--- zzzz-none-000/linux-3.10.107/net/xfrm/xfrm_policy.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/net/xfrm/xfrm_policy.c	2021-02-04 17:41:59.000000000 +0000
@@ -39,12 +39,10 @@
 #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
 #define XFRM_MAX_QUEUE_LEN	100
 
-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);
+struct xfrm_flo {
+	struct dst_entry *dst_orig;
+	u8 flags;
+};
 
 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
 static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
@@ -57,6 +55,7 @@
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
 static void xfrm_policy_queue_process(unsigned long arg);
 
+static void __xfrm_policy_link(struct xfrm_policy *pol, int dir);
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 						int dir);
 
@@ -116,7 +115,8 @@
 	rcu_read_unlock();
 }
 
-static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos,
+static inline struct dst_entry *__xfrm_dst_lookup(struct net *net,
+						  int tos, int oif,
 						  const xfrm_address_t *saddr,
 						  const xfrm_address_t *daddr,
 						  int family)
@@ -128,14 +128,15 @@
 	if (unlikely(afinfo == NULL))
 		return ERR_PTR(-EAFNOSUPPORT);
 
-	dst = afinfo->dst_lookup(net, tos, saddr, daddr);
+	dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr);
 
 	xfrm_policy_put_afinfo(afinfo);
 
 	return dst;
 }
 
-static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos,
+static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
+						int tos, int oif,
 						xfrm_address_t *prev_saddr,
 						xfrm_address_t *prev_daddr,
 						int family)
@@ -154,7 +155,7 @@
 		daddr = x->coaddr;
 	}
 
-	dst = __xfrm_dst_lookup(net, tos, saddr, daddr, family);
+	dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family);
 
 	if (!IS_ERR(dst)) {
 		if (prev_saddr != saddr)
@@ -176,7 +177,7 @@
 
 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;
@@ -302,30 +303,27 @@
 }
 EXPORT_SYMBOL(xfrm_policy_alloc);
 
+static void xfrm_policy_destroy_rcu(struct rcu_head *head)
+{
+	struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu);
+
+	security_xfrm_policy_free(policy->security);
+	kfree(policy);
+}
+
 /* Destroy xfrm_policy: descendant resources must be released to this moment. */
 
 void xfrm_policy_destroy(struct xfrm_policy *policy)
 {
 	BUG_ON(!policy->walk.dead);
 
-	if (del_timer(&policy->timer))
+	if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer))
 		BUG();
 
-	security_xfrm_policy_free(policy->security);
-	kfree(policy);
+	call_rcu(&policy->rcu, xfrm_policy_destroy_rcu);
 }
 EXPORT_SYMBOL(xfrm_policy_destroy);
 
-static void xfrm_queue_purge(struct sk_buff_head *list)
-{
-	struct sk_buff *skb;
-
-	while ((skb = skb_dequeue(list)) != NULL) {
-		dev_put(skb->dev);
-		kfree_skb(skb);
-	}
-}
-
 /* Rule must be locked. Release descentant resources, announce
  * entry dead. The rule must be unlinked from lists to the moment.
  */
@@ -336,8 +334,9 @@
 
 	atomic_inc(&policy->genid);
 
-	del_timer(&policy->polq.hold_timer);
-	xfrm_queue_purge(&policy->polq.hold_queue);
+	if (del_timer(&policy->polq.hold_timer))
+		xfrm_pol_put(policy);
+	skb_queue_purge(&policy->polq.hold_queue);
 
 	if (del_timer(&policy->timer))
 		xfrm_pol_put(policy);
@@ -352,12 +351,39 @@
 	return __idx_hash(index, net->xfrm.policy_idx_hmask);
 }
 
+/* calculate policy hash thresholds */
+static void __get_hash_thresh(struct net *net,
+			      unsigned short family, int dir,
+			      u8 *dbits, u8 *sbits)
+{
+	switch (family) {
+	case AF_INET:
+		*dbits = net->xfrm.policy_bydst[dir].dbits4;
+		*sbits = net->xfrm.policy_bydst[dir].sbits4;
+		break;
+
+	case AF_INET6:
+		*dbits = net->xfrm.policy_bydst[dir].dbits6;
+		*sbits = net->xfrm.policy_bydst[dir].sbits6;
+		break;
+
+	default:
+		*dbits = 0;
+		*sbits = 0;
+	}
+}
+
 static struct hlist_head *policy_hash_bysel(struct net *net,
 					    const struct xfrm_selector *sel,
 					    unsigned short family, int dir)
 {
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
-	unsigned int hash = __sel_hash(sel, family, hmask);
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __sel_hash(sel, family, hmask, dbits, sbits);
 
 	return (hash == hmask + 1 ?
 		&net->xfrm.policy_inexact[dir] :
@@ -370,25 +396,35 @@
 					     unsigned short family, int dir)
 {
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
-	unsigned int hash = __addr_hash(daddr, saddr, family, hmask);
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits);
 
 	return net->xfrm.policy_bydst[dir].table + hash;
 }
 
-static void xfrm_dst_hash_transfer(struct hlist_head *list,
+static void xfrm_dst_hash_transfer(struct net *net,
+				   struct hlist_head *list,
 				   struct hlist_head *ndsttable,
-				   unsigned int nhashmask)
+				   unsigned int nhashmask,
+				   int dir)
 {
 	struct hlist_node *tmp, *entry0 = NULL;
 	struct xfrm_policy *pol;
 	unsigned int h0 = 0;
+	u8 dbits;
+	u8 sbits;
 
 redo:
 	hlist_for_each_entry_safe(pol, tmp, list, bydst) {
 		unsigned int h;
 
