3 files changed, 490 insertions, 50 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 98ec53bd3ac7..f5eae9febd26 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -26,8 +26,8 @@
 #include <net/xfrm.h>
 #include <net/ip.h>
 
-DECLARE_MUTEX(xfrm_cfg_sem);
-EXPORT_SYMBOL(xfrm_cfg_sem);
+DEFINE_MUTEX(xfrm_cfg_mutex);
+EXPORT_SYMBOL(xfrm_cfg_mutex);
 
 static DEFINE_RWLOCK(xfrm_policy_lock);
 
@@ -203,7 +203,7 @@ static void xfrm_policy_timer(unsigned long data)
 	}
 
 	if (warn)
-		km_policy_expired(xp, dir, 0);
+		km_policy_expired(xp, dir, 0, 0);
 	if (next != LONG_MAX &&
 	    !mod_timer(&xp->timer, jiffies + make_jiffies(next)))
 		xfrm_pol_hold(xp);
@@ -216,7 +216,7 @@ out:
 expired:
 	read_unlock(&xp->lock);
 	if (!xfrm_policy_delete(xp, dir))
-		km_policy_expired(xp, dir, 1);
+		km_policy_expired(xp, dir, 1, 0);
 	xfrm_pol_put(xp);
 }
 
@@ -621,6 +621,7 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 	}
 	return -ENOENT;
 }
+EXPORT_SYMBOL(xfrm_policy_delete);
 
 int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 {
@@ -782,7 +783,7 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl,
 	int nx = 0;
 	int err;
 	u32 genid;
-	u16 family = dst_orig->ops->family;
+	u16 family;
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
 	u32 sk_sid = security_sk_sid(sk, fl, dir);
 restart:
@@ -796,13 +797,14 @@ restart:
 		if ((dst_orig->flags & DST_NOXFRM) || !xfrm_policy_list[XFRM_POLICY_OUT])
 			return 0;
 
-		policy = flow_cache_lookup(fl, sk_sid, family, dir,
-					   xfrm_policy_lookup);
+		policy = flow_cache_lookup(fl, sk_sid, dst_orig->ops->family,
+					   dir, xfrm_policy_lookup);
 	}
 
 	if (!policy)
 		return 0;
 
+	family = dst_orig->ops->family;
 	policy->curlft.use_time = (unsigned long)xtime.tv_sec;
 
 	switch (policy->action) {
@@ -885,8 +887,6 @@ restart:
 			 * We can't enlist stable bundles either.
 			 */
 			write_unlock_bh(&policy->lock);
-
-			xfrm_pol_put(policy);
 			if (dst)
 				dst_free(dst);
 
@@ -997,13 +997,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			struct sec_decap_state *xvec = &(skb->sp->x[i]);
 			if (!xfrm_selector_match(&xvec->xvec->sel, &fl, family))
 				return 0;
-
-			/* If there is a post_input processor, try running it */
-			if (xvec->xvec->type->post_input &&
-			    (xvec->xvec->type->post_input)(xvec->xvec,
-							   &(xvec->decap),
-							   skb) != 0)
-				return 0;
 		}
 	}
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e12d0be5f976..a8e14dc1b04e 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -20,6 +20,15 @@
 #include <linux/module.h>
 #include <asm/uaccess.h>
 
+struct sock *xfrm_nl;
+EXPORT_SYMBOL(xfrm_nl);
+
+u32 sysctl_xfrm_aevent_etime = XFRM_AE_ETIME;
+EXPORT_SYMBOL(sysctl_xfrm_aevent_etime);
+
+u32 sysctl_xfrm_aevent_rseqth = XFRM_AE_SEQT_SIZE;
+EXPORT_SYMBOL(sysctl_xfrm_aevent_rseqth);
+
 /* Each xfrm_state may be linked to two tables:
 
    1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
@@ -50,18 +59,20 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 
 static int xfrm_state_gc_flush_bundles;
 
