xfrm: cache bundles instead of policies for outgoing flows

__xfrm_lookup() is called for each packet transmitted out of
system. The xfrm_find_bundle() does a linear search which can
kill system performance depending on how many bundles are
required per policy.

This modifies __xfrm_lookup() to store bundles directly in
the flow cache. If we did not get a hit, we just create a new
bundle instead of doing slow search. This means that we can now
get multiple xfrm_dst's for same flow (on per-cpu basis).

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/xfrm.h

@@ -267,7 +267,6 @@ struct xfrm_policy_afinfo {
 					       xfrm_address_t *saddr,
 					       xfrm_address_t *daddr);
 	int			(*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr);
-	struct dst_entry	*(*find_bundle)(struct flowi *fl, struct xfrm_policy *policy);
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
 						  int reverse);
@@ -483,13 +482,13 @@ struct xfrm_policy {
 	struct timer_list	timer;
 
 	struct flow_cache_object flo;
+	atomic_t		genid;
 	u32			priority;
 	u32			index;
 	struct xfrm_mark	mark;
 	struct xfrm_selector	selector;
 	struct xfrm_lifetime_cfg lft;
 	struct xfrm_lifetime_cur curlft;
-	struct dst_entry       *bundles;
 	struct xfrm_policy_walk_entry walk;
 	u8			type;
 	u8			action;
@@ -879,11 +878,15 @@ struct xfrm_dst {
 		struct rt6_info		rt6;
 	} u;
 	struct dst_entry *route;
+	struct flow_cache_object flo;
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	int num_pols, num_xfrms;
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct flowi *origin;
 	struct xfrm_selector *partner;
 #endif
-	u32 genid;
+	u32 xfrm_genid;
+	u32 policy_genid;
 	u32 route_mtu_cached;
 	u32 child_mtu_cached;
 	u32 route_cookie;
@@ -893,6 +896,7 @@ struct xfrm_dst {
 #ifdef CONFIG_XFRM
 static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
 {
+	xfrm_pols_put(xdst->pols, xdst->num_pols);
 	dst_release(xdst->route);
 	if (likely(xdst->u.dst.xfrm))
 		xfrm_state_put(xdst->u.dst.xfrm);

net/ipv4/xfrm4_policy.c

@@ -59,27 +59,6 @@ static int xfrm4_get_saddr(struct net *net,
 	return 0;
 }
 
-static struct dst_entry *
-__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
-{
-	struct dst_entry *dst;
-
-	read_lock_bh(&policy->lock);
-	for (dst = policy->bundles; dst; dst = dst->next) {
-		struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
-		if (xdst->u.rt.fl.oif == fl->oif &&	/*XXX*/
-		    xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
-		    xdst->u.rt.fl.fl4_src == fl->fl4_src &&
-		    xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
-		    xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
-			dst_clone(dst);
-			break;
-		}
-	}
-	read_unlock_bh(&policy->lock);
-	return dst;
-}
-
 static int xfrm4_get_tos(struct flowi *fl)
 {
 	return fl->fl4_tos;
@@ -259,7 +238,6 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.dst_ops =		&xfrm4_dst_ops,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
-	.find_bundle = 		__xfrm4_find_bundle,
 	.decode_session =	_decode_session4,
 	.get_tos =		xfrm4_get_tos,
 	.init_path =		xfrm4_init_path,

net/ipv6/xfrm6_policy.c

@@ -67,36 +67,6 @@ static int xfrm6_get_saddr(struct net *net,
 	return 0;
 }
 
-static struct dst_entry *
-__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
-{
-	struct dst_entry *dst;
-
-	/* Still not clear if we should set fl->fl6_{src,dst}... */
-	read_lock_bh(&policy->lock);
-	for (dst = policy->bundles; dst; dst = dst->next) {
-		struct xfrm_dst *xdst = (struct xfrm_dst*)dst;
-		struct in6_addr fl_dst_prefix, fl_src_prefix;
-
-		ipv6_addr_prefix(&fl_dst_prefix,
-				 &fl->fl6_dst,
-				 xdst->u.rt6.rt6i_dst.plen);
-		ipv6_addr_prefix(&fl_src_prefix,
-				 &fl->fl6_src,
-				 xdst->u.rt6.rt6i_src.plen);
-		if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
-		    ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
-		    xfrm_bundle_ok(policy, xdst, fl, AF_INET6,
-				   (xdst->u.rt6.rt6i_dst.plen != 128 ||
-				    xdst->u.rt6.rt6i_src.plen != 128))) {
-			dst_clone(dst);
-			break;
-		}
-	}
-	read_unlock_bh(&policy->lock);
-	return dst;
-}
-
 static int xfrm6_get_tos(struct flowi *fl)
 {
 	return 0;
@@ -291,7 +261,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.dst_ops =		&xfrm6_dst_ops,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr = 		xfrm6_get_saddr,
-	.find_bundle =		__xfrm6_find_bundle,
 	.decode_session =	_decode_session6,
 	.get_tos =		xfrm6_get_tos,
 	.init_path =		xfrm6_init_path,

