1 files changed, 201 insertions, 124 deletions

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b9c3f9e943a..0ab54134bb4 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -35,8 +35,6 @@
       destination/tunnel endpoint. (output)
  */
 
-static DEFINE_SPINLOCK(xfrm_state_lock);
-
 static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
 
 static inline unsigned int xfrm_dst_hash(struct net *net,
@@ -127,7 +125,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 		goto out_unlock;
 	}
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
 	for (i = net->xfrm.state_hmask; i >= 0; i--)
@@ -144,7 +142,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	net->xfrm.state_byspi = nspi;
 	net->xfrm.state_hmask = nhashmask;
 
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	osize = (ohashmask + 1) * sizeof(struct hlist_head);
 	xfrm_hash_free(odst, osize);
@@ -163,6 +161,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 int __xfrm_state_delete(struct xfrm_state *x);
 
 int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
+bool km_is_alive(const struct km_event *c);
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 
 static DEFINE_SPINLOCK(xfrm_type_lock);
@@ -374,8 +373,6 @@ static void xfrm_state_gc_task(struct work_struct *work)
 
 	hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
 		xfrm_state_gc_destroy(x);
-
-	wake_up(&net->xfrm.km_waitq);
 }
 
 static inline unsigned long make_jiffies(long secs)
@@ -386,11 +383,10 @@ static inline unsigned long make_jiffies(long secs)
 		return secs*HZ;
 }
 
-static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
+static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
 	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
 	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
-	struct net *net = xs_net(x);
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
@@ -453,27 +449,21 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
 	if (warn)
 		km_state_expired(x, 0, 0);
 resched:
-	if (next != LONG_MAX){
+	if (next != LONG_MAX) {
 		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
 	}
 
 	goto out;
 
 expired:
-	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) {
+	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0)
 		x->km.state = XFRM_STATE_EXPIRED;
-		wake_up(&net->xfrm.km_waitq);
-		next = 2;
-		goto resched;
-	}
 
 	err = __xfrm_state_delete(x);
-	if (!err && x->id.spi)
+	if (!err)
 		km_state_expired(x, 1, 0);
 
-	xfrm_audit_state_delete(x, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 
 out:
 	spin_unlock(&x->lock);
@@ -535,14 +525,14 @@ int __xfrm_state_delete(struct xfrm_state *x)
 
 	if (x->km.state != XFRM_STATE_DEAD) {
 		x->km.state = XFRM_STATE_DEAD;
-		spin_lock(&xfrm_state_lock);
+		spin_lock(&net->xfrm.xfrm_state_lock);
 		list_del(&x->km.all);
 		hlist_del(&x->bydst);
 		hlist_del(&x->bysrc);
 		if (x->id.spi)
 			hlist_del(&x->byspi);
 		net->xfrm.state_num--;
-		spin_unlock(&xfrm_state_lock);
+		spin_unlock(&net->xfrm.xfrm_state_lock);
 
 		/* All xfrm_state objects are created by xfrm_state_alloc.
 		 * The xfrm_state_alloc call gives a reference, and that
@@ -570,7 +560,7 @@ EXPORT_SYMBOL(xfrm_state_delete);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static inline int
-xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0;
 
@@ -580,10 +570,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi
 		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
 			if (xfrm_id_proto_match(x->id.proto, proto) &&
 			   (err = security_xfrm_state_delete(x)) != 0) {
-				xfrm_audit_state_delete(x, 0,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+				xfrm_audit_state_delete(x, 0, task_valid);
 				return err;
 			}
 		}
@@ -593,18 +580,18 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi
 }
 #else
 static inline int
-xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	return 0;
 }
 #endif
 
-int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0, cnt = 0;
 
-	spin_lock_bh(&xfrm_state_lock);
-	err = xfrm_state_flush_secctx_check(net, proto, audit_info);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	err = xfrm_state_flush_secctx_check(net, proto, task_valid);
 	if (err)
 		goto out;
 
