(dst); - } + 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(u8 type, int dir, - struct xfrm_selector *sel, +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(sel, sel->family, dir); + write_lock_bh(&net->xfrm.xfrm_policy_lock); + chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, 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); + *err = security_xfrm_policy_delete( + pol->security); if (*err) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - xfrm_policy_count[dir]--; + __xfrm_policy_unlink(pol, dir); } ret = pol; break; } } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); - if (ret && delete) { - atomic_inc(&flow_cache_genid); + if (ret && delete) xfrm_policy_kill(ret); - } return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(u8 type, int dir, u32 id, int delete, - int *err) +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 = xfrm_policy_byidx + idx_hash(id); + write_lock_bh(&net->xfrm.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) { + hlist_for_each_entry(pol, 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); + *err = security_xfrm_policy_delete( + pol->security); if (*err) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - xfrm_policy_count[dir]--; + __xfrm_policy_unlink(pol, dir); } ret = pol; break; } } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); - if (ret && delete) { - atomic_inc(&flow_cache_genid); + 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(u8 type, struct xfrm_audit *audit_info) +xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { 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, - &xfrm_policy_inexact[dir], bydst) { + hlist_for_each_entry(pol, + &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; - err = security_xfrm_policy_delete(pol); + err = security_xfrm_policy_delete(pol->security); if (err) { - xfrm_audit_policy_delete(pol, 0, - audit_info->loginuid, - audit_info->secid); + xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { - hlist_for_each_entry(pol, entry, - xfrm_policy_bydst[dir].table + i, + for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { + hlist_for_each_entry(pol, + net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) continue; - err = security_xfrm_policy_delete(pol); + err = security_xfrm_policy_delete( + pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, - audit_info->loginuid, - audit_info->secid); + task_valid); return err; } } @@ -750,162 +807,170 @@ xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) } #else static inline int -xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) +xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } #endif -int xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info) +int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { - int dir, err = 0; + int dir, err = 0, cnt = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); - err = xfrm_policy_flush_secctx_check(type, audit_info); + err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) goto out; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; - struct hlist_node *entry; - int i, killed; + int i; - killed = 0; again1: - hlist_for_each_entry(pol, entry, - &xfrm_policy_inexact[dir], bydst) { + hlist_for_each_entry(pol, + &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - write_unlock_bh(&xfrm_policy_lock); + __xfrm_policy_unlink(pol, dir); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); + cnt++; - xfrm_audit_policy_delete(pol, 1, audit_info->loginuid, - audit_info->secid); + xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); - killed++; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); goto again1; } - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { again2: - hlist_for_each_entry(pol, entry, - xfrm_policy_bydst[dir].table + i, + hlist_for_each_entry(pol, + net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) continue; - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - write_unlock_bh(&xfrm_policy_lock); + __xfrm_policy_unlink(pol, dir); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); + cnt++; - xfrm_audit_policy_delete(pol, 1, - audit_info->loginuid, - audit_info->secid); + xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); - killed++; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); goto again2; } } - xfrm_policy_count[dir] -= killed; } - atomic_inc(&flow_cache_genid); + if (!cnt) + err = -ESRCH; out: - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); -int xfrm_policy_walk(u8 type, int (*func)(struct xfrm_policy *, int, int, void*), +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, *last = NULL; - struct hlist_node *entry; - int dir, last_dir = 0, count, error; + struct xfrm_policy *pol; + struct xfrm_policy_walk_entry *x; + int error = 0; - read_lock_bh(&xfrm_policy_lock); - count = 0; + if (walk->type >= XFRM_POLICY_TYPE_MAX && + walk->type != XFRM_POLICY_TYPE_ANY) + return -EINVAL; - for (dir = 0; dir < 2*XFRM_POLICY_MAX; dir++) { - struct hlist_head *table = xfrm_policy_bydst[dir].table; - int i; + if (list_empty(&walk->walk.all) && walk->seq != 0) + return 0; - hlist_for_each_entry(pol, entry, - &xfrm_policy_inexact[dir], bydst) { - if (pol->type != type) - continue; - if (last) { - error = func(last, last_dir % XFRM_POLICY_MAX, - count, data); - if (error) - goto out; - } - last = pol; - last_dir = dir; - count++; - } - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { - hlist_for_each_entry(pol, entry, table + i, bydst) { - if (pol->type != type) - continue; - if (last) { - error = func(last, last_dir % XFRM_POLICY_MAX, - count, data); - if (error) - goto out; - } - last = pol; - last_dir = dir; - count++; - } + write_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_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 (count == 0) { + if (walk->seq == 0) { error = -ENOENT; goto out; } - error = func(last, last_dir % XFRM_POLICY_MAX, 0, data); + list_del_init(&walk->walk.all); out: - read_unlock_bh(&xfrm_policy_lock); + write_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; + + write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ + list_del(&walk->walk.all); + write_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(struct xfrm_policy *pol, struct flowi *fl, +static int xfrm_policy_match(const struct xfrm_policy *pol, + const struct flowi *fl, u8 type, u16 family, int dir) { - struct xfrm_selector *sel = &pol->selector; - int match, ret = -ESRCH; + const struct xfrm_selector *sel = &pol->selector; + int ret = -ESRCH; + bool match; 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, fl->secid, dir); + ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, + dir); return ret; } -static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, +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; - xfrm_address_t *daddr, *saddr; - struct hlist_node *entry; + const xfrm_address_t *daddr, *saddr; struct hlist_head *chain; u32 priority = ~0U; @@ -914,10 +979,10 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, if (unlikely(!daddr || !saddr)) return NULL; - read_lock_bh(&xfrm_policy_lock); - chain = policy_hash_direct(daddr, saddr, family, dir); + read_lock_bh(&net->xfrm.xfrm_policy_lock); + chain = policy_hash_direct(net, daddr, saddr, family, dir); ret = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -932,8 +997,8 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, break; } } - chain = &xfrm_policy_inexact[dir]; - hlist_for_each_entry(pol, entry, chain, bydst) { + chain = &net->xfrm.policy_inexact[dir]; + hlist_for_each_entry(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -950,37 +1015,60 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, if (ret) xfrm_pol_hold(ret); fail: - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } -static int xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, - void **objp, atomic_t **obj_refp) +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; - int err = 0; -#ifdef CONFIG_XFRM_SUB_POLICY - pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_SUB, fl, family, dir); - if (IS_ERR(pol)) { - err = PTR_ERR(pol); - pol = NULL; - } - if (pol || err) - goto end; + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); + if (pol != NULL) + return pol; #endif - pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, fl, family, dir); - if (IS_ERR(pol)) { - err = PTR_ERR(pol); - pol = NULL; + return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); +} + +static int flow_to_policy_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 FLOW_DIR_IN: + return XFRM_POLICY_IN; + case FLOW_DIR_OUT: + return XFRM_POLICY_OUT; + case FLOW_DIR_FWD: + return XFRM_POLICY_FWD; } -#ifdef CONFIG_XFRM_SUB_POLICY -end: -#endif - if ((*objp = (void *) pol) != NULL) - *obj_refp = &pol->refcnt; - return err; +} + +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, flow_to_policy_dir(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) @@ -1000,19 +1088,26 @@ static inline int policy_to_flow_dir(int dir) } } -static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl) +static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, + const struct flowi *fl) { struct xfrm_policy *pol; + struct net *net = sock_net(sk); - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); if ((pol = sk->sk_policy[dir]) != NULL) { - int match = xfrm_selector_match(&pol->selector, fl, - sk->sk_family); + bool match = xfrm_selector_match(&pol->selector, fl, + sk->sk_family); int err = 0; if (match) { - err = security_xfrm_policy_lookup(pol, fl->secid, - policy_to_flow_dir(dir)); + 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) @@ -1022,45 +1117,51 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struc } else pol = NULL; } - read_unlock_bh(&xfrm_policy_lock); +out: + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { - struct hlist_head *chain = policy_hash_bysel(&pol->selector, + 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, xfrm_policy_byidx+idx_hash(pol->index)); - xfrm_policy_count[dir]++; + 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(dir, NULL)) - schedule_work(&xfrm_hash_work); + 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_init(&pol->bydst); hlist_del(&pol->byidx); - xfrm_policy_count[dir]--; + 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); + struct net *net = xp_net(pol); + + write_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { - if (dir < XFRM_POLICY_MAX) - atomic_inc(&flow_cache_genid); xfrm_policy_kill(pol); return 0; } @@ -1070,6 +1171,7 @@ 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 @@ -1077,17 +1179,24 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) return -EINVAL; #endif - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.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(pol->type, XFRM_POLICY_MAX+dir); + pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir); } - if (old_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_policy_unlink(old_pol, XFRM_POLICY_MAX+dir); - write_unlock_bh(&xfrm_policy_lock); + } + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); @@ -1095,18 +1204,21 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) return 0; } -static struct xfrm_policy *clone_policy(struct xfrm_policy *old, int dir) +static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { - struct xfrm_policy *newp = xfrm_policy_alloc(GFP_ATOMIC); + 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, newp)) { + 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; @@ -1114,9 +1226,9 @@ static struct xfrm_policy *clone_policy(struct xfrm_policy *old, int dir) newp->type = old->type; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); __xfrm_policy_link(newp, XFRM_POLICY_MAX+dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; @@ -1136,7 +1248,7 @@ int __xfrm_sk_clone_policy(struct sock *sk) } static int -xfrm_get_saddr(xfrm_address_t *local, xfrm_address_t *remote, +xfrm_get_saddr(struct net *net, xfrm_address_t *local, xfrm_address_t *remote, unsigned short family) { int err; @@ -1144,7 +1256,7 @@ xfrm_get_saddr(xfrm_address_t *local, xfrm_address_t *remote, if (unlikely(afinfo == NULL)) return -EINVAL; - err = afinfo->get_saddr(local, remote); + err = afinfo->get_saddr(net, local, remote); xfrm_policy_put_afinfo(afinfo); return err; } @@ -1152,17 +1264,17 @@ xfrm_get_saddr(xfrm_address_t *local, xfrm_address_t *remote, /* Resolve list of templates for the flow, given policy. */ static int -xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, - struct xfrm_state **xfrm, - unsigned short family) +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++) { + for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; @@ -1172,9 +1284,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; - family = tmpl->encap_family; - if (xfrm_addr_any(local, family)) { - error = xfrm_get_saddr(&tmp, remote, family); + if (xfrm_addr_any(local, tmpl->encap_family)) { + error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family); if (error) goto fail; local = &tmp; @@ -1193,6 +1304,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); + } else if (error == -ESRCH) { + error = -EAGAIN; } if (!tmpl->optional) @@ -1201,15 +1314,14 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, return nx; fail: - for (nx--; nx>=0; nx--) + for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } static int -xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, - struct xfrm_state **xfrm, - unsigned short family) +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; @@ -1239,7 +1351,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, return cnx; fail: - for (cnx--; cnx>=0; cnx--) + for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; @@ -1249,19 +1361,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, * still valid. */ -static struct dst_entry * -xfrm_find_bundle(struct flowi *fl, struct xfrm_policy *policy, unsigned