net/xfrm/xfrm_policy.c

@@ -37,6 +37,8 @@
 DEFINE_MUTEX(xfrm_cfg_mutex);
 EXPORT_SYMBOL(xfrm_cfg_mutex);
 
+static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
+static struct dst_entry *xfrm_policy_sk_bundles;
 static DEFINE_RWLOCK(xfrm_policy_lock);
 
 static DEFINE_RWLOCK(xfrm_policy_afinfo_lock);
@@ -50,6 +52,7 @@ 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 struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
@@ -277,8 +280,6 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
 {
 	BUG_ON(!policy->walk.dead);
 
-	BUG_ON(policy->bundles);
-
 	if (del_timer(&policy->timer))
 		BUG();
 
@@ -289,12 +290,7 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
 
 static void xfrm_policy_gc_kill(struct xfrm_policy *policy)
 {
-	struct dst_entry *dst;
+	atomic_inc(&policy->genid);
-
-	while ((dst = policy->bundles) != NULL) {
-		policy->bundles = dst->next;
-		dst_free(dst);
-	}
 
 	if (del_timer(&policy->timer))
 		atomic_dec(&policy->refcnt);
@@ -572,7 +568,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct xfrm_policy *delpol;
 	struct hlist_head *chain;
 	struct hlist_node *entry, *newpos;
-	struct dst_entry *gc_list;
 	u32 mark = policy->mark.v & policy->mark.m;
 
 	write_lock_bh(&xfrm_policy_lock);
@@ -622,34 +617,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	else if (xfrm_bydst_should_resize(net, dir, NULL))
 		schedule_work(&net->xfrm.policy_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);
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_policy_insert);
@@ -998,6 +965,19 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	return ret;
 }
 
+static struct xfrm_policy *
+__xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir)
+{
+#ifdef CONFIG_XFRM_SUB_POLICY
+	struct xfrm_policy *pol;
+
+	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
+	if (pol != NULL)
+		return pol;
+#endif
+	return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
+}
+
 static struct flow_cache_object *
 xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
 		   u8 dir, struct flow_cache_object *old_obj, void *ctx)
@@ -1007,21 +987,10 @@ xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
 	if (old_obj)
 		xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo));
 
-#ifdef CONFIG_XFRM_SUB_POLICY
+	pol = __xfrm_policy_lookup(net, fl, family, dir);
-	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
+	if (IS_ERR_OR_NULL(pol))
-	if (IS_ERR(pol))
 		return ERR_CAST(pol);
-	if (pol)
-		goto found;
-#endif
-	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
-	if (IS_ERR(pol))
-		return ERR_CAST(pol);
-	if (pol)
-		goto found;
-	return NULL;
 
-found:
 	/* Resolver returns two references:
 	 * one for cache and one for caller of flow_cache_lookup() */
 	xfrm_pol_hold(pol);
@@ -1313,18 +1282,6 @@ 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)
 {
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
@@ -1340,6 +1297,54 @@ static inline int xfrm_get_tos(struct flowi *fl, int family)
 	return tos;
 }
 