@@ -616,18 +603,16 @@ restart:
 			if (!xfrm_state_kern(x) &&
 			    xfrm_id_proto_match(x->id.proto, proto)) {
 				xfrm_state_hold(x);
-				spin_unlock_bh(&xfrm_state_lock);
+				spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 				err = xfrm_state_delete(x);
 				xfrm_audit_state_delete(x, err ? 0 : 1,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+							task_valid);
 				xfrm_state_put(x);
 				if (!err)
 					cnt++;
 
-				spin_lock_bh(&xfrm_state_lock);
+				spin_lock_bh(&net->xfrm.xfrm_state_lock);
 				goto restart;
 			}
 		}
@@ -636,19 +621,18 @@ restart:
 		err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
-	wake_up(&net->xfrm.km_waitq);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_flush);
 
 void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 {
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	si->sadcnt = net->xfrm.state_num;
 	si->sadhcnt = net->xfrm.state_hmask;
 	si->sadhmcnt = xfrm_state_hashmax;
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 }
 EXPORT_SYMBOL(xfrm_sad_getinfo);
 
@@ -798,10 +782,11 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	struct xfrm_state *best = NULL;
 	u32 mark = pol->mark.v & pol->mark.m;
 	unsigned short encap_family = tmpl->encap_family;
+	struct km_event c;
 
 	to_put = NULL;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family == encap_family &&
@@ -815,7 +800,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 			xfrm_state_look_at(pol, x, fl, encap_family,
 					   &best, &acquire_in_progress, &error);
 	}
-	if (best)
+	if (best || acquire_in_progress)
 		goto found;
 
 	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
@@ -824,7 +809,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
 		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
-		    xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
+		    xfrm_addr_equal(&x->id.daddr, daddr, encap_family) &&
 		    tmpl->mode == x->props.mode &&
 		    tmpl->id.proto == x->id.proto &&
 		    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
@@ -842,6 +827,17 @@ found:
 			error = -EEXIST;
 			goto out;
 		}
+
+		c.net = net;
+		/* If the KMs have no listeners (yet...), avoid allocating an SA
+		 * for each and every packet - garbage collection might not
+		 * handle the flood.
+		 */
+		if (!km_is_alive(&c)) {
+			error = -ESRCH;
+			goto out;
+		}
+
 		x = xfrm_state_alloc(net);
 		if (x == NULL) {
 			error = -ENOMEM;
@@ -886,7 +882,7 @@ out:
 		xfrm_state_hold(x);
 	else
 		*err = acquire_in_progress ? -EAGAIN : error;
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	if (to_put)
 		xfrm_state_put(to_put);
 	return x;
@@ -900,7 +896,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 	unsigned int h;
 	struct xfrm_state *rx = NULL, *x = NULL;
 
-	spin_lock(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family == family &&
@@ -918,13 +914,35 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 
 	if (rx)
 		xfrm_state_hold(rx);
-	spin_unlock(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 
 	return rx;
 }
 EXPORT_SYMBOL(xfrm_stateonly_find);
 
+struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+					      unsigned short family)
+{
+	struct xfrm_state *x;
+	struct xfrm_state_walk *w;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	list_for_each_entry(w, &net->xfrm.state_all, all) {
+		x = container_of(w, struct xfrm_state, km);
+		if (x->props.family != family ||
+			x->id.spi != spi)
+			continue;
+
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		xfrm_state_hold(x);
+		return x;
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(xfrm_state_lookup_byspi);
+
 static void __xfrm_state_insert(struct xfrm_state *x)
 {
 	struct net *net = xs_net(x);
@@ -950,14 +968,12 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 	if (x->replay_maxage)
 		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
 
-	wake_up(&net->xfrm.km_waitq);
-
 	net->xfrm.state_num++;
 
 	xfrm_hash_grow_check(net, x->bydst.next != NULL);
 }
 
-/* xfrm_state_lock is held */
+/* net->xfrm.xfrm_state_lock is held */
 static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 {
 	struct net *net = xs_net(xnew);
@@ -980,14 +996,16 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 
 void xfrm_state_insert(struct xfrm_state *x)
 {
-	spin_lock_bh(&xfrm_state_lock);
+	struct net *net = xs_net(x);
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	__xfrm_state_bump_genids(x);
 	__xfrm_state_insert(x);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 }
 EXPORT_SYMBOL(xfrm_state_insert);
 