short family) -{ - struct dst_entry *x; - struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return ERR_PTR(-EINVAL); - x = afinfo->find_bundle(fl, policy); - xfrm_policy_put_afinfo(afinfo); - return x; -} - -static inline int xfrm_get_tos(struct flowi *fl, int family) +static inline int xfrm_get_tos(const struct flowi *fl, int family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); int tos; @@ -1276,15 +1376,88 @@ static inline int xfrm_get_tos(struct flowi *fl, int family) return tos; } -static inline struct xfrm_dst *xfrm_alloc_dst(int family) +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 if (dst->flags & DST_XFRM_QUEUE) { + 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); - xdst = dst_alloc(afinfo->dst_ops) ?: ERR_PTR(-ENOBUFS); + 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, DST_OBSOLETE_NONE, 0); + + if (likely(xdst)) { + struct dst_entry *dst = &xdst->u.dst; + + memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst)); + xdst->flo.ops = &xfrm_bundle_fc_ops; + if (afinfo->init_dst) + afinfo->init_dst(net, xdst); + } else + xdst = ERR_PTR(-ENOBUFS); xfrm_policy_put_afinfo(afinfo); @@ -1308,7 +1481,8 @@ static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, return err; } -static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev) +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); @@ -1317,24 +1491,27 @@ static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev) if (!afinfo) return -EINVAL; - err = afinfo->fill_dst(xdst, dev); + 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, - struct flowi *fl, + 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; @@ -1344,6 +1521,9 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, 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; @@ -1353,7 +1533,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_hold(dst); for (; i < nx; i++) { - struct xfrm_dst *xdst = xfrm_alloc_dst(family); + struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); @@ -1362,6 +1542,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, 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 { @@ -1370,11 +1561,12 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, } xdst->route = dst; - memcpy(&dst1->metrics, &dst->metrics, sizeof(dst->metrics)); + 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, family); + dst = xfrm_dst_lookup(xfrm[i], tos, &saddr, &daddr, + family); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; @@ -1382,14 +1574,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_hold(dst); dst1->xfrm = xfrm[i]; - xdst->genid = xfrm[i]->genid; + xdst->xfrm_genid = xfrm[i]->genid; - dst1->obsolete = -1; + dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->flags |= DST_HOST; dst1->lastuse = now; dst1->input = dst_discard; - dst1->output = xfrm[i]->outer_mode->afinfo->output; + dst1->output = inner_mode->afinfo->output; dst1->next = dst_prev; dst_prev = dst1; @@ -1408,16 +1600,13 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (!dev) goto free_dst; - /* Copy neighbout for reachability confirmation */ - dst0->neighbour = neigh_clone(dst->neighbour); - 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); + err = xfrm_fill_dst(xdst, dev, fl); if (err) goto free_dst; @@ -1440,20 +1629,22 @@ free_dst: goto out; } -static int inline -xfrm_dst_alloc_copy(void **target, void *src, int size) +#ifdef CONFIG_XFRM_SUB_POLICY +static int 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; } +#endif -static int inline -xfrm_dst_update_parent(struct dst_entry *dst, struct xfrm_selector *sel) +static int 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; @@ -1464,8 +1655,8 @@ xfrm_dst_update_parent(struct dst_entry *dst, struct xfrm_selector *sel) #endif } -static int inline -xfrm_dst_update_origin(struct dst_entry *dst, struct flowi *fl) +static int 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; @@ -1475,276 +1666,537 @@ xfrm_dst_update_origin(struct dst_entry *dst, struct flowi *fl) #endif } -static int stale_bundle(struct dst_entry *dst); +static int xfrm_expand_policies(const struct flowi *fl, u16 family, + struct xfrm_policy **pols, + int *num_pols, int *num_xfrms) +{ + int i; -/* 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. - */ -int __xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, - struct sock *sk, int flags) + 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 xfrm_policy *policy; - struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; - int npols; - int pol_dead; - int xfrm_nr; - int pi; + struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; - struct dst_entry *dst, *dst_orig = *dst_p; - int nx = 0; + struct dst_entry *dst; + struct xfrm_dst *xdst; int err; - u32 genid; - u16 family; - u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); -restart: - genid = atomic_read(&flow_cache_genid); - policy = NULL; - for (pi = 0; pi < ARRAY_SIZE(pols); pi++) - pols[pi] = NULL; - npols = 0; - pol_dead = 0; - xfrm_nr = 0; + /* 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); + } - if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { - policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); - err = PTR_ERR(policy); - if (IS_ERR(policy)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLERROR); - goto dropdst; - } + 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); } - if (!policy) { - /* To accelerate a bit... */ - if ((dst_orig->flags & DST_NOXFRM) || - !xfrm_policy_count[XFRM_POLICY_OUT]) - goto nopol; + 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); + } - policy = flow_cache_lookup(fl, dst_orig->ops->family, - dir, xfrm_policy_lookup); - err = PTR_ERR(policy); - if (IS_ERR(policy)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLERROR); - goto dropdst; - } + 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(unsigned long arg) +{ + int err = 0; + struct sk_buff *skb; + struct sock *sk; + struct dst_entry *dst; + struct xfrm_policy *pol = (struct xfrm_policy *)arg; + 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); - if (!policy) - goto nopol; + dst_hold(dst->path); + dst = xfrm_lookup(xp_net(pol), dst->path, &fl, + sk, 0); + if (IS_ERR(dst)) + goto purge_queue; - family = dst_orig->ops->family; - pols[0] = policy; - npols ++; - xfrm_nr += pols[0]->xfrm_nr; + if (dst->flags & DST_XFRM_QUEUE) { + dst_release(dst); - err = -ENOENT; - if ((flags & XFRM_LOOKUP_ICMP) && !