+		__get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
 		h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
-				pol->family, nhashmask);
+				pol->family, nhashmask, dbits, sbits);
 		if (!entry0) {
 			hlist_del(&pol->bydst);
 			hlist_add_head(&pol->bydst, ndsttable+h);
@@ -397,7 +433,7 @@
 			if (h != h0)
 				continue;
 			hlist_del(&pol->bydst);
-			hlist_add_after(entry0, &pol->bydst);
+			hlist_add_behind(&pol->bydst, entry0);
 		}
 		entry0 = &pol->bydst;
 	}
@@ -439,15 +475,15 @@
 	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_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
 
 	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));
 }
@@ -464,7 +500,7 @@
 	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);
@@ -472,7 +508,7 @@
 	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));
 }
@@ -505,7 +541,7 @@
 
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 {
-	read_lock_bh(&xfrm_policy_lock);
+	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];
@@ -514,7 +550,7 @@
 	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);
 
@@ -527,7 +563,7 @@
 	mutex_lock(&hash_resize_mutex);
 
 	total = 0;
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		if (xfrm_bydst_should_resize(net, dir, &total))
 			xfrm_bydst_resize(net, dir);
 	}
@@ -537,9 +573,89 @@
 	mutex_unlock(&hash_resize_mutex);
 }
 
+static void xfrm_hash_rebuild(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net,
+				       xfrm.policy_hthresh.work);
+	unsigned int hmask;
+	struct xfrm_policy *pol;
+	struct xfrm_policy *policy;
+	struct hlist_head *chain;
+	struct hlist_head *odst;
+	struct hlist_node *newpos;
+	int i;
+	int dir;
+	unsigned seq;
+	u8 lbits4, rbits4, lbits6, rbits6;
+
+	mutex_lock(&hash_resize_mutex);
+
+	/* read selector prefixlen thresholds */
+	do {
+		seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		lbits4 = net->xfrm.policy_hthresh.lbits4;
+		rbits4 = net->xfrm.policy_hthresh.rbits4;
+		lbits6 = net->xfrm.policy_hthresh.lbits6;
+		rbits6 = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
+
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	/* reset the bydst and inexact table in all directions */
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
+		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+		hmask = net->xfrm.policy_bydst[dir].hmask;
+		odst = net->xfrm.policy_bydst[dir].table;
+		for (i = hmask; i >= 0; i--)
+			INIT_HLIST_HEAD(odst + i);
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			/* dir out => dst = remote, src = local */
+			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = rbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = lbits6;
+		} else {
+			/* dir in/fwd => dst = local, src = remote */
+			net->xfrm.policy_bydst[dir].dbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = lbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = rbits6;
+		}
+	}
+
+	/* re-insert all policies by order of creation */
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		newpos = NULL;
+		chain = policy_hash_bysel(net, &policy->selector,
+					  policy->family,
+					  xfrm_policy_id2dir(policy->index));
+		hlist_for_each_entry(pol, chain, bydst) {
+			if (policy->priority >= pol->priority)
+				newpos = &pol->bydst;
+			else
+				break;
+		}
+		if (newpos)
+			hlist_add_behind(&policy->bydst, newpos);
+		else
+			hlist_add_head(&policy->bydst, chain);
+	}
+
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	mutex_unlock(&hash_resize_mutex);
+}
+
+void xfrm_policy_hash_rebuild(struct net *net)
+{
+	schedule_work(&net->xfrm.policy_hthresh.work);
+}
+EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
+
 /* Generate new index... KAME seems to generate them ordered by cost
  * of an absolute inpredictability of ordering of rules. This will not pass. */
-static u32 xfrm_gen_index(struct net *net, int dir)
+static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
 {
 	static u32 idx_generator;
 
@@ -549,8 +665,14 @@
 		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 = net->xfrm.policy_byidx + idx_hash(net, idx);
@@ -587,22 +709,24 @@
 	struct xfrm_policy_queue *pq = &old->polq;
 	struct sk_buff_head list;
 
+	if (skb_queue_empty(&pq->hold_queue))
+		return;
+
 	__skb_queue_head_init(&list);
 
 	spin_lock_bh(&pq->hold_queue.lock);
 	skb_queue_splice_init(&pq->hold_queue, &list);
-	del_timer(&pq->hold_timer);
+	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;
-	mod_timer(&pq->hold_timer, jiffies);
+	if (!mod_timer(&pq->hold_timer, jiffies))
+		xfrm_pol_hold(new);
 	spin_unlock_bh(&pq->hold_queue.lock);
 }
 