-/* xfrm_state_lock is held */
+/* net->xfrm.xfrm_state_lock is held */
 static struct xfrm_state *__find_acq_core(struct net *net,
 					  const struct xfrm_mark *m,
 					  unsigned short family, u8 mode,
@@ -1079,7 +1097,7 @@ int xfrm_state_add(struct xfrm_state *x)
 
 	to_put = NULL;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	x1 = __xfrm_state_locate(x, use_spi, family);
 	if (x1) {
@@ -1108,7 +1126,7 @@ int xfrm_state_add(struct xfrm_state *x)
 	err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (x1) {
 		xfrm_state_delete(x1);
@@ -1123,10 +1141,9 @@ out:
 EXPORT_SYMBOL(xfrm_state_add);
 
 #ifdef CONFIG_XFRM_MIGRATE
-static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
+static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig)
 {
 	struct net *net = xs_net(orig);
-	int err = -ENOMEM;
 	struct xfrm_state *x = xfrm_state_alloc(net);
 	if (!x)
 		goto out;
@@ -1147,6 +1164,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
 	}
 	x->props.aalgo = orig->props.aalgo;
 
+	if (orig->aead) {
+		x->aead = xfrm_algo_aead_clone(orig->aead);
+		if (!x->aead)
+			goto error;
+	}
 	if (orig->ealg) {
 		x->ealg = xfrm_algo_clone(orig->ealg);
 		if (!x->ealg)
@@ -1175,20 +1197,21 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
 	}
 
 	if (orig->replay_esn) {
-		err = xfrm_replay_clone(x, orig);
-		if (err)
+		if (xfrm_replay_clone(x, orig))
 			goto error;
 	}
 
 	memcpy(&x->mark, &orig->mark, sizeof(x->mark));
 
-	err = xfrm_init_state(x);
-	if (err)
+	if (xfrm_init_state(x) < 0)
 		goto error;
 
 	x->props.flags = orig->props.flags;
 	x->props.extra_flags = orig->props.extra_flags;
 
+	x->tfcpad = orig->tfcpad;
+	x->replay_maxdiff = orig->replay_maxdiff;
+	x->replay_maxage = orig->replay_maxage;
 	x->curlft.add_time = orig->curlft.add_time;
 	x->km.state = orig->km.state;
 	x->km.seq = orig->km.seq;
@@ -1198,21 +1221,20 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
  error:
 	xfrm_state_put(x);
 out:
-	if (errp)
-		*errp = err;
 	return NULL;
 }
 
-/* xfrm_state_lock is held */
-struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
 {
 	unsigned int h;
-	struct xfrm_state *x;
+	struct xfrm_state *x = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (m->reqid) {
-		h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr,
+		h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
 				  m->reqid, m->old_family);
-		hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) {
+		hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
@@ -1224,12 +1246,12 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	} else {
-		h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr,
+		h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
 				  m->old_family);
-		hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) {
+		hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
@@ -1239,21 +1261,22 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	}
 
-	return NULL;
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	return x;
 }
 EXPORT_SYMBOL(xfrm_migrate_state_find);
 
-struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
-				       struct xfrm_migrate *m)
+struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+				      struct xfrm_migrate *m)
 {
 	struct xfrm_state *xc;
-	int err;
 
-	xc = xfrm_state_clone(x, &err);
+	xc = xfrm_state_clone(x);
 	if (!xc)
 		return NULL;
 
@@ -1266,7 +1289,7 @@ struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
 		   state is to be updated as it is a part of triplet */
 		xfrm_state_insert(xc);
 	} else {
-		if ((err = xfrm_state_add(xc)) < 0)
+		if (xfrm_state_add(xc) < 0)
 			goto error;
 	}
 
@@ -1283,10 +1306,11 @@ int xfrm_state_update(struct xfrm_state *x)
 	struct xfrm_state *x1, *to_put;
 	int err;
 	int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
+	struct net *net = xs_net(x);
 
 	to_put = NULL;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x1 = __xfrm_state_locate(x, use_spi, x->props.family);
 
 	err = -ESRCH;
@@ -1306,7 +1330,7 @@ int xfrm_state_update(struct xfrm_state *x)
 	err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (to_put)
 		xfrm_state_put(to_put);
@@ -1357,7 +1381,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL);
+		tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
 		return -EINVAL;
 	}
 