-static int __xfrm_state_delete(struct xfrm_state *x);
+int __xfrm_state_delete(struct xfrm_state *x);
 
 static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family);
 static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
 
-static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
-static void km_state_expired(struct xfrm_state *x, int hard);
+int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
+void km_state_expired(struct xfrm_state *x, int hard, u32 pid);
 
 static void xfrm_state_gc_destroy(struct xfrm_state *x)
 {
 	if (del_timer(&x->timer))
 		BUG();
+	if (del_timer(&x->rtimer))
+		BUG();
 	kfree(x->aalg);
 	kfree(x->ealg);
 	kfree(x->calg);
@@ -153,7 +164,7 @@ static void xfrm_timer_handler(unsigned long data)
 
 	x->km.dying = warn;
 	if (warn)
-		km_state_expired(x, 0);
+		km_state_expired(x, 0, 0);
 resched:
 	if (next != LONG_MAX &&
 	    !mod_timer(&x->timer, jiffies + make_jiffies(next)))
@@ -168,13 +179,15 @@ expired:
 		goto resched;
 	}
 	if (!__xfrm_state_delete(x) && x->id.spi)
-		km_state_expired(x, 1);
+		km_state_expired(x, 1, 0);
 
 out:
 	spin_unlock(&x->lock);
 	xfrm_state_put(x);
 }
 
+static void xfrm_replay_timer_handler(unsigned long data);
+
 struct xfrm_state *xfrm_state_alloc(void)
 {
 	struct xfrm_state *x;
@@ -190,11 +203,16 @@ struct xfrm_state *xfrm_state_alloc(void)
 		init_timer(&x->timer);
 		x->timer.function = xfrm_timer_handler;
 		x->timer.data	  = (unsigned long)x;
+		init_timer(&x->rtimer);
+		x->rtimer.function = xfrm_replay_timer_handler;
+		x->rtimer.data     = (unsigned long)x;
 		x->curlft.add_time = (unsigned long)xtime.tv_sec;
 		x->lft.soft_byte_limit = XFRM_INF;
 		x->lft.soft_packet_limit = XFRM_INF;
 		x->lft.hard_byte_limit = XFRM_INF;
 		x->lft.hard_packet_limit = XFRM_INF;
+		x->replay_maxage = 0;
+		x->replay_maxdiff = 0;
 		spin_lock_init(&x->lock);
 	}
 	return x;
@@ -212,7 +230,7 @@ void __xfrm_state_destroy(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(__xfrm_state_destroy);
 
-static int __xfrm_state_delete(struct xfrm_state *x)
+int __xfrm_state_delete(struct xfrm_state *x)
 {
 	int err = -ESRCH;
 
@@ -220,14 +238,16 @@ static int __xfrm_state_delete(struct xfrm_state *x)
 		x->km.state = XFRM_STATE_DEAD;
 		spin_lock(&xfrm_state_lock);
 		list_del(&x->bydst);
-		atomic_dec(&x->refcnt);
+		__xfrm_state_put(x);
 		if (x->id.spi) {
 			list_del(&x->byspi);
-			atomic_dec(&x->refcnt);
+			__xfrm_state_put(x);
 		}
 		spin_unlock(&xfrm_state_lock);
 		if (del_timer(&x->timer))
-			atomic_dec(&x->refcnt);
+			__xfrm_state_put(x);
+		if (del_timer(&x->rtimer))
+			__xfrm_state_put(x);
 
 		/* The number two in this test is the reference
 		 * mentioned in the comment below plus the reference
@@ -243,12 +263,13 @@ static int __xfrm_state_delete(struct xfrm_state *x)
 		 * The xfrm_state_alloc call gives a reference, and that
 		 * is what we are dropping here.
 		 */
-		atomic_dec(&x->refcnt);
+		__xfrm_state_put(x);
 		err = 0;
 	}
 
 	return err;
 }
+EXPORT_SYMBOL(__xfrm_state_delete);
 
 int xfrm_state_delete(struct xfrm_state *x)
 {
@@ -426,6 +447,10 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 	if (!mod_timer(&x->timer, jiffies + HZ))
 		xfrm_state_hold(x);
 