+static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *flo)
+{
+	struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
+	struct dst_entry *dst = &xdst->u.dst;
+
+	if (xdst->route == NULL) {
+		/* Dummy bundle - if it has xfrms we were not
+		 * able to build bundle as template resolution failed.
+		 * It means we need to try again resolving. */
+		if (xdst->num_xfrms > 0)
+			return NULL;
+	} else {
+		/* Real bundle */
+		if (stale_bundle(dst))
+			return NULL;
+	}
+
+	dst_hold(dst);
+	return flo;
+}
+
+static int xfrm_bundle_flo_check(struct flow_cache_object *flo)
+{
+	struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
+	struct dst_entry *dst = &xdst->u.dst;
+
+	if (!xdst->route)
+		return 0;
+	if (stale_bundle(dst))
+		return 0;
+
+	return 1;
+}
+
+static void xfrm_bundle_flo_delete(struct flow_cache_object *flo)
+{
+	struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
+	struct dst_entry *dst = &xdst->u.dst;
+
+	dst_free(dst);
+}
+
+static const struct flow_cache_ops xfrm_bundle_fc_ops = {
+	.get = xfrm_bundle_flo_get,
+	.check = xfrm_bundle_flo_check,
+	.delete = xfrm_bundle_flo_delete,
+};
+
 static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 {
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
@@ -1362,9 +1367,10 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 		BUG();
 	}
 	xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS);
-
 	xfrm_policy_put_afinfo(afinfo);
 
+	xdst->flo.ops = &xfrm_bundle_fc_ops;
+
 	return xdst;
 }
 
@@ -1402,6 +1408,7 @@ static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	return err;
 }
 
+
 /* Allocate chain of dst_entry's, attach known xfrm's, calculate
  * all the metrics... Shortly, bundle a bundle.
  */
@@ -1465,7 +1472,7 @@ 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->flags |= DST_HOST;
@@ -1558,7 +1565,186 @@ 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(struct flowi *fl, u16 family,
+				struct xfrm_policy **pols,
+				int *num_pols, int *num_xfrms)
+{
+	int i;
+
+	if (*num_pols == 0 || !pols[0]) {
+		*num_pols = 0;
+		*num_xfrms = 0;
+		return 0;
+	}
+	if (IS_ERR(pols[0]))
+		return PTR_ERR(pols[0]);
+
+	*num_xfrms = pols[0]->xfrm_nr;
+
+#ifdef CONFIG_XFRM_SUB_POLICY
+	if (pols[0] && pols[0]->action == XFRM_POLICY_ALLOW &&
+	    pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
+		pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
+						    XFRM_POLICY_TYPE_MAIN,
+						    fl, family,
+						    XFRM_POLICY_OUT);
+		if (pols[1]) {
+			if (IS_ERR(pols[1])) {
+				xfrm_pols_put(pols, *num_pols);
+				return PTR_ERR(pols[1]);
+			}
+			(*num_pols) ++;
+			(*num_xfrms) += pols[1]->xfrm_nr;
+		}
+	}
+#endif
+	for (i = 0; i < *num_pols; i++) {
+		if (pols[i]->action != XFRM_POLICY_ALLOW) {
+			*num_xfrms = -1;
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
+static struct xfrm_dst *
+xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
+			       struct flowi *fl, u16 family,
+			       struct dst_entry *dst_orig)
+{
+	struct net *net = xp_net(pols[0]);
+	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
+	struct dst_entry *dst;
+	struct xfrm_dst *xdst;
+	int err;
+
+	/* Try to instantiate a bundle */
+	err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
+	if (err < 0) {
+		if (err != -EAGAIN)
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+		return ERR_PTR(err);
+	}
+
+	dst = xfrm_bundle_create(pols[0], xfrm, err, fl, dst_orig);
+	if (IS_ERR(dst)) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
+		return ERR_CAST(dst);
+	}
+
+	xdst = (struct xfrm_dst *)dst;
+	xdst->num_xfrms = err;
+	if (num_pols > 1)
+		err = xfrm_dst_update_parent(dst, &pols[1]->selector);
+	else
+		err = xfrm_dst_update_origin(dst, fl);
+	if (unlikely(err)) {
+		dst_free(dst);
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
+		return ERR_PTR(err);
+	}
+
+	xdst->num_pols = num_pols;
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	xdst->policy_genid = atomic_read(&pols[0]->genid);
+
+	return xdst;
+}
+
+static struct flow_cache_object *
+xfrm_bundle_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir,
+		   struct flow_cache_object *oldflo, void *ctx)
+{
+	struct dst_entry *dst_orig = (struct dst_entry *)ctx;
+	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
+	struct xfrm_dst *xdst, *new_xdst;
+	int num_pols = 0, num_xfrms = 0, i, err, pol_dead;
+
+	/* Check if the policies from old bundle are usable */
+	xdst = NULL;
+	if (oldflo) {
+		xdst = container_of(oldflo, struct xfrm_dst, flo);
+		num_pols = xdst->num_pols;
+		num_xfrms = xdst->num_xfrms;
+		pol_dead = 0;
+		for (i = 0; i < num_pols; i++) {
+			pols[i] = xdst->pols[i];
+			pol_dead |= pols[i]->walk.dead;
+		}
+		if (pol_dead) {
+			dst_free(&xdst->u.dst);
+			xdst = NULL;
+			num_pols = 0;
+			num_xfrms = 0;
+			oldflo = NULL;
+		}
+	}
+
+	/* Resolve policies to use if we couldn't get them from
+	 * previous cache entry */
+	if (xdst == NULL) {
+		num_pols = 1;
+		pols[0] = __xfrm_policy_lookup(net, fl, family, dir);
+		err = xfrm_expand_policies(fl, family, pols,
+					   &num_pols, &num_xfrms);
+		if (err < 0)
+			goto inc_error;
+		if (num_pols == 0)
+			return NULL;
+		if (num_xfrms <= 0)
+			goto make_dummy_bundle;
+	}
+
+	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig);
+	if (IS_ERR(new_xdst)) {
+		err = PTR_ERR(new_xdst);
+		if (err != -EAGAIN)
+			goto error;
+		if (oldflo == NULL)
+			goto make_dummy_bundle;
+		dst_hold(&xdst->u.dst);
+		return oldflo;
+	}
+
+	/* Kill the previous bundle */
+	if (xdst) {
+		/* The policies were stolen for newly generated bundle */
+		xdst->num_pols = 0;
+		dst_free(&xdst->u.dst);
+	}
+
+	/* Flow cache does not have reference, it dst_free()'s,
+	 * but we do need to return one reference for original caller */
+	dst_hold(&new_xdst->u.dst);
+	return &new_xdst->flo;
+
+make_dummy_bundle:
+	/* We found policies, but there's no bundles to instantiate:
+	 * either because the policy blocks, has no transformations or
+	 * we could not build template (no xfrm_states).*/
+	xdst = xfrm_alloc_dst(net, family);
+	if (IS_ERR(xdst)) {
+		xfrm_pols_put(pols, num_pols);
+		return ERR_CAST(xdst);
+	}
+	xdst->num_pols = num_pols;
+	xdst->num_xfrms = num_xfrms;
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+
+	dst_hold(&xdst->u.dst);
+	return &xdst->flo;
+
+inc_error:
+	XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+error:
+	if (xdst != NULL)
+		dst_free(&xdst->u.dst);
+	else
+		xfrm_pols_put(pols, num_pols);
+	return ERR_PTR(err);
+}
 