(policy->flags & XFRM_POLICY_ICMP)) - goto error; + if (pq->timeout >= XFRM_QUEUE_TMO_MAX) + goto purge_queue; - policy->curlft.use_time = get_seconds(); + pq->timeout = pq->timeout << 1; + if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) + xfrm_pol_hold(pol); + goto out; + } - switch (policy->action) { - default: - case XFRM_POLICY_BLOCK: - /* Prohibit the flow */ - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLBLOCK); - err = -EPERM; - goto error; + dst_release(dst); - case XFRM_POLICY_ALLOW: -#ifndef CONFIG_XFRM_SUB_POLICY - if (policy->xfrm_nr == 0) { - /* Flow passes not transformed. */ - xfrm_pol_put(policy); - return 0; - } -#endif + __skb_queue_head_init(&list); - /* Try to find matching bundle. - * - * LATER: help from flow cache. It is optional, this - * is required only for output policy. - */ - dst = xfrm_find_bundle(fl, policy, family); + 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(skb_dst(skb)->path); + dst = xfrm_lookup(xp_net(pol), skb_dst(skb)->path, + &fl, skb->sk, 0); if (IS_ERR(dst)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - err = PTR_ERR(dst); - goto error; + kfree_skb(skb); + continue; } - if (dst) - break; + nf_reset(skb); + skb_dst_drop(skb); + skb_dst_set(skb, dst); -#ifdef CONFIG_XFRM_SUB_POLICY - if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { - pols[1] = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, - fl, family, - XFRM_POLICY_OUT); - if (pols[1]) { - if (IS_ERR(pols[1])) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLERROR); - err = PTR_ERR(pols[1]); - goto error; - } - if (pols[1]->action == XFRM_POLICY_BLOCK) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLBLOCK); - err = -EPERM; - goto error; - } - npols ++; - xfrm_nr += pols[1]->xfrm_nr; - } - } + err = dst_output(skb); + } - /* - * Because neither flowi nor bundle information knows about - * transformation template size. On more than one policy usage - * we can realize whether all of them is bypass or not after - * they are searched. See above not-transformed bypass - * is surrounded by non-sub policy configuration, too. - */ - if (xfrm_nr == 0) { - /* Flow passes not transformed. */ - xfrm_pols_put(pols, npols); - return 0; - } +out: + xfrm_pol_put(pol); + return; -#endif - nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); - - if (unlikely(nx<0)) { - err = nx; - if (err == -EAGAIN && sysctl_xfrm_larval_drop) { - /* EREMOTE tells the caller to generate - * a one-shot blackhole route. - */ - XFRM_INC_STATS(LINUX_MIB_XFRMOUTNOSTATES); - xfrm_pol_put(policy); - return -EREMOTE; - } - if (err == -EAGAIN && (flags & XFRM_LOOKUP_WAIT)) { - DECLARE_WAITQUEUE(wait, current); +purge_queue: + pq->timeout = 0; + xfrm_queue_purge(&pq->hold_queue); + xfrm_pol_put(pol); +} - add_wait_queue(&km_waitq, &wait); - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - set_current_state(TASK_RUNNING); - remove_wait_queue(&km_waitq, &wait); +static int xdst_queue_output(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; + const struct sk_buff *fclone = skb + 1; - nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); + if (unlikely(skb->fclone == SKB_FCLONE_ORIG && + fclone->fclone == SKB_FCLONE_CLONE)) { + kfree_skb(skb); + return 0; + } - if (nx == -EAGAIN && signal_pending(current)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTNOSTATES); - err = -ERESTART; - goto error; - } - if (nx == -EAGAIN || - genid != atomic_read(&flow_cache_genid)) { - xfrm_pols_put(pols, npols); - goto restart; - } - err = nx; - } - if (err < 0) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTNOSTATES); - goto error; - } - } - if (nx == 0) { - /* Flow passes not transformed. */ - xfrm_pols_put(pols, npols); - return 0; - } + if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { + kfree_skb(skb); + return -EAGAIN; + } - dst = xfrm_bundle_create(policy, xfrm, nx, fl, dst_orig); - err = PTR_ERR(dst); - if (IS_ERR(dst)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLEGENERROR); - goto error; - } + skb_dst_force(skb); - for (pi = 0; pi < npols; pi++) { - read_lock_bh(&pols[pi]->lock); - pol_dead |= pols[pi]->dead; - read_unlock_bh(&pols[pi]->lock); - } + spin_lock_bh(&pq->hold_queue.lock); - write_lock_bh(&policy->lock); - if (unlikely(pol_dead || stale_bundle(dst))) { - /* Wow! While we worked on resolving, this - * policy has gone. Retry. It is not paranoia, - * we just cannot enlist new bundle to dead object. - * We can't enlist stable bundles either. - */ - write_unlock_bh(&policy->lock); - if (dst) - dst_free(dst); - - if (pol_dead) - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLDEAD); - else - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - err = -EHOSTUNREACH; - goto error; - } + if (!pq->timeout) + pq->timeout = XFRM_QUEUE_TMO_MIN; - if (npols > 1) - err = xfrm_dst_update_parent(dst, &pols[1]->selector); - else - err = xfrm_dst_update_origin(dst, fl); - if (unlikely(err)) { - write_unlock_bh(&policy->lock); - if (dst) - dst_free(dst); - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - goto error; - } + sched_next = jiffies + pq->timeout; - dst->next = policy->bundles; - policy->bundles = dst; - dst_hold(dst); - write_unlock_bh(&policy->lock); + 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); } - *dst_p = dst; - dst_release(dst_orig); - xfrm_pols_put(pols, npols); + + __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 dst_entry *dst, + const struct flowi *fl, + int num_xfrms, + u16 family) +{ + int err; + struct net_device *dev; + struct dst_entry *dst1; + struct xfrm_dst *xdst; + + xdst = xfrm_alloc_dst(net, family); + if (IS_ERR(xdst)) + return xdst; + + if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0) + return xdst; + + 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); + dst1->child = dst; + dst1->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 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, + flow_to_policy_dir(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_create_dummy_bundle(net, dst_orig, 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); + + dst_hold(&xdst->u.dst); + return &xdst->flo; + +inc_error: + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: - xfrm_pols_put(pols, npols); -dropdst: - dst_release(dst_orig); - *dst_p = NULL; - return err; + if (xdst != NULL) + dst_free(&xdst->u.dst); + else + xfrm_pols_put(pols, num_pols); + return ERR_PTR(err); +} -nopol: - err = -ENOENT; - if (flags & XFRM_LOOKUP_ICMP) - goto dropdst; - return 0; +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); + return ERR_PTR(-EINVAL); + } else { + ret = afinfo->blackhole_route(net, dst_orig); + } + xfrm_policy_put_afinfo(afinfo); + + return ret; } -EXPORT_SYMBOL(__xfrm_lookup); -int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, - struct sock *sk, int flags) +/* 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) { - int err = __xfrm_lookup(dst_p, fl, sk, 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; + + 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); + xdst->u.dst.flags |= DST_NOCACHE; + 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) { + dst_release(dst); + xfrm_pols_put(pols, drop_pols); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); + + return make_blackhole(net, family, dst_orig); + } - if (err == -EREMOTE) { - dst_release(*dst_p); - *dst_p = NULL; err = -EAGAIN; + + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); + goto error; } - return