+	if (x->replay_maxage &&
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+		xfrm_state_hold(x);
+
 	wake_up(&km_waitq);
 }
 
@@ -580,7 +605,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	    (x->curlft.bytes >= x->lft.soft_byte_limit ||
 	     x->curlft.packets >= x->lft.soft_packet_limit)) {
 		x->km.dying = 1;
-		km_state_expired(x, 0);
+		km_state_expired(x, 0, 0);
 	}
 	return 0;
 }
@@ -762,6 +787,61 @@ out:
 }
 EXPORT_SYMBOL(xfrm_state_walk);
 
+
+void xfrm_replay_notify(struct xfrm_state *x, int event)
+{
+	struct km_event c;
+	/* we send notify messages in case
+	 *  1. we updated on of the sequence numbers, and the seqno difference
+	 *     is at least x->replay_maxdiff, in this case we also update the
+	 *     timeout of our timer function
+	 *  2. if x->replay_maxage has elapsed since last update,
+	 *     and there were changes
+	 *
+	 *  The state structure must be locked!
+	 */
+
+	switch (event) {
+	case XFRM_REPLAY_UPDATE:
+		if (x->replay_maxdiff &&
+		    (x->replay.seq - x->preplay.seq < x->replay_maxdiff) &&
+		    (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))
+			return;
+
+		break;
+
+	case XFRM_REPLAY_TIMEOUT:
+		if ((x->replay.seq == x->preplay.seq) &&
+		    (x->replay.bitmap == x->preplay.bitmap) &&
+		    (x->replay.oseq == x->preplay.oseq))
+			return;
+
+		break;
+	}
+
+	memcpy(&x->preplay, &x->replay, sizeof(struct xfrm_replay_state));
+	c.event = XFRM_MSG_NEWAE;
+	c.data.aevent = event;
+	km_state_notify(x, &c);
+
+	if (x->replay_maxage &&
+	    !mod_timer(&x->rtimer, jiffies + x->replay_maxage))
+		xfrm_state_hold(x);
+}
+EXPORT_SYMBOL(xfrm_replay_notify);
+
+static void xfrm_replay_timer_handler(unsigned long data)
+{
+	struct xfrm_state *x = (struct xfrm_state*)data;
+
+	spin_lock(&x->lock);
+
+	if (xfrm_aevent_is_on() && x->km.state == XFRM_STATE_VALID)
+		xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
+
+	spin_unlock(&x->lock);
+}
+
 int xfrm_replay_check(struct xfrm_state *x, u32 seq)
 {
 	u32 diff;
@@ -805,6 +885,9 @@ void xfrm_replay_advance(struct xfrm_state *x, u32 seq)
 		diff = x->replay.seq - seq;
 		x->replay.bitmap |= (1U << diff);
 	}
+
+	if (xfrm_aevent_is_on())
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 }
 EXPORT_SYMBOL(xfrm_replay_advance);
 
@@ -835,11 +918,12 @@ void km_state_notify(struct xfrm_state *x, struct km_event *c)
 EXPORT_SYMBOL(km_policy_notify);
 EXPORT_SYMBOL(km_state_notify);
 
-static void km_state_expired(struct xfrm_state *x, int hard)
+void km_state_expired(struct xfrm_state *x, int hard, u32 pid)
 {
 	struct km_event c;
 
 	c.data.hard = hard;
+	c.pid = pid;
 	c.event = XFRM_MSG_EXPIRE;
 	km_state_notify(x, &c);
 
@@ -847,11 +931,12 @@ static void km_state_expired(struct xfrm_state *x, int hard)
 		wake_up(&km_waitq);
 }
 