 /* Main function: finds/creates a bundle for given flow.
  *
@@ -1568,248 +1754,152 @@ static int stale_bundle(struct dst_entry *dst);
 int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl,
 		  struct sock *sk, int flags)
 {
-	struct xfrm_policy *policy;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
-	int npols;
+	struct flow_cache_object *flo;
-	int pol_dead;
+	struct xfrm_dst *xdst;
-	int xfrm_nr;
+	struct dst_entry *dst, *dst_orig = *dst_p, *route;
-	int pi;
+	u16 family = dst_orig->ops->family;
-	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
-	struct dst_entry *dst, *dst_orig = *dst_p;
-	int nx = 0;
-	int err;
-	u32 genid;
-	u16 family;
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
+	int i, err, num_pols, num_xfrms, drop_pols = 0;
 
 restart:
-	genid = atomic_read(&flow_cache_genid);
+	dst = NULL;
-	policy = NULL;
+	xdst = NULL;
-	for (pi = 0; pi < ARRAY_SIZE(pols); pi++)
+	route = NULL;
-		pols[pi] = NULL;
-	npols = 0;
-	pol_dead = 0;
-	xfrm_nr = 0;
 
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
-		policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+		num_pols = 1;
-		err = PTR_ERR(policy);
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
-		if (IS_ERR(policy)) {
+		err = xfrm_expand_policies(fl, family, pols,
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+					   &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;
+			}
+
+			spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+			xdst->u.dst.next = xfrm_policy_sk_bundles;
+			xfrm_policy_sk_bundles = &xdst->u.dst;
+			spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+
+			route = xdst->route;
 		}
 	}
 