@@ -629,7 +753,7 @@
 	struct hlist_head *chain;
 	struct hlist_node *newpos;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
 	delpol = NULL;
 	newpos = NULL;
@@ -640,7 +764,7 @@
 		    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;
@@ -654,25 +778,29 @@
 			break;
 	}
 	if (newpos)
-		hlist_add_after(newpos, &policy->bydst);
+		hlist_add_behind(&policy->bydst, newpos);
 	else
 		hlist_add_head(&policy->bydst, chain);
-	xfrm_pol_hold(policy);
-	net->xfrm.policy_count[dir]++;
-	atomic_inc(&flow_cache_genid);
-	rt_genid_bump(net);
+	__xfrm_policy_link(policy, 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) {
 		xfrm_policy_requeue(delpol, policy);
 		__xfrm_policy_unlink(delpol, dir);
 	}
-	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
+	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
 	hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
 	policy->curlft.add_time = get_seconds();
 	policy->curlft.use_time = 0;
 	if (!mod_timer(&policy->timer, jiffies + HZ))
 		xfrm_pol_hold(policy);
-	list_add(&policy->walk.all, &net->xfrm.policy_all);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (delpol)
 		xfrm_policy_kill(delpol);
@@ -692,7 +820,7 @@
 	struct hlist_head *chain;
 
 	*err = 0;
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
@@ -705,7 +833,7 @@
 				*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;
 				}
 				__xfrm_policy_unlink(pol, dir);
@@ -714,7 +842,7 @@
 			break;
 		}
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
@@ -733,7 +861,7 @@
 		return NULL;
 
 	*err = 0;
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = net->xfrm.policy_byidx + idx_hash(net, id);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, byidx) {
@@ -744,7 +872,7 @@
 				*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;
 				}
 				__xfrm_policy_unlink(pol, dir);
@@ -753,7 +881,7 @@
 			break;
 		}
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
@@ -763,7 +891,7 @@
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static inline int
-xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0;
 
@@ -777,10 +905,7 @@
 				continue;
 			err = security_xfrm_policy_delete(pol->security);
 			if (err) {
-				xfrm_audit_policy_delete(pol, 0,
-							 audit_info->loginuid,
-							 audit_info->sessionid,
-							 audit_info->secid);
+				xfrm_audit_policy_delete(pol, 0, task_valid);
 				return err;
 			}
 		}
@@ -794,9 +919,7 @@
 								pol->security);
 				if (err) {
 					xfrm_audit_policy_delete(pol, 0,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+								 task_valid);
 					return err;
 				}
 			}
@@ -806,19 +929,19 @@
 }
 #else
 static inline int
-xfrm_policy_flush_secctx_check(struct net *net, 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(struct net *net, u8 type, struct xfrm_audit *audit_info)
+int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 {
 	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(net, type, audit_info);
+	err = xfrm_policy_flush_secctx_check(net, type, task_valid);
 	if (err)
 		goto out;
 
@@ -832,16 +955,14 @@
 			if (pol->type != type)
 				continue;
 			__xfrm_policy_unlink(pol, dir);
-			write_unlock_bh(&xfrm_policy_lock);
+			write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 			cnt++;
 
-			xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
-						 audit_info->sessionid,
-						 audit_info->secid);
+			xfrm_audit_policy_delete(pol, 1, task_valid);
 
 			xfrm_policy_kill(pol);
 
-			write_lock_bh(&xfrm_policy_lock);
+			write_lock_bh(&net->xfrm.xfrm_policy_lock);
 			goto again1;
 		}
 
@@ -853,16 +974,13 @@
 				if (pol->type != type)
 					continue;
 				__xfrm_policy_unlink(pol, dir);
-				write_unlock_bh(&xfrm_policy_lock);
+				write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 				cnt++;
 
-				xfrm_audit_policy_delete(pol, 1,
-							 audit_info->loginuid,
-							 audit_info->sessionid,
-							 audit_info->secid);
+				xfrm_audit_policy_delete(pol, 1, task_valid);
 				xfrm_policy_kill(pol);
 
-				write_lock_bh(&xfrm_policy_lock);
+				write_lock_bh(&net->xfrm.xfrm_policy_lock);
 				goto again2;
 			}
 		}
@@ -871,7 +989,7 @@
 	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);
@@ -891,11 +1009,13 @@
 	if (list_empty(&walk->walk.all) && walk->seq != 0)
 		return 0;
 
-	write_lock_bh(&xfrm_policy_lock);
+	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);
+		x = list_first_entry(&walk->walk.all,
+				     struct xfrm_policy_walk_entry, all);
+
 	list_for_each_entry_from(x, &net->xfrm.policy_all, all) {
 		if (x->dead)
 			continue;
@@ -917,7 +1037,7 @@
 	}
 	list_del_init(&walk->walk.all);
 out:
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return error;
 }
 EXPORT_SYMBOL(xfrm_policy_walk);
@@ -931,14 +1051,14 @@
 }
 EXPORT_SYMBOL(xfrm_policy_walk_init);
 
-void xfrm_policy_walk_done(struct xfrm_policy_walk *walk)
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
 {
 	if (list_empty(&walk->walk.all))
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
 	list_del(&walk->walk.all);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 EXPORT_SYMBOL(xfrm_policy_walk_done);
 
@@ -983,7 +1103,7 @@
 	if (unlikely(!daddr || !saddr))
 		return NULL;
 