@@ -1377,9 +1401,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
 EXPORT_SYMBOL(xfrm_state_lookup);
@@ -1391,9 +1415,9 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
 EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
@@ -1405,9 +1429,9 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	return x;
 }
@@ -1416,17 +1440,17 @@ EXPORT_SYMBOL(xfrm_find_acq);
 #ifdef CONFIG_XFRM_SUB_POLICY
 int
 xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
-	       unsigned short family)
+	       unsigned short family, struct net *net)
 {
 	int err = 0;
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
 	if (!afinfo)
 		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
 	if (afinfo->tmpl_sort)
 		err = afinfo->tmpl_sort(dst, src, n);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
@@ -1438,13 +1462,15 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 {
 	int err = 0;
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct net *net = xs_net(*src);
+
 	if (!afinfo)
 		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	if (afinfo->state_sort)
 		err = afinfo->state_sort(dst, src, n);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
@@ -1476,9 +1502,9 @@ struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __xfrm_find_acq_byseq(net, mark, seq);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
 EXPORT_SYMBOL(xfrm_find_acq_byseq);
@@ -1496,6 +1522,30 @@ u32 xfrm_get_acqseq(void)
 }
 EXPORT_SYMBOL(xfrm_get_acqseq);
 
+int verify_spi_info(u8 proto, u32 min, u32 max)
+{
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+		break;
+
+	case IPPROTO_COMP:
+		/* IPCOMP spi is 16-bits. */
+		if (max >= 0x10000)
+			return -EINVAL;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (min > max)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(verify_spi_info);
+
 int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 {
 	struct net *net = xs_net(x);
@@ -1525,8 +1575,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 		x->id.spi = minspi;
 	} else {
 		u32 spi = 0;
-		for (h=0; h<high-low+1; h++) {
-			spi = low + net_random()%(high-low+1);
+		for (h = 0; h < high-low+1; h++) {
+			spi = low + prandom_u32()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
 				x->id.spi = htonl(spi);
@@ -1536,10 +1586,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 		}
 	}
 	if (x->id.spi) {
-		spin_lock_bh(&xfrm_state_lock);
+		spin_lock_bh(&net->xfrm.xfrm_state_lock);
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
 		hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
-		spin_unlock_bh(&xfrm_state_lock);
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 		err = 0;
 	}
@@ -1551,6 +1601,23 @@ unlock:
 }
 EXPORT_SYMBOL(xfrm_alloc_spi);
 
+static bool __xfrm_state_filter_match(struct xfrm_state *x,
+				      struct xfrm_address_filter *filter)
+{
+	if (filter) {
+		if ((filter->family == AF_INET ||
+		     filter->family == AF_INET6) &&
+		    x->props.family != filter->family)
+			return false;
+
+		return addr_match(&x->props.saddr, &filter->saddr,
+				  filter->splen) &&
+		       addr_match(&x->id.daddr, &filter->daddr,
+				  filter->dplen);
+	}
+	return true;
+}
+
 int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 		    int (*func)(struct xfrm_state *, int, void*),
 		    void *data)
@@ -1562,7 +1629,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 	if (walk->seq != 0 && list_empty(&walk->all))
 		return 0;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	if (list_empty(&walk->all))
 		x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all);
 	else
@@ -1573,6 +1640,8 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 		state = container_of(x, struct xfrm_state, km);
 		if (!xfrm_id_proto_match(state->id.proto, walk->proto))
 			continue;
+		if (!__xfrm_state_filter_match(state, walk->filter))
+			continue;
 		err = func(state, walk->seq, data);
 		if (err) {
 			list_move_tail(&walk->all, &x->all);
@@ -1586,34 +1655,38 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 	}
 	list_del_init(&walk->all);
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_walk);
 