err; +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); + if (dst && dst->xfrm && + dst->xfrm->props.mode == XFRM_MODE_TUNNEL) + dst->flags |= DST_XFRM_TUNNEL; + 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, struct flowi *fl) +xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { struct xfrm_state *x; @@ -1763,7 +2215,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, struct flowi *fl) */ static inline int -xfrm_state_ok(struct xfrm_tmpl *tmpl, struct xfrm_state *x, +xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { if (xfrm_state_kern(x)) @@ -1772,7 +2224,7 @@ xfrm_state_ok(struct xfrm_tmpl *tmpl, struct xfrm_state *x, (x->id.spi == tmpl->id.spi || !tmpl->id.spi) && (x->props.reqid == tmpl->reqid || !tmpl->reqid) && x->props.mode == tmpl->mode && - ((tmpl->aalgos & (1<<x->props.aalgo)) || + (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)); @@ -1786,7 +2238,7 @@ xfrm_state_ok(struct xfrm_tmpl *tmpl, struct xfrm_state *x, * Otherwise "-2 - errored_index" is returned. */ static inline int -xfrm_policy_ok(struct xfrm_tmpl *tmpl, struct sec_path *sp, int start, +xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, unsigned short family) { int idx = start; @@ -1818,13 +2270,13 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, return -EAFNOSUPPORT; afinfo->decode_session(skb, fl, reverse); - err = security_xfrm_decode_session(skb, &fl->secid); + err = security_xfrm_decode_session(skb, &fl->flowi_secid); xfrm_policy_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(__xfrm_decode_session); -static inline int secpath_has_nontransport(struct sec_path *sp, int k, int *idxp) +static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { @@ -1839,6 +2291,7 @@ static inline int secpath_has_nontransport(struct sec_path *sp, int k, int *idxp int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { + struct net *net = dev_net(skb->dev); struct xfrm_policy *pol; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int npols = 0; @@ -1854,7 +2307,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, fl_dir = policy_to_flow_dir(dir); if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) { - XFRM_INC_STATS(LINUX_MIB_XFRMINHDRERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } @@ -1864,10 +2317,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (skb->sp) { int i; - for (i=skb->sp->len-1; i>=0; i--) { + for (i = skb->sp->len-1; i >= 0; i--) { struct xfrm_state *x = skb->sp->xvec[i]; if (!xfrm_selector_match(&x->sel, &fl, family)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); return 0; } } @@ -1877,24 +2330,31 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl); if (IS_ERR(pol)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } } - if (!pol) - pol = flow_cache_lookup(&fl, family, fl_dir, - xfrm_policy_lookup); + if (!pol) { + struct flow_cache_object *flo; + + flo = flow_cache_lookup(net, &fl, family, fl_dir, + xfrm_policy_lookup, NULL); + if (IS_ERR_OR_NULL(flo)) + pol = ERR_CAST(flo); + else + pol = container_of(flo, struct xfrm_policy, flo); + } if (IS_ERR(pol)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } if (!pol) { if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) { xfrm_secpath_reject(xerr_idx, skb, &fl); - XFRM_INC_STATS(LINUX_MIB_XFRMINNOPOLS); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } return 1; @@ -1903,19 +2363,19 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol->curlft.use_time = get_seconds(); pols[0] = pol; - npols ++; + npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { - pols[1] = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, + pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, XFRM_POLICY_IN); if (pols[1]) { if (IS_ERR(pols[1])) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } pols[1]->curlft.use_time = get_seconds(); - npols ++; + npols++; } } #endif @@ -1935,11 +2395,11 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, for (pi = 0; pi < npols; pi++) { if (pols[pi] != pol && pols[pi]->action != XFRM_POLICY_ALLOW) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLBLOCK); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); goto reject; } if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) { - XFRM_INC_STATS(LINUX_MIB_XFRMINBUFFERERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto reject_error; } for (i = 0; i < pols[pi]->xfrm_nr; i++) @@ -1947,7 +2407,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; if (npols > 1) { - xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); + xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net); tpp = stp; } @@ -1963,20 +2423,20 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (k < -1) /* "-2 - errored_index" returned */ xerr_idx = -(2+k); - XFRM_INC_STATS(LINUX_MIB_XFRMINTMPLMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } } if (secpath_has_nontransport(sp, k, &xerr_idx)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINTMPLMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } xfrm_pols_put(pols, npols); return 1; } - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLBLOCK); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); reject: xfrm_secpath_reject(xerr_idx, skb, &fl); @@ -1988,15 +2448,25 @@ EXPORT_SYMBOL(__xfrm_policy_check); int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { + struct net *net = dev_net(skb->dev); struct flowi fl; + struct dst_entry *dst; + int res = 1; if (xfrm_decode_session(skb, &fl, family) < 0) { - /* XXX: we should have something like FWDHDRERROR here. */ - XFRM_INC_STATS(LINUX_MIB_XFRMINHDRERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } - return xfrm_lookup(&skb->dst, &fl, NULL, 0) == 0; + skb_dst_force(skb); + + dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0); + if (IS_ERR(dst)) { + res = 0; + dst = NULL; + } + skb_dst_set(skb, dst); + return res; } EXPORT_SYMBOL(__xfrm_route_forward); @@ -2005,12 +2475,13 @@ EXPORT_SYMBOL(__xfrm_route_forward); static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) { /* Code (such as __xfrm4_bundle_create()) sets dst->obsolete - * to "-1" to force all XFRM destinations to get validated by - * dst_ops->check on every use. We do this because when a - * normal route referenced by an XFRM dst is obsoleted we do - * not go looking around for all parent referencing XFRM dsts - * so that we can invalidate them. It is just too much work. - * Instead we make the checks here on every use. For example: + * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to + * get validated by dst_ops->check on every use. We do this + * because when a normal route referenced by an XFRM dst is + * obsoleted we do not go looking around for all parent + * referencing XFRM dsts so that we can invalidate them. It + * is just too much work. Instead we make the checks here on + * every use. For example: * * XFRM dst A --> IPv4 dst X * @@ -2020,9 +2491,9 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) * stale_bundle() check. * * When