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_direct(net, daddr, saddr, family, dir);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
@@ -1003,6 +1123,9 @@
 	}
 	chain = &net->xfrm.policy_inexact[dir];
 	hlist_for_each_entry(pol, chain, bydst) {
+		if ((pol->priority >= priority) && ret)
+			break;
+
 		err = xfrm_policy_match(pol, fl, type, family, dir);
 		if (err) {
 			if (err == -ESRCH)
@@ -1011,15 +1134,15 @@
 				ret = ERR_PTR(err);
 				goto fail;
 			}
-		} else if (pol->priority < priority) {
+		} else {
 			ret = pol;
 			break;
 		}
 	}
-	if (ret)
-		xfrm_pol_hold(ret);
+
+	xfrm_pol_hold(ret);
 fail:
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	return ret;
 }
@@ -1092,17 +1215,25 @@
 	}
 }
 
-static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
-						 const struct flowi *fl)
+static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
+						 const struct flowi *fl, u16 family)
 {
 	struct xfrm_policy *pol;
+	struct net *net = sock_net(sk);
 
-	read_lock_bh(&xfrm_policy_lock);
-	if ((pol = sk->sk_policy[dir]) != NULL) {
-		bool match = xfrm_selector_match(&pol->selector, fl,
-						 sk->sk_family);
+	rcu_read_lock();
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
+	pol = rcu_dereference(sk->sk_policy[dir]);
+	if (pol != NULL) {
+		bool match;
 		int err = 0;
 
+		if (pol->family != family) {
+			pol = NULL;
+			goto out;
+		}
+
+		match = xfrm_selector_match(&pol->selector, fl, family);
 		if (match) {
 			if ((sk->sk_mark & pol->mark.m) != pol->mark.v) {
 				pol = NULL;
@@ -1121,24 +1252,18 @@
 			pol = NULL;
 	}
 out:
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	rcu_read_unlock();
 	return pol;
 }
 
 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
 {
 	struct net *net = xp_net(pol);
-	struct hlist_head *chain = policy_hash_bysel(net, &pol->selector,
-						     pol->family, dir);
 
 	list_add(&pol->walk.all, &net->xfrm.policy_all);
-	hlist_add_head(&pol->bydst, chain);
-	hlist_add_head(&pol->byidx, net->xfrm.policy_byidx+idx_hash(net, pol->index));
 	net->xfrm.policy_count[dir]++;
 	xfrm_pol_hold(pol);
-
-	if (xfrm_bydst_should_resize(net, dir, NULL))
-		schedule_work(&net->xfrm.policy_hash_work);
 }
 
 static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
@@ -1146,22 +1271,38 @@
 {
 	struct net *net = xp_net(pol);
 
-	if (hlist_unhashed(&pol->bydst))
+	if (list_empty(&pol->walk.all))
 		return NULL;
 
-	hlist_del(&pol->bydst);
-	hlist_del(&pol->byidx);
-	list_del(&pol->walk.all);
+	/* Socket policies are not hashed. */
+	if (!hlist_unhashed(&pol->bydst)) {
+		hlist_del(&pol->bydst);
+		hlist_del(&pol->byidx);
+	}
+
+	list_del_init(&pol->walk.all);
 	net->xfrm.policy_count[dir]--;
 
 	return pol;
 }
 
+static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_link(pol, XFRM_POLICY_MAX + dir);
+}
+
+static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir)
+{
+	__xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir);
+}
+
 int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 {
-	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) {
 		xfrm_policy_kill(pol);
 		return 0;
@@ -1180,14 +1321,15 @@
 		return -EINVAL;
 #endif
 
-	write_lock_bh(&xfrm_policy_lock);
-	old_pol = sk->sk_policy[dir];
-	sk->sk_policy[dir] = pol;
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
+	old_pol = rcu_dereference_protected(sk->sk_policy[dir],
+				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
 	if (pol) {
 		pol->curlft.add_time = get_seconds();
-		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
-		__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
+		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
+		xfrm_sk_policy_link(pol, dir);
 	}
+	rcu_assign_pointer(sk->sk_policy[dir], pol);
 	if (old_pol) {
 		if (pol)
 			xfrm_policy_requeue(old_pol, pol);
@@ -1195,9 +1337,9 @@
 		/* Unlinking succeeds always. This is the only function
 		 * allowed to delete or replace socket policy.
 		 */
-		__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
+		xfrm_sk_policy_unlink(old_pol, dir);
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (old_pol) {
 		xfrm_policy_kill(old_pol);
@@ -1208,6 +1350,7 @@
 static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 {
 	struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
+	struct net *net = xp_net(old);
 
 	if (newp) {
 		newp->selector = old->selector;
@@ -1226,37 +1369,46 @@
 		newp->type = old->type;
 		memcpy(newp->xfrm_vec, old->xfrm_vec,
 		       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
-		write_lock_bh(&xfrm_policy_lock);
-		__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
-		write_unlock_bh(&xfrm_policy_lock);
+		write_lock_bh(&net->xfrm.xfrm_policy_lock);
+		xfrm_sk_policy_link(newp, dir);
+		write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 		xfrm_pol_put(newp);
 	}
 	return newp;
 }
 