+EXPORT_SYMBOL(km_state_expired);
 /*
  * We send to all registered managers regardless of failure
  * We are happy with one success
 */
-static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
+int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
 {
 	int err = -EINVAL, acqret;
 	struct xfrm_mgr *km;
@@ -865,6 +950,7 @@ static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_polic
 	read_unlock(&xfrm_km_lock);
 	return err;
 }
+EXPORT_SYMBOL(km_query);
 
 int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport)
 {
@@ -883,17 +969,19 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport)
 }
 EXPORT_SYMBOL(km_new_mapping);
 
-void km_policy_expired(struct xfrm_policy *pol, int dir, int hard)
+void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid)
 {
 	struct km_event c;
 
 	c.data.hard = hard;
+	c.pid = pid;
 	c.event = XFRM_MSG_POLEXPIRE;
 	km_policy_notify(pol, dir, &c);
 
 	if (hard)
 		wake_up(&km_waitq);
 }
+EXPORT_SYMBOL(km_policy_expired);
 
 int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
 {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ac87a09ba83e..81d1005830f4 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -28,8 +28,6 @@
 #include <net/netlink.h>
 #include <asm/uaccess.h>
 
-static struct sock *xfrm_nl;
-
 static int verify_one_alg(struct rtattr **xfrma, enum xfrm_attr_type_t type)
 {
 	struct rtattr *rt = xfrma[type - 1];
@@ -103,9 +101,6 @@ static inline int verify_sec_ctx_len(struct rtattr **xfrma)
 
 	uctx = RTA_DATA(rt);
 
-	if (uctx->ctx_len > PAGE_SIZE)
-		return -EINVAL;
-
 	len += sizeof(struct xfrm_user_sec_ctx);
 	len += uctx->ctx_len;
 
@@ -276,6 +271,56 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info *
 	x->props.flags = p->flags;
 }
 
+/*
+ * someday when pfkey also has support, we could have the code
+ * somehow made shareable and move it to xfrm_state.c - JHS
+ *
+*/
+static int xfrm_update_ae_params(struct xfrm_state *x, struct rtattr **xfrma)
+{
+	int err = - EINVAL;
+	struct rtattr *rp = xfrma[XFRMA_REPLAY_VAL-1];
+	struct rtattr *lt = xfrma[XFRMA_LTIME_VAL-1];
+	struct rtattr *et = xfrma[XFRMA_ETIMER_THRESH-1];
+	struct rtattr *rt = xfrma[XFRMA_REPLAY_THRESH-1];
+
+	if (rp) {
+		struct xfrm_replay_state *replay;
+		if (RTA_PAYLOAD(rp) < sizeof(*replay))
+			goto error;
+		replay = RTA_DATA(rp);
+		memcpy(&x->replay, replay, sizeof(*replay));
+		memcpy(&x->preplay, replay, sizeof(*replay));
+	}
+
+	if (lt) {
+		struct xfrm_lifetime_cur *ltime;
+		if (RTA_PAYLOAD(lt) < sizeof(*ltime))
+			goto error;
+		ltime = RTA_DATA(lt);
+		x->curlft.bytes = ltime->bytes;
+		x->curlft.packets = ltime->packets;
+		x->curlft.add_time = ltime->add_time;
+		x->curlft.use_time = ltime->use_time;
+	}
+
+	if (et) {
+		if (RTA_PAYLOAD(et) < sizeof(u32))
+			goto error;
+		x->replay_maxage = *(u32*)RTA_DATA(et);
+	}
+
+	if (rt) {
+		if (RTA_PAYLOAD(rt) < sizeof(u32))
+			goto error;
+		x->replay_maxdiff = *(u32*)RTA_DATA(rt);
+	}
+
+	return 0;
+error:
+	return err;
+}
+
 static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p,
 					       struct rtattr **xfrma,
 					       int *errp)
@@ -311,6 +356,18 @@ static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p,
 		goto error;
 
 	x->km.seq = p->seq;
+	x->replay_maxdiff = sysctl_xfrm_aevent_rseqth;
+	/* sysctl_xfrm_aevent_etime is in 100ms units */
+	x->replay_maxage = (sysctl_xfrm_aevent_etime*HZ)/XFRM_AE_ETH_M;
+	x->preplay.bitmap = 0;
+	x->preplay.seq = x->replay.seq+x->replay_maxdiff;
+	x->preplay.oseq = x->replay.oseq +x->replay_maxdiff;
+
+	/* override default values from above */
+
+	err = xfrm_update_ae_params(x, (struct rtattr **)xfrma);
+	if (err	< 0)
+		goto error;
 
 	return x;
 