a policy's bundle is pruned, we dst_free() the XFRM - * dst which causes it's ->obsolete field to be set to a - * positive non-zero integer. If an XFRM dst has been pruned - * like this, we want to force a new route lookup. + * dst which causes it's ->obsolete field to be set to + * DST_OBSOLETE_DEAD. If an XFRM dst has been pruned like + * this, we want to force a new route lookup. */ if (dst->obsolete < 0 && !stale_bundle(dst)) return dst; @@ -2032,13 +2503,13 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) static int stale_bundle(struct dst_entry *dst) { - return !xfrm_bundle_ok(NULL, (struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0); + return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = dst->child) && dst->xfrm && dst->dev == dev) { - dst->dev = dev->nd_net->loopback_dev; + dst->dev = dev_net(dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); } @@ -2048,7 +2519,6 @@ EXPORT_SYMBOL(xfrm_dst_ifdown); static void xfrm_link_failure(struct sk_buff *skb) { /* Impossible. Such dst must be popped before reaches point of failure. */ - return; } static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) @@ -2062,69 +2532,15 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) return dst; } -static void prune_one_bundle(struct xfrm_policy *pol, int (*func)(struct dst_entry *), struct dst_entry **gc_list_p) +void xfrm_garbage_collect(struct net *net) { - struct dst_entry *dst, **dstp; - - write_lock(&pol->lock); - dstp = &pol->bundles; - while ((dst=*dstp) != NULL) { - if (func(dst)) { - *dstp = dst->next; - dst->next = *gc_list_p; - *gc_list_p = dst; - } else { - dstp = &dst->next; - } - } - write_unlock(&pol->lock); + flow_cache_flush(net); } +EXPORT_SYMBOL(xfrm_garbage_collect); -static void xfrm_prune_bundles(int (*func)(struct dst_entry *)) +static void xfrm_garbage_collect_deferred(struct net *net) { - struct dst_entry *gc_list = NULL; - int dir; - - read_lock_bh(&xfrm_policy_lock); - for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { - struct xfrm_policy *pol; - struct hlist_node *entry; - struct hlist_head *table; - int i; - - hlist_for_each_entry(pol, entry, - &xfrm_policy_inexact[dir], bydst) - prune_one_bundle(pol, func, &gc_list); - - table = xfrm_policy_bydst[dir].table; - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { - hlist_for_each_entry(pol, entry, table + i, bydst) - prune_one_bundle(pol, func, &gc_list); - } - } - read_unlock_bh(&xfrm_policy_lock); - - while (gc_list) { - struct dst_entry *dst = gc_list; - gc_list = dst->next; - dst_free(dst); - } -} - -static int unused_bundle(struct dst_entry *dst) -{ - return !atomic_read(&dst->__refcnt); -} - -static void __xfrm_garbage_collect(void) -{ - xfrm_prune_bundles(unused_bundle); -} - -static int xfrm_flush_bundles(void) -{ - xfrm_prune_bundles(stale_bundle); - return 0; + flow_cache_flush_deferred(net); } static void xfrm_init_pmtu(struct dst_entry *dst) @@ -2144,7 +2560,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) if (pmtu > route_mtu_cached) pmtu = route_mtu_cached; - dst->metrics[RTAX_MTU-1] = pmtu; + dst_metric_set(dst, RTAX_MTU, pmtu); } while ((dst = dst->next)); } @@ -2152,8 +2568,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) * still valid. */ -int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, - struct flowi *fl, int family, int strict) +static int xfrm_bundle_ok(struct xfrm_dst *first) { struct dst_entry *dst = &first->u.dst; struct xfrm_dst *last; @@ -2162,34 +2577,21 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, if (!dst_check(dst->path, ((struct xfrm_dst *)dst)->path_cookie) || (dst->dev && !netif_running(dst->dev))) return 0; -#ifdef CONFIG_XFRM_SUB_POLICY - if (fl) { - if (first->origin && !flow_cache_uli_match(first->origin, fl)) - return 0; - if (first->partner && - !xfrm_selector_match(first->partner, fl, family)) - return 0; - } -#endif + + if (dst->flags & DST_XFRM_QUEUE) + return 1; last = NULL; do { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (fl && !xfrm_selector_match(&dst->xfrm->sel, fl, family)) - return 0; - if (fl && pol && - !security_xfrm_state_pol_flow_match(dst->xfrm, pol, fl)) - return 0; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; - if (xdst->genid != dst->xfrm->genid) + if (xdst->xfrm_genid != dst->xfrm->genid) return 0; - - if (strict && fl && - !(dst->xfrm->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) && - !xfrm_state_addr_flow_check(dst->xfrm, fl, family)) + if (xdst->num_pols > 0 && + xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; mtu = dst_mtu(dst->child); @@ -2219,7 +2621,7 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, mtu = xfrm_state_mtu(dst->xfrm, mtu); if (mtu > last->route_mtu_cached) mtu = last->route_mtu_cached; - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); if (last == first) break; @@ -2231,16 +2633,34 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, return 1; } -EXPORT_SYMBOL(xfrm_bundle_ok); +static unsigned int xfrm_default_advmss(const struct dst_entry *dst) +{ + return dst_metric_advmss(dst->path); +} + +static unsigned int xfrm_mtu(const struct dst_entry *dst) +{ + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst_mtu(dst->path); +} + +static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) +{ + return dst->path->ops->neigh_lookup(dst, skb, daddr); +} int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { + struct net *net; int err = 0; if (unlikely(afinfo == NULL)) return -EINVAL; if (unlikely(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; - write_lock_bh(&xfrm_policy_afinfo_lock); + spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[afinfo->family] != NULL)) err = -ENOBUFS; else { @@ -2249,15 +2669,42 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->kmem_cachep = xfrm_dst_cache; if (likely(dst_ops->check == NULL)) dst_ops->check = xfrm_dst_check; + if (likely(dst_ops->default_advmss == NULL)) + dst_ops->default_advmss = xfrm_default_advmss; + if (likely(dst_ops->mtu == NULL)) + dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) dst_ops->link_failure = xfrm_link_failure; + if (likely(dst_ops->neigh_lookup == NULL)) + dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(afinfo->garbage_collect == NULL)) - afinfo->garbage_collect = __xfrm_garbage_collect; - xfrm_policy_afinfo[afinfo->family] = afinfo; + afinfo->garbage_collect = xfrm_garbage_collect_deferred; + rcu_assign_pointer(xfrm_policy_afinfo[afinfo->family], afinfo); } - write_unlock_bh(&xfrm_policy_afinfo_lock); + spin_unlock(&xfrm_policy_afinfo_lock); + + rtnl_lock(); + for_each_net(net) { + struct dst_ops *xfrm_dst_ops; + + switch (afinfo->family) { + case AF_INET: + xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops; + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops; + break; +#endif + default: + BUG(); + } + *xfrm_dst_ops = *afinfo->dst_ops; + } + rtnl_unlock(); + return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); @@ -2269,78 +2716,97 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) return -EINVAL; if (unlikely(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; - write_lock_bh(&xfrm_policy_afinfo_lock); + spin_lock(&xfrm_policy_afinfo_lock); if (likely(xfrm_policy_afinfo[afinfo->family] != NULL)) { if (unlikely(xfrm_policy_afinfo[afinfo->family] != afinfo)) err = -EINVAL; - else { - struct dst_ops *dst_ops = afinfo->dst_ops; - xfrm_policy_afinfo[afinfo->family] = NULL; - dst_ops->kmem_cachep = NULL; - dst_ops->check = NULL; - dst_ops->negative_advice = NULL; - dst_ops->link_failure = NULL; - afinfo->garbage_collect = NULL; - } + else + RCU_INIT_POINTER(xfrm_policy_afinfo[afinfo->family], + NULL); + } + spin_unlock(&xfrm_policy_afinfo_lock); + if (!err) { + struct dst_ops *dst_ops = afinfo->dst_ops; + + synchronize_rcu(); + + dst_ops->kmem_cachep = NULL; + dst_ops->check = NULL; + dst_ops->negative_advice = NULL; + dst_ops->link_failure = NULL; + afinfo->garbage_collect = NULL; } - write_unlock_bh(&xfrm_policy_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); -static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) +static void __net_init xfrm_dst_ops_init(struct net *net) { struct xfrm_policy_afinfo *afinfo; - if (unlikely(family >= NPROTO)) - return NULL; - read_lock(&xfrm_policy_afinfo_lock); - afinfo = xfrm_policy_afinfo[family]; - if (unlikely(!afinfo)) - read_unlock(&xfrm_policy_afinfo_lock); - return afinfo; -} -static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo) -{ - read_unlock(&xfrm_policy_afinfo_lock); + rcu_read_lock(); + afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]); + if (afinfo) + net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; +#if IS_ENABLED(CONFIG_IPV6) + afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]); + if (afinfo) + net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; +#endif + rcu_read_unlock(); } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; - - if (dev->nd_net != &init_net) - return NOTIFY_DONE; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_DOWN: - xfrm_flush_bundles(); + xfrm_garbage_collect(dev_net(dev)); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { - xfrm_dev_event, - NULL, - 0 + .notifier_call = xfrm_dev_event, }; #ifdef CONFIG_XFRM_STATISTICS -static int __init xfrm_statistics_init(void) +static int __net_init xfrm_statistics_init(struct net *net) { - if (snmp_mib_init((void **)xfrm_statistics, - sizeof(struct linux_xfrm_mib)) < 0) + int rv; + net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib); + if (!net->mib.xfrm_statistics) return -ENOMEM; + rv = xfrm_proc_init(net); + if (rv < 0) + free_percpu(net->mib.xfrm_statistics); + return rv; +} + +static void xfrm_statistics_fini(struct net *net) +{ + xfrm_proc_fini(net); + free_percpu(net->mib.xfrm_statistics); +} +#else +static int __net_init xfrm_statistics_init(struct net *net) +{ return 0; } + +static void xfrm_statistics_fini(struct net *net) +{ +} #endif -static void __init xfrm_policy_init(void) +static int __net_init xfrm_policy_init(struct net *net) { unsigned int hmask, sz; int dir; - xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", + if (net_eq(net, &init_net)) + xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", sizeof(struct xfrm_dst), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); @@ -2348,38 +2814,129 @@ static void __init xfrm_policy_init(void) hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); - xfrm_policy_byidx = xfrm_hash_alloc(sz); - xfrm_idx_hmask = hmask; - if (!xfrm_policy_byidx) - panic("XFRM: failed to allocate byidx hash\n"); + net->xfrm.policy_byidx = xfrm_hash_alloc(sz); + if (!net->xfrm.policy_byidx) + goto out_byidx; + net->xfrm.policy_idx_hmask = hmask; for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { struct xfrm_policy_hash *htab; - INIT_HLIST_HEAD(&xfrm_policy_inexact[dir]); + net->xfrm.policy_count[dir] = 0; + INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); - htab = &xfrm_policy_bydst[dir]; + htab = &net->xfrm.policy_bydst[dir]; htab->table = xfrm_hash_alloc(sz); - htab->hmask = hmask; if (!htab->table) - panic("XFRM: failed to allocate bydst hash\n"); + goto out_bydst; + htab->hmask = hmask; } - INIT_WORK(&xfrm_policy_gc_work, xfrm_policy_gc_task); - register_netdevice_notifier(&xfrm_dev_notifier); + INIT_LIST_HEAD(&net->xfrm.policy_all); + INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize); + if (net_eq(net, &init_net)) + register_netdevice_notifier(&xfrm_dev_notifier); + return 0; + +out_bydst: + for (dir--; dir >= 0; dir--) { + struct xfrm_policy_hash *htab; + + htab = &net->xfrm.policy_bydst[dir]; + xfrm_hash_free(htab->table, sz); + } + xfrm_hash_free(net->xfrm.policy_byidx, sz); +out_byidx: + return -ENOMEM; } -void __init xfrm_init(void) +static void xfrm_policy_fini(struct net *net) { -#ifdef CONFIG_XFRM_STATISTICS - xfrm_statistics_init(); + unsigned int sz; + int dir; + + flush_work(&net->xfrm.policy_hash_work); +#ifdef CONFIG_XFRM_SUB_POLICY + xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif - xfrm_state_init(); - xfrm_policy_init(); + xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); + + WARN_ON(!list_empty(&net->xfrm.policy_all)); + + for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { + struct xfrm_policy_hash *htab; + + WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); + + htab = &net->xfrm.policy_bydst[dir]; + sz = (htab->hmask + 1) * sizeof(struct hlist_head); + WARN_ON(!hlist_empty(htab->table)); + xfrm_hash_free(htab->table, sz); + } + + sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); + WARN_ON(!hlist_empty(net->xfrm.policy_byidx)); + xfrm_hash_free(net->xfrm.policy_byidx, sz); +} + +static int __net_init xfrm_net_init(struct net *net) +{ + int rv; + + rv = xfrm_statistics_init(net); + if (rv < 0) + goto out_statistics; + rv = xfrm_state_init(net); + if (rv < 0) + goto out_state; + rv = xfrm_policy_init(net); + if (rv < 0) + goto out_policy; + xfrm_dst_ops_init(net); + rv = xfrm_sysctl_init(net); + if (rv < 0) + goto out_sysctl; + rv = flow_cache_init(net); + if (rv < 0) + goto out; + + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + rwlock_init(&net->xfrm.xfrm_policy_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + + return 0; + +out: + xfrm_sysctl_fini(net); +out_sysctl: + xfrm_policy_fini(net); +out_policy: + xfrm_state_fini(net); +out_state: + xfrm_statistics_fini(net); +out_statistics: + return rv; +} + +static void __net_exit xfrm_net_exit(struct net *net) +{ + flow_cache_fini(net); + xfrm_sysctl_fini(net); + xfrm_policy_fini(net); + xfrm_state_fini(net); + xfrm_statistics_fini(net); +} + +static struct pernet_operations __net_initdata xfrm_net_ops = { + .init = xfrm_net_init, + .exit = xfrm_net_exit, +}; + +void __init xfrm_init(void) +{ + register_pernet_subsys(&xfrm_net_ops); xfrm_input_init(); -#ifdef CONFIG_XFRM_STATISTICS - xfrm_proc_init(); -#endif } #ifdef