-	if (!policy) {
+	if (xdst == NULL) {
-		struct flow_cache_object *flo;
-
 		/* 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, dst_orig->ops->family,
+		flo = flow_cache_lookup(net, fl, family, dir,
-					dir, xfrm_policy_lookup, NULL);
+					xfrm_bundle_lookup, dst_orig);
-		err = PTR_ERR(flo);
+		if (flo == NULL)
+			goto nopol;
 		if (IS_ERR(flo)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
+			err = PTR_ERR(flo);
 			goto dropdst;
 		}
-		if (flo)
+		xdst = container_of(flo, struct xfrm_dst, flo);
-			policy = container_of(flo, struct xfrm_policy, flo);
+
-		else
+		num_pols = xdst->num_pols;
-			policy = NULL;
+		num_xfrms = xdst->num_xfrms;
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+		route = xdst->route;
 	}
 
-	if (!policy)
+	dst = &xdst->u.dst;
+	if (route == NULL && num_xfrms > 0) {
+		/* The only case when xfrm_bundle_lookup() returns a
+		 * bundle with null route, is when the template could
+		 * not be resolved. It means policies are there, but
+		 * bundle could not be created, since we don't yet
+		 * have the xfrm_state's. We need to wait for KM to
+		 * negotiate new SA's or bail out with error.*/
+		if (net->xfrm.sysctl_larval_drop) {
+			/* EREMOTE tells the caller to generate
+			 * a one-shot blackhole route. */
+			dst_release(dst);
+			xfrm_pols_put(pols, num_pols);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
+			return -EREMOTE;
+		}
+		if (flags & XFRM_LOOKUP_WAIT) {
+			DECLARE_WAITQUEUE(wait, current);
+
+			add_wait_queue(&net->xfrm.km_waitq, &wait);
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+			set_current_state(TASK_RUNNING);
+			remove_wait_queue(&net->xfrm.km_waitq, &wait);
+
+			if (!signal_pending(current)) {
+				dst_release(dst);
+				goto restart;
+			}
+
+			err = -ERESTART;
+		} else
+			err = -EAGAIN;
+
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
+		goto error;
+	}
+
+no_transform:
+	if (num_pols == 0)
 		goto nopol;
 
-	family = dst_orig->ops->family;
+	if ((flags & XFRM_LOOKUP_ICMP) &&
-	pols[0] = policy;
+	    !(pols[0]->flags & XFRM_POLICY_ICMP)) {
-	npols ++;
+		err = -ENOENT;
-	xfrm_nr += pols[0]->xfrm_nr;
-
-	err = -ENOENT;
-	if ((flags & XFRM_LOOKUP_ICMP) && !(policy->flags & XFRM_POLICY_ICMP))
 		goto error;
+	}
 
-	policy->curlft.use_time = get_seconds();
+	for (i = 0; i < num_pols; i++)
+		pols[i]->curlft.use_time = get_seconds();
 