@@ -345,7 +402,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
-		xfrm_state_put(x);
+		__xfrm_state_put(x);
 		goto out;
 	}
 
@@ -1025,9 +1082,142 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma
 	return 0;
 }
 
-static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+
+static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c)
+{
+	struct xfrm_aevent_id *id;
+	struct nlmsghdr *nlh;
+	struct xfrm_lifetime_cur ltime;
+	unsigned char *b = skb->tail;
+
+	nlh = NLMSG_PUT(skb, c->pid, c->seq, XFRM_MSG_NEWAE, sizeof(*id));
+	id = NLMSG_DATA(nlh);
+	nlh->nlmsg_flags = 0;
+
+	id->sa_id.daddr = x->id.daddr;
+	id->sa_id.spi = x->id.spi;
+	id->sa_id.family = x->props.family;
+	id->sa_id.proto = x->id.proto;
+	id->flags = c->data.aevent;
+
+	RTA_PUT(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), &x->replay);
+
+	ltime.bytes = x->curlft.bytes;
+	ltime.packets = x->curlft.packets;
+	ltime.add_time = x->curlft.add_time;
+	ltime.use_time = x->curlft.use_time;
+
+	RTA_PUT(skb, XFRMA_LTIME_VAL, sizeof(struct xfrm_lifetime_cur), &ltime);
+
+	if (id->flags&XFRM_AE_RTHR) {
+		RTA_PUT(skb,XFRMA_REPLAY_THRESH,sizeof(u32),&x->replay_maxdiff);
+	}
+
+	if (id->flags&XFRM_AE_ETHR) {
+		u32 etimer = x->replay_maxage*10/HZ;
+		RTA_PUT(skb,XFRMA_ETIMER_THRESH,sizeof(u32),&etimer);
+	}
+
+	nlh->nlmsg_len = skb->tail - b;
+	return skb->len;
+
+rtattr_failure:
+nlmsg_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_state *x;
+	struct sk_buff *r_skb;
+	int err;
+	struct km_event c;
+	struct xfrm_aevent_id *p = NLMSG_DATA(nlh);
+	int len = NLMSG_LENGTH(sizeof(struct xfrm_aevent_id));
+	struct xfrm_usersa_id *id = &p->sa_id;
+
+	len += RTA_SPACE(sizeof(struct xfrm_replay_state));
+	len += RTA_SPACE(sizeof(struct xfrm_lifetime_cur));
+
+	if (p->flags&XFRM_AE_RTHR)
+		len+=RTA_SPACE(sizeof(u32));
+
+	if (p->flags&XFRM_AE_ETHR)
+		len+=RTA_SPACE(sizeof(u32));
+
+	r_skb = alloc_skb(len, GFP_ATOMIC);
+	if (r_skb == NULL)
+		return -ENOMEM;
+
+	x = xfrm_state_lookup(&id->daddr, id->spi, id->proto, id->family);
+	if (x == NULL) {
+		kfree(r_skb);
+		return -ESRCH;
+	}
+
+	/*
+	 * XXX: is this lock really needed - none of the other
+	 * gets lock (the concern is things getting updated
+	 * while we are still reading) - jhs
+	*/
+	spin_lock_bh(&x->lock);
+	c.data.aevent = p->flags;
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+
+	if (build_aevent(r_skb, x, &c) < 0)
+		BUG();
+	err = netlink_unicast(xfrm_nl, r_skb,
+			      NETLINK_CB(skb).pid, MSG_DONTWAIT);
+	spin_unlock_bh(&x->lock);
+	xfrm_state_put(x);
+	return err;
+}
+
+static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 {
+	struct xfrm_state *x;
 	struct km_event c;
+	int err = - EINVAL;
+	struct xfrm_aevent_id *p = NLMSG_DATA(nlh);
+	struct rtattr *rp = xfrma[XFRMA_REPLAY_VAL-1];
+	struct rtattr *lt = xfrma[XFRMA_LTIME_VAL-1];
+
+	if (!lt && !rp)
+		return err;
+
+	/* pedantic mode - thou shalt sayeth replaceth */
+	if (!(nlh->nlmsg_flags&NLM_F_REPLACE))
+		return err;
+
+	x = xfrm_state_lookup(&p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family);
+	if (x == NULL)
+		return -ESRCH;
+
+	if (x->km.state != XFRM_STATE_VALID)
+		goto out;
+
+	spin_lock_bh(&x->lock);
+	err = xfrm_update_ae_params(x,(struct rtattr **)xfrma);
+	spin_unlock_bh(&x->lock);
+	if (err	< 0)
+		goto out;
+
+	c.event = nlh->nlmsg_type;
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+	c.data.aevent = XFRM_AE_CU;
+	km_state_notify(x, &c);
+	err = 0;
+out:
+	xfrm_state_put(x);
+	return err;
+}
+
+static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+struct km_event c;
 