CONFIG_AUDITSYSCALL @@ -2393,27 +2950,23 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(sel->family) { + switch (sel->family) { case AF_INET: - audit_log_format(audit_buf, " src=" NIPQUAD_FMT, - NIPQUAD(sel->saddr.a4)); + audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); - audit_log_format(audit_buf, " dst=" NIPQUAD_FMT, - NIPQUAD(sel->daddr.a4)); + audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4); if (sel->prefixlen_d != 32) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; case AF_INET6: - audit_log_format(audit_buf, " src=" NIP6_FMT, - NIP6(*(struct in6_addr *)sel->saddr.a6)); + audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6); if (sel->prefixlen_s != 128) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); - audit_log_format(audit_buf, " dst=" NIP6_FMT, - NIP6(*(struct in6_addr *)sel->daddr.a6)); + audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6); if (sel->prefixlen_d != 128) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); @@ -2421,15 +2974,14 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, } } -void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, - u32 auid, u32 secid) +void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-add"); if (audit_buf == NULL) return; - xfrm_audit_helper_usrinfo(auid, secid, audit_buf); + xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); @@ -2437,14 +2989,14 @@ void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, EXPORT_SYMBOL_GPL(xfrm_audit_policy_add); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, - u32 auid, u32 secid) + bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-delete"); if (audit_buf == NULL) return; - xfrm_audit_helper_usrinfo(auid, secid, audit_buf); + xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); @@ -2453,38 +3005,37 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE -static int xfrm_migrate_selector_match(struct xfrm_selector *sel_cmp, - struct xfrm_selector *sel_tgt) +static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, + const struct xfrm_selector *sel_tgt) { if (sel_cmp->proto == IPSEC_ULPROTO_ANY) { if (sel_tgt->family == sel_cmp->family && - xfrm_addr_cmp(&sel_tgt->daddr, &sel_cmp->daddr, - sel_cmp->family) == 0 && - xfrm_addr_cmp(&sel_tgt->saddr, &sel_cmp->saddr, - sel_cmp->family) == 0 && + xfrm_addr_equal(&sel_tgt->daddr, &sel_cmp->daddr, + sel_cmp->family) && + xfrm_addr_equal(&sel_tgt->saddr, &sel_cmp->saddr, + sel_cmp->family) && sel_tgt->prefixlen_d == sel_cmp->prefixlen_d && sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) { - return 1; + return true; } } else { if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) { - return 1; + return true; } } - return 0; + return false; } -static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, - u8 dir, u8 type) +static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, + u8 dir, u8 type, struct net *net) { struct xfrm_policy *pol, *ret = NULL; - struct hlist_node *entry; struct hlist_head *chain; u32 priority = ~0U; - read_lock_bh(&xfrm_policy_lock); - chain = policy_hash_direct(&sel->daddr, &sel->saddr, sel->family, dir); - hlist_for_each_entry(pol, entry, chain, bydst) { + read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/ + chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); + hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; @@ -2492,8 +3043,8 @@ static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, break; } } - chain = &xfrm_policy_inexact[dir]; - hlist_for_each_entry(pol, entry, chain, bydst) { + chain = &net->xfrm.policy_inexact[dir]; + hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type && pol->priority < priority) { @@ -2505,12 +3056,12 @@ static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, if (ret) xfrm_pol_hold(ret); - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } -static int migrate_tmpl_match(struct xfrm_migrate *m, struct xfrm_tmpl *t) +static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t) { int match = 0; @@ -2519,10 +3070,10 @@ static int migrate_tmpl_match(struct xfrm_migrate *m, struct xfrm_tmpl *t) switch (t->mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: - if (xfrm_addr_cmp(&t->id.daddr, &m->old_daddr, - m->old_family) == 0 && - xfrm_addr_cmp(&t->saddr, &m->old_saddr, - m->old_family) == 0) { + if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr, + m->old_family) && + xfrm_addr_equal(&t->saddr, &m->old_saddr, + m->old_family)) { match = 1; } break; @@ -2544,11 +3095,10 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, struct xfrm_migrate *m, int num_migrate) { struct xfrm_migrate *mp; - struct dst_entry *dst; int i, j, n = 0; write_lock_bh(&pol->lock); - if (unlikely(pol->dead)) { + if (unlikely(pol->walk.dead)) { /* target policy has been deleted */ write_unlock_bh(&pol->lock); return -ENOENT; @@ -2569,10 +3119,7 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, sizeof(pol->xfrm_vec[i].saddr)); pol->xfrm_vec[i].encap_family = mp->new_family; /* flush bundles */ - while ((dst = pol->bundles) != NULL) { - pol->bundles = dst->next; - dst_free(dst); - } + atomic_inc(&pol->genid); } } @@ -2584,7 +3131,7 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, return 0; } -static int xfrm_migrate_check(struct xfrm_migrate *m, int num_migrate) +static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) { int i, j; @@ -2592,10 +3139,10 @@ static int xfrm_migrate_check(struct xfrm_migrate *m, int num_migrate) return -EINVAL; for (i = 0; i < num_migrate; i++) { - if ((xfrm_addr_cmp(&m[i].old_daddr, &m[i].new_daddr, - m[i].old_family) == 0) && - (xfrm_addr_cmp(&m[i].old_saddr, &m[i].new_saddr, - m[i].old_family) == 0)) + if (xfrm_addr_equal(&m[i].old_daddr, &m[i].new_daddr, + m[i].old_family) && + xfrm_addr_equal(&m[i].old_saddr, &m[i].new_saddr, + m[i].old_family)) return -EINVAL; if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) @@ -2618,8 +3165,9 @@ static int xfrm_migrate_check(struct xfrm_migrate *m, int num_migrate) return 0; } -int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_migrate) +int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + struct xfrm_migrate *m, int num_migrate, + struct xfrm_kmaddress *k, struct net *net) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -2632,14 +3180,14 @@ int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, goto out; /* Stage 1 - find policy */ - if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) { + if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) { err = -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { - if ((x = xfrm_migrate_state_find(mp))) { + if ((x = xfrm_migrate_state_find(mp, net))) { x_cur[nx_cur] = x; nx_cur++; if ((xc = xfrm_state_migrate(x, mp))) { @@ -2663,7 +3211,7 @@ int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 5 - announce */ - km_migrate(sel, dir, type, m, num_migrate); + km_migrate(sel, dir, type, m, num_migrate, k); xfrm_pol_put(pol); |