-void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
+void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto,
+			  struct xfrm_address_filter *filter)
 {
 	INIT_LIST_HEAD(&walk->all);
 	walk->proto = proto;
 	walk->state = XFRM_STATE_DEAD;
 	walk->seq = 0;
+	walk->filter = filter;
 }
 EXPORT_SYMBOL(xfrm_state_walk_init);
 
-void xfrm_state_walk_done(struct xfrm_state_walk *walk)
+void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
 {
+	kfree(walk->filter);
+
 	if (list_empty(&walk->all))
 		return;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	list_del(&walk->all);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 }
 EXPORT_SYMBOL(xfrm_state_walk_done);
 
 static void xfrm_replay_timer_handler(unsigned long data)
 {
-	struct xfrm_state *x = (struct xfrm_state*)data;
+	struct xfrm_state *x = (struct xfrm_state *)data;
 
 	spin_lock(&x->lock);
 
@@ -1655,16 +1728,12 @@ EXPORT_SYMBOL(km_state_notify);
 
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid)
 {
-	struct net *net = xs_net(x);
 	struct km_event c;
 
 	c.data.hard = hard;
 	c.portid = portid;
 	c.event = XFRM_MSG_EXPIRE;
 	km_state_notify(x, &c);
-
-	if (hard)
-		wake_up(&net->xfrm.km_waitq);
 }
 
 EXPORT_SYMBOL(km_state_expired);
@@ -1707,16 +1776,12 @@ EXPORT_SYMBOL(km_new_mapping);
 
 void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid)
 {
-	struct net *net = xp_net(pol);
 	struct km_event c;
 
 	c.data.hard = hard;
 	c.portid = portid;
 	c.event = XFRM_MSG_POLEXPIRE;
 	km_policy_notify(pol, dir, &c);
-
-	if (hard)
-		wake_up(&net->xfrm.km_waitq);
 }
 EXPORT_SYMBOL(km_policy_expired);
 
@@ -1762,6 +1827,24 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address
 }
 EXPORT_SYMBOL(km_report);
 
+bool km_is_alive(const struct km_event *c)
+{
+	struct xfrm_mgr *km;
+	bool is_alive = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		if (km->is_alive && km->is_alive(c)) {
+			is_alive = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return is_alive;
+}
+EXPORT_SYMBOL(km_is_alive);
+
 int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
 {
 	int err;
@@ -2025,7 +2108,7 @@ int __net_init xfrm_state_init(struct net *net)
 	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
 	INIT_HLIST_HEAD(&net->xfrm.state_gc_list);
 	INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task);
-	init_waitqueue_head(&net->xfrm.km_waitq);
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
 	return 0;
 
 out_byspi:
@@ -2038,14 +2121,10 @@ out_bydst:
 
 void xfrm_state_fini(struct net *net)
 {
-	struct xfrm_audit audit_info;
 	unsigned int sz;
 
 	flush_work(&net->xfrm.state_hash_work);
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = -1;
-	audit_info.secid = 0;
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info);
+	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
 	flush_work(&net->xfrm.state_gc_work);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
@@ -2070,7 +2149,7 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x,
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(x->props.family) {
+	switch (x->props.family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
 				 &x->props.saddr.a4, &x->id.daddr.a4);
@@ -2100,7 +2179,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 		iph6 = ipv6_hdr(skb);
 		audit_log_format(audit_buf,
 				 " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
-				 &iph6->saddr,&iph6->daddr,
+				 &iph6->saddr, &iph6->daddr,
 				 iph6->flow_lbl[0] & 0x0f,
 				 iph6->flow_lbl[1],
 				 iph6->flow_lbl[2]);
@@ -2108,30 +2187,28 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 	}
 }
 
-void xfrm_audit_state_add(struct xfrm_state *x, int result,
-			  kuid_t auid, u32 sessionid, u32 secid)
+void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SAD-add");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	xfrm_audit_helper_sainfo(x, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	audit_log_end(audit_buf);
 }
 EXPORT_SYMBOL_GPL(xfrm_audit_state_add);
 
-void xfrm_audit_state_delete(struct xfrm_state *x, int result,
-			     kuid_t auid, u32 sessionid, u32 secid)
+void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SAD-delete");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	xfrm_audit_helper_sainfo(x, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	audit_log_end(audit_buf);