 	xfrm_policy_flush();
 	c.event = nlh->nlmsg_type;
@@ -1037,6 +1227,139 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **x
 	return 0;
 }
 
+static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_policy *xp;
+	struct xfrm_user_polexpire *up = NLMSG_DATA(nlh);
+	struct xfrm_userpolicy_info *p = &up->pol;
+	int err = -ENOENT;
+
+	if (p->index)
+		xp = xfrm_policy_byid(p->dir, p->index, 0);
+	else {
+		struct rtattr **rtattrs = (struct rtattr **)xfrma;
+		struct rtattr *rt = rtattrs[XFRMA_SEC_CTX-1];
+		struct xfrm_policy tmp;
+
+		err = verify_sec_ctx_len(rtattrs);
+		if (err)
+			return err;
+
+		memset(&tmp, 0, sizeof(struct xfrm_policy));
+		if (rt) {
+			struct xfrm_user_sec_ctx *uctx = RTA_DATA(rt);
+
+			if ((err = security_xfrm_policy_alloc(&tmp, uctx)))
+				return err;
+		}
+		xp = xfrm_policy_bysel_ctx(p->dir, &p->sel, tmp.security, 0);
+		security_xfrm_policy_free(&tmp);
+	}
+
+	if (xp == NULL)
+		return err;
+											read_lock(&xp->lock);
+	if (xp->dead) {
+		read_unlock(&xp->lock);
+		goto out;
+	}
+
+	read_unlock(&xp->lock);
+	err = 0;
+	if (up->hard) {
+		xfrm_policy_delete(xp, p->dir);
+	} else {
+		// reset the timers here?
+		printk("Dont know what to do with soft policy expire\n");
+	}
+	km_policy_expired(xp, p->dir, up->hard, current->pid);
+
+out:
+	xfrm_pol_put(xp);
+	return err;
+}
+
+static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_state *x;
+	int err;
+	struct xfrm_user_expire *ue = NLMSG_DATA(nlh);
+	struct xfrm_usersa_info *p = &ue->state;
+
+	x = xfrm_state_lookup(&p->id.daddr, p->id.spi, p->id.proto, p->family);
+		err = -ENOENT;
+
+	if (x == NULL)
+		return err;
+
+	err = -EINVAL;
+
+	spin_lock_bh(&x->lock);
+	if (x->km.state != XFRM_STATE_VALID)
+		goto out;
+	km_state_expired(x, ue->hard, current->pid);
+
+	if (ue->hard)
+		__xfrm_state_delete(x);
+out:
+	spin_unlock_bh(&x->lock);
+	xfrm_state_put(x);
+	return err;
+}
+
+static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
+{
+	struct xfrm_policy *xp;
+	struct xfrm_user_tmpl *ut;
+	int i;
+	struct rtattr *rt = xfrma[XFRMA_TMPL-1];
+
+	struct xfrm_user_acquire *ua = NLMSG_DATA(nlh);
+	struct xfrm_state *x = xfrm_state_alloc();
+	int err = -ENOMEM;
+
+	if (!x)
+		return err;
+
+	err = verify_newpolicy_info(&ua->policy);
+	if (err) {
+		printk("BAD policy passed\n");
+		kfree(x);
+		return err;
+	}
+
+	/*   build an XP */
+	xp = xfrm_policy_construct(&ua->policy, (struct rtattr **) xfrma, &err);        if (!xp) {
+		kfree(x);
+		return err;
+	}
+
+	memcpy(&x->id, &ua->id, sizeof(ua->id));
+	memcpy(&x->props.saddr, &ua->saddr, sizeof(ua->saddr));
+	memcpy(&x->sel, &ua->sel, sizeof(ua->sel));
+
+	ut = RTA_DATA(rt);
+	/* extract the templates and for each call km_key */
+	for (i = 0; i < xp->xfrm_nr; i++, ut++) {
+		struct xfrm_tmpl *t = &xp->xfrm_vec[i];
+		memcpy(&x->id, &t->id, sizeof(x->id));
+		x->props.mode = t->mode;
+		x->props.reqid = t->reqid;
+		x->props.family = ut->family;
+		t->aalgos = ua->aalgos;
+		t->ealgos = ua->ealgos;
+		t->calgos = ua->calgos;
+		err = km_query(x, t, xp);
+
+	}
+
+	kfree(x);
+	kfree(xp);
+
+	return 0;
+}
+
+
 #define XMSGSIZE(type) NLMSG_LENGTH(sizeof(struct type))
 