-int __xfrm_sk_clone_policy(struct sock *sk)
+int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
 {
-	struct xfrm_policy *p0 = sk->sk_policy[0],
-			   *p1 = sk->sk_policy[1];
+	const struct xfrm_policy *p;
+	struct xfrm_policy *np;
+	int i, ret = 0;
 
-	sk->sk_policy[0] = sk->sk_policy[1] = NULL;
-	if (p0 && (sk->sk_policy[0] = clone_policy(p0, 0)) == NULL)
-		return -ENOMEM;
-	if (p1 && (sk->sk_policy[1] = clone_policy(p1, 1)) == NULL)
-		return -ENOMEM;
-	return 0;
+	rcu_read_lock();
+	for (i = 0; i < 2; i++) {
+		p = rcu_dereference(osk->sk_policy[i]);
+		if (p) {
+			np = clone_policy(p, i);
+			if (unlikely(!np)) {
+				ret = -ENOMEM;
+				break;
+			}
+			rcu_assign_pointer(sk->sk_policy[i], np);
+		}
+	}
+	rcu_read_unlock();
+	return ret;
 }
 
 static int
-xfrm_get_saddr(struct net *net, xfrm_address_t *local, xfrm_address_t *remote,
-	       unsigned short family)
+xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local,
+	       xfrm_address_t *remote, unsigned short family)
 {
 	int err;
 	struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
 
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
-	err = afinfo->get_saddr(net, local, remote);
+	err = afinfo->get_saddr(net, oif, local, remote);
 	xfrm_policy_put_afinfo(afinfo);
 	return err;
 }
@@ -1274,7 +1426,7 @@
 	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;
@@ -1285,7 +1437,9 @@
 			remote = &tmpl->id.daddr;
 			local = &tmpl->saddr;
 			if (xfrm_addr_any(local, tmpl->encap_family)) {
-				error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family);
+				error = xfrm_get_saddr(net, fl->flowi_oif,
+						       &tmp, remote,
+						       tmpl->encap_family);
 				if (error)
 					goto fail;
 				local = &tmp;
@@ -1304,9 +1458,9 @@
 			error = (x->km.state == XFRM_STATE_ERROR ?
 				 -EINVAL : -EAGAIN);
 			xfrm_state_put(x);
-		}
-		else if (error == -ESRCH)
+		} else if (error == -ESRCH) {
 			error = -EAGAIN;
+		}
 
 		if (!tmpl->optional)
 			goto fail;
@@ -1314,7 +1468,7 @@
 	return nx;
 
 fail:
-	for (nx--; nx>=0; nx--)
+	for (nx--; nx >= 0; nx--)
 		xfrm_state_put(xfrm[nx]);
 	return error;
 }
@@ -1351,7 +1505,7 @@
 	return cnx;
 
  fail:
-	for (cnx--; cnx>=0; cnx--)
+	for (cnx--; cnx >= 0; cnx--)
 		xfrm_state_put(tpp[cnx]);
 	return error;
 
@@ -1454,8 +1608,6 @@
 
 		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);
 
@@ -1565,8 +1717,8 @@
 
 		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
 			family = xfrm[i]->props.family;
-			dst = xfrm_dst_lookup(xfrm[i], tos, &saddr, &daddr,
-					      family);
+			dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
+					      &saddr, &daddr, family);
 			err = PTR_ERR(dst);
 			if (IS_ERR(dst))
 				goto put_states;
@@ -1629,20 +1781,22 @@
 	goto out;
 }
 
-static int inline
-xfrm_dst_alloc_copy(void **target, const 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, const 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;
@@ -1653,8 +1807,8 @@
 #endif
 }
 
-static int inline
-xfrm_dst_update_origin(struct dst_entry *dst, const 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;
@@ -1692,7 +1846,7 @@
 				xfrm_pols_put(pols, *num_pols);
 				return PTR_ERR(pols[1]);
 			}
-			(*num_pols) ++;
+			(*num_pols)++;
 			(*num_xfrms) += pols[1]->xfrm_nr;
 		}
 	}
@@ -1746,7 +1900,7 @@
 	}
 
 	xdst->num_pols = num_pols;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 	xdst->policy_genid = atomic_read(&pols[0]->genid);
 
 	return xdst;
@@ -1754,26 +1908,28 @@
 
 static void xfrm_policy_queue_process(unsigned long arg)
 {
-	int err = 0;
 	struct sk_buff *skb;
 	struct sock *sk;
 	struct dst_entry *dst;
-	struct net_device *dev;
 	struct xfrm_policy *pol = (struct xfrm_policy *)arg;
+	struct net *net = xp_net(pol);
 	struct xfrm_policy_queue *pq = &pol->polq;
 	struct flowi fl;
 	struct sk_buff_head list;
 
 	spin_lock(&pq->hold_queue.lock);
 	skb = skb_peek(&pq->hold_queue);
+	if (!skb) {
+		spin_unlock(&pq->hold_queue.lock);
+		goto out;
+	}
 	dst = skb_dst(skb);
 	sk = skb->sk;
 	xfrm_decode_session(skb, &fl, dst->ops->family);
 	spin_unlock(&pq->hold_queue.lock);
 
 	dst_hold(dst->path);
-	dst = xfrm_lookup(xp_net(pol), dst->path, &fl,
-			  sk, 0);
+	dst = xfrm_lookup(net, dst->path, &fl, sk, 0);
 	if (IS_ERR(dst))
 		goto purge_queue;
 