-	switch (policy->action) {
+	if (num_xfrms < 0) {
-	default:
-	case XFRM_POLICY_BLOCK:
 		/* Prohibit the flow */
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
 		err = -EPERM;
 		goto error;
-
+	} else if (num_xfrms > 0) {
-	case XFRM_POLICY_ALLOW:
+		/* Flow transformed */
-#ifndef CONFIG_XFRM_SUB_POLICY
+		*dst_p = dst;
-		if (policy->xfrm_nr == 0) {
+		dst_release(dst_orig);
-			/* Flow passes not transformed. */
+	} else {
-			xfrm_pol_put(policy);
+		/* Flow passes untransformed */
-			return 0;
+		dst_release(dst);
-		}
-#endif
-
-		/* 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);
-		if (IS_ERR(dst)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-			err = PTR_ERR(dst);
-			goto error;
-		}
-
-		if (dst)
-			break;
-
-#ifdef CONFIG_XFRM_SUB_POLICY
-		if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
-			pols[1] = xfrm_policy_lookup_bytype(net,
-							    XFRM_POLICY_TYPE_MAIN,
-							    fl, family,
-							    XFRM_POLICY_OUT);
-			if (pols[1]) {
-				if (IS_ERR(pols[1])) {
-					XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
-					err = PTR_ERR(pols[1]);
-					goto error;
-				}
-				if (pols[1]->action == XFRM_POLICY_BLOCK) {
-					XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK);
-					err = -EPERM;
-					goto error;
-				}
-				npols ++;
-				xfrm_nr += pols[1]->xfrm_nr;
-			}
-		}
-
-		/*
-		 * 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;
-		}
-
-#endif
-		nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family);
-
-		if (unlikely(nx<0)) {
-			err = nx;
-			if (err == -EAGAIN && net->xfrm.sysctl_larval_drop) {
-				/* EREMOTE tells the caller to generate
-				 * a one-shot blackhole route.
-				 */
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-				xfrm_pol_put(policy);
-				return -EREMOTE;
-			}
-			if (err == -EAGAIN && (flags & XFRM_LOOKUP_WAIT)) {
-				DECLARE_WAITQUEUE(wait, current);
-
-				add_wait_queue(&net->xfrm.km_waitq, &wait);
-				set_current_state(TASK_INTERRUPTIBLE);
-				schedule();
-				set_current_state(TASK_RUNNING);
-				remove_wait_queue(&net->xfrm.km_waitq, &wait);
-
-				nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family);
-
-				if (nx == -EAGAIN && signal_pending(current)) {
-					XFRM_INC_STATS(net, 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(net, LINUX_MIB_XFRMOUTNOSTATES);
-				goto error;
-			}
-		}
-		if (nx == 0) {
-			/* Flow passes not transformed. */
-			xfrm_pols_put(pols, npols);
-			return 0;
-		}
-
-		dst = xfrm_bundle_create(policy, xfrm, nx, fl, dst_orig);
-		err = PTR_ERR(dst);
-		if (IS_ERR(dst)) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
-			goto error;
-		}
-
-		for (pi = 0; pi < npols; pi++)
-			pol_dead |= pols[pi]->walk.dead;
-
-		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);
-			dst_free(dst);
-
-			if (pol_dead)
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLDEAD);
-			else
-				XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-			err = -EHOSTUNREACH;
-			goto error;
-		}
-
-		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);
-			dst_free(dst);
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR);
-			goto error;
-		}
-
-		dst->next = policy->bundles;
-		policy->bundles = dst;
-		dst_hold(dst);
-		write_unlock_bh(&policy->lock);
 	}
-	*dst_p = dst;
+ok:
-	dst_release(dst_orig);
+	xfrm_pols_put(pols, drop_pols);
-	xfrm_pols_put(pols, npols);
 	return 0;
 
+nopol:
+	if (!(flags & XFRM_LOOKUP_ICMP))
+		goto ok;
+	err = -ENOENT;
 error:
-	xfrm_pols_put(pols, npols);
+	dst_release(dst);
 dropdst:
 	dst_release(dst_orig);
 	*dst_p = NULL;
+	xfrm_pols_put(pols, drop_pols);
 	return err;
-
-nopol:
-	err = -ENOENT;
-	if (flags & XFRM_LOOKUP_ICMP)
-		goto dropdst;
-	return 0;
 }
 EXPORT_SYMBOL(__xfrm_lookup);
 
@@ -2161,69 +2251,22 @@ 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)
-{
-	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);
-}
-
-static void xfrm_prune_bundles(struct net *net, int (*func)(struct dst_entry *))
-{
-	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,
-				     &net->xfrm.policy_inexact[dir], bydst)
-			prune_one_bundle(pol, func, &gc_list);
-
-		table = net->xfrm.policy_bydst[dir].table;
-		for (i = net->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(struct net *net)
 {
-	xfrm_prune_bundles(net, unused_bundle);
+	struct dst_entry *head, *next;
-}
 
-static int xfrm_flush_bundles(struct net *net)
+	flow_cache_flush();
-{
+
-	xfrm_prune_bundles(net, stale_bundle);
+	spin_lock_bh(&xfrm_policy_sk_bundle_lock);
-	return 0;
+	head = xfrm_policy_sk_bundles;
+	xfrm_policy_sk_bundles = NULL;
+	spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+
+	while (head) {
+		next = head->next;
+		dst_free(head);
+		head = next;
+	}
 }
 
 static void xfrm_init_pmtu(struct dst_entry *dst)
@@ -2283,7 +2326,9 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first,
 			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 (xdst->policy_genid != atomic_read(&xdst->pols[0]->genid))
 			return 0;
 
 		if (strict && fl &&
@@ -2448,7 +2493,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 
 	switch (event) {
 	case NETDEV_DOWN:
-		xfrm_flush_bundles(dev_net(dev));
+		__xfrm_garbage_collect(dev_net(dev));
 	}
 	return NOTIFY_DONE;
 }
@@ -2780,7 +2825,6 @@ 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);
@@ -2805,10 +2849,7 @@ 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) {
+			atomic_inc(&pol->genid);
-				pol->bundles = dst->next;
-				dst_free(dst);
-			}
 		}
 	}