 static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
@@ -1054,6 +1377,8 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire),
 	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
 	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = NLMSG_LENGTH(0),
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
 };
 
 #undef XMSGSIZE
@@ -1071,10 +1396,15 @@ static struct xfrm_link {
 	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_get_policy,
 						   .dump = xfrm_dump_policy   },
 	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi },
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = { .doit = xfrm_add_acquire   },
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = { .doit = xfrm_add_sa_expire },
 	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = { .doit = xfrm_add_policy    },
 	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = { .doit = xfrm_add_sa        },
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = { .doit = xfrm_add_pol_expire},
 	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = { .doit = xfrm_flush_sa      },
 	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_flush_policy  },
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = { .doit = xfrm_new_ae  },
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = { .doit = xfrm_get_ae  },
 };
 
 static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp)
@@ -1156,26 +1486,26 @@ static void xfrm_netlink_rcv(struct sock *sk, int len)
 	unsigned int qlen = 0;
 
 	do {
-		down(&xfrm_cfg_sem);
+		mutex_lock(&xfrm_cfg_mutex);
 		netlink_run_queue(sk, &qlen, &xfrm_user_rcv_msg);
-		up(&xfrm_cfg_sem);
+		mutex_unlock(&xfrm_cfg_mutex);
 
 	} while (qlen);
 }
 
-static int build_expire(struct sk_buff *skb, struct xfrm_state *x, int hard)
+static int build_expire(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c)
 {
 	struct xfrm_user_expire *ue;
 	struct nlmsghdr *nlh;
 	unsigned char *b = skb->tail;
 
-	nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_EXPIRE,
+	nlh = NLMSG_PUT(skb, c->pid, 0, XFRM_MSG_EXPIRE,
 			sizeof(*ue));
 	ue = NLMSG_DATA(nlh);
 	nlh->nlmsg_flags = 0;
 
 	copy_to_user_state(x, &ue->state);
-	ue->hard = (hard != 0) ? 1 : 0;
+	ue->hard = (c->data.hard != 0) ? 1 : 0;
 
 	nlh->nlmsg_len = skb->tail - b;
 	return skb->len;
@@ -1194,13 +1524,31 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c)
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_expire(skb, x, c->data.hard) < 0)
+	if (build_expire(skb, x, c) < 0)
 		BUG();
 