@@ -1784,8 +1940,9 @@
 			goto purge_queue;
 
 		pq->timeout = pq->timeout << 1;
-		mod_timer(&pq->hold_timer, jiffies + pq->timeout);
-		return;
+		if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout))
+			xfrm_pol_hold(pol);
+	goto out;
 	}
 
 	dst_release(dst);
@@ -1802,36 +1959,41 @@
 
 		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);
+		dst = xfrm_lookup(net, skb_dst(skb)->path, &fl, skb->sk, 0);
 		if (IS_ERR(dst)) {
-			dev_put(skb->dev);
 			kfree_skb(skb);
 			continue;
 		}
 
-		nf_reset(skb);
+		nf_reset_no_generic_ct(skb);
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 
-		dev = skb->dev;
-		err = dst_output(skb);
-		dev_put(dev);
+		dst_output(net, skb->sk, skb);
 	}
 
+out:
+	xfrm_pol_put(pol);
 	return;
 
 purge_queue:
 	pq->timeout = 0;
-	xfrm_queue_purge(&pq->hold_queue);
+	skb_queue_purge(&pq->hold_queue);
+	xfrm_pol_put(pol);
 }
 
-static int xdst_queue_output(struct sk_buff *skb)
+static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	unsigned long sched_next;
 	struct dst_entry *dst = skb_dst(skb);
 	struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
-	struct xfrm_policy_queue *pq = &xdst->pols[0]->polq;
+	struct xfrm_policy *pol = xdst->pols[0];
+	struct xfrm_policy_queue *pq = &pol->polq;
+
+	if (unlikely(skb_fclone_busy(sk, skb))) {
+		kfree_skb(skb);
+		return 0;
+	}
 
 	if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) {
 		kfree_skb(skb);
@@ -1839,7 +2001,6 @@
 	}
 
 	skb_dst_force(skb);
-	dev_hold(skb->dev);
 
 	spin_lock_bh(&pq->hold_queue.lock);
 
@@ -1851,10 +2012,12 @@
 	if (del_timer(&pq->hold_timer)) {
 		if (time_before(pq->hold_timer.expires, sched_next))
 			sched_next = pq->hold_timer.expires;
+		xfrm_pol_put(pol);
 	}
 
 	__skb_queue_tail(&pq->hold_queue, skb);
-	mod_timer(&pq->hold_timer, sched_next);
+	if (!mod_timer(&pq->hold_timer, sched_next))
+		xfrm_pol_hold(pol);
 
 	spin_unlock_bh(&pq->hold_queue.lock);
 
@@ -1862,13 +2025,14 @@
 }
 
 static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
-						 struct dst_entry *dst,
+						 struct xfrm_flo *xflo,
 						 const struct flowi *fl,
 						 int num_xfrms,
 						 u16 family)
 {
 	int err;
 	struct net_device *dev;
+	struct dst_entry *dst;
 	struct dst_entry *dst1;
 	struct xfrm_dst *xdst;
 
@@ -1876,10 +2040,12 @@
 	if (IS_ERR(xdst))
 		return xdst;
 
-	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 ||
-	    (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP))
+	if (!(xflo->flags & XFRM_LOOKUP_QUEUE) ||
+	    net->xfrm.sysctl_larval_drop ||
+	    num_xfrms <= 0)
 		return xdst;
 
+	dst = xflo->dst_orig;
 	dst1 = &xdst->u.dst;
 	dst_hold(dst);
 	xdst->route = dst;
@@ -1921,7 +2087,7 @@
 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_flo *xflo = (struct xfrm_flo *)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;
@@ -1962,7 +2128,8 @@
 			goto make_dummy_bundle;
 	}
 
-	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig);
+	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
+						  xflo->dst_orig);
 	if (IS_ERR(new_xdst)) {
 		err = PTR_ERR(new_xdst);
 		if (err != -EAGAIN)
@@ -1996,14 +2163,14 @@
 	/* 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);
+	xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family);
 	if (IS_ERR(xdst)) {
 		xfrm_pols_put(pols, num_pols);
 		return ERR_CAST(xdst);
 	}
 	xdst->num_pols = num_pols;
 	xdst->num_xfrms = num_xfrms;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 
 	dst_hold(&xdst->u.dst);
 	return &xdst->flo;
@@ -2042,7 +2209,7 @@
  */
 struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			      const struct flowi *fl,
-			      struct sock *sk, int flags)
+			      const struct sock *sk, int flags)
 {
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	struct flow_cache_object *flo;
@@ -2052,14 +2219,14 @@
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
 	int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
 
-restart:
 	dst = NULL;
 	xdst = NULL;
 	route = NULL;
 
+	sk = sk_const_to_full_sk(sk);
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
 		num_pols = 1;
-		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
 		err = xfrm_expand_policies(fl, family, pols,
 					   &num_pols, &num_xfrms);
 		if (err < 0)
@@ -2085,24 +2252,24 @@
 			}
 
 			dst_hold(&xdst->u.dst);
-
-			spin_lock_bh(&xfrm_policy_sk_bundle_lock);
-			xdst->u.dst.next = xfrm_policy_sk_bundles;
-			xfrm_policy_sk_bundles = &xdst->u.dst;
-			spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
-
+			xdst->u.dst.flags |= DST_NOCACHE;
 			route = xdst->route;
 		}
 	}
 
 	if (xdst == NULL) {
+		struct xfrm_flo xflo;
+
+		xflo.dst_orig = dst_orig;
+		xflo.flags = flags;
+
 		/* 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);
+					xfrm_bundle_lookup, &xflo);
 		if (flo == NULL)
 			goto nopol;
 		if (IS_ERR(flo)) {
@@ -2113,7 +2280,7 @@
 
 		num_pols = xdst->num_pols;
 		num_xfrms = xdst->num_xfrms;
-		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
 		route = xdst->route;
 	}
 
@@ -2126,31 +2293,12 @@
 		 * have the xfrm_state's. We need to wait for KM to
 		 * negotiate new SA's or bail out with error.*/
 		if (net->xfrm.sysctl_larval_drop) {
-			/* EREMOTE tells the caller to generate
-			 * a one-shot blackhole route. */
-			dst_release(dst);
-			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-
-			return make_blackhole(net, family, dst_orig);
+			err = -EREMOTE;
+			goto error;
 		}
-		if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) {
-			DECLARE_WAITQUEUE(wait, current);
 
-			add_wait_queue(&net->xfrm.km_waitq, &wait);
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-			set_current_state(TASK_RUNNING);
-			remove_wait_queue(&net->xfrm.km_waitq, &wait);
-
-			if (!signal_pending(current)) {
-				dst_release(dst);
-				goto restart;
-			}
-
-			err = -ERESTART;
-		} else
-			err = -EAGAIN;
+		err = -EAGAIN;
 
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 		goto error;
@@ -2198,12 +2346,31 @@
 error:
 	dst_release(dst);
 dropdst:
-	dst_release(dst_orig);
+	if (!(flags & XFRM_LOOKUP_KEEP_DST_REF))
+		dst_release(dst_orig);
 	xfrm_pols_put(pols, drop_pols);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(xfrm_lookup);
 
+/* Callers of xfrm_lookup_route() must ensure a call to dst_output().
+ * Otherwise we may send out blackholed packets.
+ */
+struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
+				    const struct flowi *fl,
+				    const struct sock *sk, int flags)
+{
+	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
+					    flags | XFRM_LOOKUP_QUEUE |
+					    XFRM_LOOKUP_KEEP_DST_REF);
+
+	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
+		return make_blackhole(net, dst_orig->ops->family, dst_orig);
+
+	return dst;
+}
+EXPORT_SYMBOL(xfrm_lookup_route);
+
 static inline int
 xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
 {
@@ -2326,7 +2493,7 @@
 	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(net, LINUX_MIB_XFRMINSTATEMISMATCH);
@@ -2336,8 +2503,9 @@
 	}
 
 	pol = NULL;
+	sk = sk_to_full_sk(sk);
 	if (sk && sk->sk_policy[dir]) {
-		pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
 		if (IS_ERR(pol)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
 			return 0;
@@ -2372,7 +2540,7 @@
 	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(net, XFRM_POLICY_TYPE_MAIN,
@@ -2384,7 +2552,7 @@
 				return 0;
 			}
 			pols[1]->curlft.use_time = get_seconds();
-			npols ++;
+			npols++;
 		}
 	}
 #endif
@@ -2416,7 +2584,7 @@
 		}
 		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;
 		}
 
@@ -2469,7 +2637,7 @@
 
 	skb_dst_force(skb);
 
-	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0);
+	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE);
 	if (IS_ERR(dst)) {
 		res = 0;
 		dst = NULL;
@@ -2541,33 +2709,15 @@
 	return dst;
 }
 
-static void __xfrm_garbage_collect(struct net *net)
-{
-	struct dst_entry *head, *next;
-
-	spin_lock_bh(&xfrm_policy_sk_bundle_lock);
-	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;
-	}
-}
-
 void xfrm_garbage_collect(struct net *net)
 {
-	flow_cache_flush();
-	__xfrm_garbage_collect(net);
+	flow_cache_flush(net);
 }
 EXPORT_SYMBOL(xfrm_garbage_collect);
 
 static void xfrm_garbage_collect_deferred(struct net *net)
 {
-	flow_cache_flush_deferred();
-	__xfrm_garbage_collect(net);
+	flow_cache_flush_deferred(net);
 }
 