 	NETLINK_CB(skb).dst_group = XFRMNLGRP_EXPIRE;
 	return netlink_broadcast(xfrm_nl, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
 }
 
+static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c)
+{
+	struct sk_buff *skb;
+	int len = NLMSG_LENGTH(sizeof(struct xfrm_aevent_id));
+
+	len += RTA_SPACE(sizeof(struct xfrm_replay_state));
+	len += RTA_SPACE(sizeof(struct xfrm_lifetime_cur));
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+
+	if (build_aevent(skb, x, c) < 0)
+		BUG();
+
+	NETLINK_CB(skb).dst_group = XFRMNLGRP_AEVENTS;
+	return netlink_broadcast(xfrm_nl, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC);
+}
+
 static int xfrm_notify_sa_flush(struct km_event *c)
 {
 	struct xfrm_usersa_flush *p;
@@ -1313,6 +1661,8 @@ static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c)
 	switch (c->event) {
 	case XFRM_MSG_EXPIRE:
 		return xfrm_exp_state_notify(x, c);
+	case XFRM_MSG_NEWAE:
+		return xfrm_aevent_state_notify(x, c);
 	case XFRM_MSG_DELSA:
 	case XFRM_MSG_UPDSA:
 	case XFRM_MSG_NEWSA:
@@ -1443,13 +1793,14 @@ static struct xfrm_policy *xfrm_compile_policy(u16 family, int opt,
 }
 
 static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
-			   int dir, int hard)
+			   int dir, struct km_event *c)
 {
 	struct xfrm_user_polexpire *upe;
 	struct nlmsghdr *nlh;
+	int hard = c->data.hard;
 	unsigned char *b = skb->tail;
 
-	nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe));
+	nlh = NLMSG_PUT(skb, c->pid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe));
 	upe = NLMSG_DATA(nlh);
 	nlh->nlmsg_flags = 0;
 
@@ -1480,7 +1831,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_eve
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_polexpire(skb, xp, dir, c->data.hard) < 0)
+	if (build_polexpire(skb, xp, dir, c) < 0)
 		BUG();
 
 	NETLINK_CB(skb).dst_group = XFRMNLGRP_EXPIRE;
@@ -1596,12 +1947,15 @@ static struct xfrm_mgr netlink_mgr = {
 
 static int __init xfrm_user_init(void)
 {
+	struct sock *nlsk;
+
 	printk(KERN_INFO "Initializing IPsec netlink socket\n");
 
-	xfrm_nl = netlink_kernel_create(NETLINK_XFRM, XFRMNLGRP_MAX,
-	                                xfrm_netlink_rcv, THIS_MODULE);
-	if (xfrm_nl == NULL)
+	nlsk = netlink_kernel_create(NETLINK_XFRM, XFRMNLGRP_MAX,
+	                             xfrm_netlink_rcv, THIS_MODULE);
+	if (nlsk == NULL)
 		return -ENOMEM;
+	rcu_assign_pointer(xfrm_nl, nlsk);
 
 	xfrm_register_km(&netlink_mgr);
 
@@ -1610,11 +1964,16 @@ static int __init xfrm_user_init(void)
 
 static void __exit xfrm_user_exit(void)
 {
+	struct sock *nlsk = xfrm_nl;
+
 	xfrm_unregister_km(&netlink_mgr);
-	sock_release(xfrm_nl->sk_socket);
+	rcu_assign_pointer(xfrm_nl, NULL);
+	synchronize_rcu();
+	sock_release(nlsk->sk_socket);
 }
 
 module_init(xfrm_user_init);
 module_exit(xfrm_user_exit);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);
+