 static void xfrm_init_pmtu(struct dst_entry *dst)
@@ -2681,7 +2831,6 @@
 
 int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 {
-	struct net *net;
 	int err = 0;
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
@@ -2689,7 +2838,7 @@
 		return -EAFNOSUPPORT;
 	spin_lock(&xfrm_policy_afinfo_lock);
 	if (unlikely(xfrm_policy_afinfo[afinfo->family] != NULL))
-		err = -ENOBUFS;
+		err = -EEXIST;
 	else {
 		struct dst_ops *dst_ops = afinfo->dst_ops;
 		if (likely(dst_ops->kmem_cachep == NULL))
@@ -2712,26 +2861,6 @@
 	}
 	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);
@@ -2767,25 +2896,9 @@
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
-static void __net_init xfrm_dst_ops_init(struct net *net)
-{
-	struct xfrm_policy_afinfo *afinfo;
-
-	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;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
 	switch (event) {
 	case NETDEV_DOWN:
@@ -2802,21 +2915,19 @@
 static int __net_init xfrm_statistics_init(struct net *net)
 {
 	int rv;
-
-	if (snmp_mib_init((void __percpu **)net->mib.xfrm_statistics,
-			  sizeof(struct linux_xfrm_mib),
-			  __alignof__(struct linux_xfrm_mib)) < 0)
+	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)
-		snmp_mib_free((void __percpu **)net->mib.xfrm_statistics);
+		free_percpu(net->mib.xfrm_statistics);
 	return rv;
 }
 
 static void xfrm_statistics_fini(struct net *net)
 {
 	xfrm_proc_fini(net);
-	snmp_mib_free((void __percpu **)net->mib.xfrm_statistics);
+	free_percpu(net->mib.xfrm_statistics);
 }
 #else
 static int __net_init xfrm_statistics_init(struct net *net)
@@ -2848,10 +2959,11 @@
 		goto out_byidx;
 	net->xfrm.policy_idx_hmask = hmask;
 
-	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
 		net->xfrm.policy_count[dir] = 0;
+		net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
 		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 
 		htab = &net->xfrm.policy_bydst[dir];
@@ -2859,10 +2971,21 @@
 		if (!htab->table)
 			goto out_bydst;
 		htab->hmask = hmask;
-	}
+		htab->dbits4 = 32;
+		htab->sbits4 = 32;
+		htab->dbits6 = 128;
+		htab->sbits6 = 128;
+	}
+	net->xfrm.policy_hthresh.lbits4 = 32;
+	net->xfrm.policy_hthresh.rbits4 = 32;
+	net->xfrm.policy_hthresh.lbits6 = 128;
+	net->xfrm.policy_hthresh.rbits6 = 128;
+
+	seqlock_init(&net->xfrm.policy_hthresh.lock);
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
+	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	if (net_eq(net, &init_net))
 		register_netdevice_notifier(&xfrm_dev_notifier);
 	return 0;
@@ -2881,25 +3004,18 @@
 
 static void xfrm_policy_fini(struct net *net)
 {
-	struct xfrm_audit audit_info;
 	unsigned int sz;
 	int dir;
 
 	flush_work(&net->xfrm.policy_hash_work);
 #ifdef CONFIG_XFRM_SUB_POLICY
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = -1;
-	audit_info.secid = 0;
-	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info);
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
 #endif
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = -1;
-	audit_info.secid = 0;
-	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info);
+	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++) {
+	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
 		WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
@@ -2919,6 +3035,11 @@
 {
 	int rv;
 
+	/* 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);
+
 	rv = xfrm_statistics_init(net);
 	if (rv < 0)
 		goto out_statistics;
@@ -2928,12 +3049,17 @@
 	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;
+
 	return 0;
 
+out:
+	xfrm_sysctl_fini(net);
 out_sysctl:
 	xfrm_policy_fini(net);
 out_policy:
@@ -2946,6 +3072,7 @@
 
 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);
@@ -2961,6 +3088,7 @@
 {
 	register_pernet_subsys(&xfrm_net_ops);
 	xfrm_input_init();
+	xfrm_output_init();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -2974,7 +3102,7 @@
 		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=%pI4", &sel->saddr.a4);
 		if (sel->prefixlen_s != 32)
@@ -2998,15 +3126,14 @@
 	}
 }
 
-void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
-			   kuid_t auid, u32 sessionid, 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, sessionid, 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);
@@ -3014,14 +3141,14 @@
 EXPORT_SYMBOL_GPL(xfrm_audit_policy_add);
 
 void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
-			      kuid_t auid, u32 sessionid, 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, sessionid, 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);
@@ -3051,15 +3178,15 @@
 	return false;
 }
 
-static struct xfrm_policy * xfrm_migrate_policy_find(const 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_head *chain;
 	u32 priority = ~0U;
 
-	read_lock_bh(&xfrm_policy_lock);
-	chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir);
+	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) {
@@ -3068,20 +3195,21 @@
 			break;
 		}
 	}
-	chain = &init_net.xfrm.policy_inexact[dir];
+	chain = &net->xfrm.policy_inexact[dir];
 	hlist_for_each_entry(pol, chain, bydst) {
+		if ((pol->priority >= priority) && ret)
+			break;
+
 		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
-		    pol->type == type &&
-		    pol->priority < priority) {
+		    pol->type == type) {
 			ret = pol;
 			break;
 		}
 	}
 
-	if (ret)
-		xfrm_pol_hold(ret);
+	xfrm_pol_hold(ret);
 
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	return ret;
 }
@@ -3192,7 +3320,7 @@
 
 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
-		 struct xfrm_kmaddress *k)
+		 struct xfrm_kmaddress *k, struct net *net)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -3205,14 +3333,14 @@
 		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))) {