take 2 WAS(Re: PATCH: IPSEC xfrm events

[jamal <hadi@cyberus.ca>]

[-- Attachment #1: Type: text/plain, Size: 1165 bytes --]

On Fri, 2005-04-01 at 20:46, Herbert Xu wrote:
> On Fri, Apr 01, 2005 at 08:42:45PM -0500, jamal wrote:
> > 
> > So always go v2?
> 
> Yes since that's the only version that the kernel knows how to generate.

Ok, heres a general patch first cut i think i got all that was discussed
in there. ive done some basic 5 minutes tests on.
Once we have agreement i will pass it on to Masahide-san to do more
thorough testing.
Look at the XXX comments in the patch.

A couple of interesting things:

1) Weve discussed this before Herbert and i think you misspoke that
pfkey delivers to all listerners.

pfkey Add/del/upd now really do tell all processes about what happened.
Before pfkey would skip the originating process. So far this doesnt seem
to be an issue in the basic testing.

2) I ended adding a policy_notify to the pfkey manager to make the code
generic. Interesting thing is i dont think pfkey knows what to do with 
policy expiration or i am misreading the code.
I dont see any message type for policy expiration as i do for sa
expiration. Ive put some hooks and a little noise. I could remove the
printks - for now they are just place holders.

cheers,
jamal

[-- Attachment #2: ipsec-event-take2 --]
[-- Type: text/plain, Size: 29278 bytes --]

--- a/include/net/xfrm.h	2005-03-25 22:28:26.000000000 -0500
+++ b/include/net/xfrm.h	2005-04-02 11:59:17.000000000 -0500
@@ -157,6 +157,28 @@
 	XFRM_STATE_DEAD
 };
 
+/* events that could be sent by kernel */
+enum {
+	XFRM_SAP_INVALID,
+	XFRM_SAP_EXPIRED,
+	XFRM_SAP_ADDED,
+	XFRM_SAP_UPDATED,
+	XFRM_SAP_DELETED,
+	XFRM_SAP_FLUSHED,
+	__XFRM_SAP_MAX
+};
+#define XFRM_SAP_MAX (__XFRM_SAP_MAX - 1)
+
+/* callback structure passed from either netlink or pfkey */
+struct km_event
+{
+	u32	data; 
+	u32	seq; 
+	u32	pid; 
+	u32	event; 
+};
+
+
 struct xfrm_type;
 struct xfrm_dst;
 struct xfrm_policy_afinfo {
@@ -178,6 +200,9 @@
 
 extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
 extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo);
+extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c);
+extern void km_state_notify(struct xfrm_state *x, struct km_event *c);
+
 
 #define XFRM_ACQ_EXPIRES	30
 
@@ -283,17 +308,17 @@
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
 };
 
-#define XFRM_KM_TIMEOUT		30
 
+#define XFRM_KM_TIMEOUT		30
 struct xfrm_mgr
 {
 	struct list_head	list;
 	char			*id;
-	int			(*notify)(struct xfrm_state *x, int event);
+	int			(*notify)(struct xfrm_state *x, struct km_event *c);
 	int			(*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir);
 	struct xfrm_policy	*(*compile_policy)(u16 family, int opt, u8 *data, int len, int *dir);
 	int			(*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport);
-	int			(*notify_policy)(struct xfrm_policy *x, int dir, int event);
+	int			(*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c);
 };
 
 extern int xfrm_register_km(struct xfrm_mgr *km);
@@ -802,7 +827,7 @@
 extern int xfrm_state_update(struct xfrm_state *x);
 extern struct xfrm_state *xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family);
 extern struct xfrm_state *xfrm_find_acq_byseq(u32 seq);
-extern void xfrm_state_delete(struct xfrm_state *x);
+extern int xfrm_state_delete(struct xfrm_state *x);
 extern void xfrm_state_flush(u8 proto);
 extern int xfrm_replay_check(struct xfrm_state *x, u32 seq);
 extern void xfrm_replay_advance(struct xfrm_state *x, u32 seq);
--- a/include/linux/xfrm.h	2005-03-25 22:28:39.000000000 -0500
+++ b/include/linux/xfrm.h	2005-04-02 09:53:03.000000000 -0500
@@ -254,5 +254,7 @@
 
 #define XFRMGRP_ACQUIRE		1
 #define XFRMGRP_EXPIRE		2
+#define XFRMGRP_SA		4
+#define XFRMGRP_POLICY		8
 
 #endif /* _LINUX_XFRM_H */
--- a/net/xfrm/xfrm_state.c	2005-03-25 22:28:25.000000000 -0500
+++ b/net/xfrm/xfrm_state.c	2005-04-02 12:15:37.000000000 -0500
@@ -48,7 +48,7 @@
 static struct list_head xfrm_state_gc_list = LIST_HEAD_INIT(xfrm_state_gc_list);
 static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 
-static void __xfrm_state_delete(struct xfrm_state *x);
+static 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);
@@ -208,8 +208,10 @@
 }
 EXPORT_SYMBOL(__xfrm_state_destroy);
 
-static void __xfrm_state_delete(struct xfrm_state *x)
+static int __xfrm_state_delete(struct xfrm_state *x)
 {
+	int err = -ESRCH;
+
 	if (x->km.state != XFRM_STATE_DEAD) {
 		x->km.state = XFRM_STATE_DEAD;
 		spin_lock(&xfrm_state_lock);
@@ -236,14 +238,47 @@
 		 * is what we are dropping here.
 		 */
 		atomic_dec(&x->refcnt);
+		err = 0;
 	}
+
+	return err;
 }
 
-void xfrm_state_delete(struct xfrm_state *x)
+static DEFINE_RWLOCK(xfrm_km_lock);
+static struct list_head xfrm_km_list = LIST_HEAD_INIT(xfrm_km_list);
+
+void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
 {
+	struct xfrm_mgr *km;
+
+	read_lock(&xfrm_km_lock);
+	list_for_each_entry(km, &xfrm_km_list, list)
+		if (km->notify_policy)
+			km->notify_policy(xp, dir, c);
+	read_unlock(&xfrm_km_lock);
+}
+
+void km_state_notify(struct xfrm_state *x, struct km_event *c)
+{
+	struct xfrm_mgr *km;
+	read_lock(&xfrm_km_lock);
+	list_for_each_entry(km, &xfrm_km_list, list)
+		km->notify(x, c);
+	read_unlock(&xfrm_km_lock);
+}
+
+EXPORT_SYMBOL(km_policy_notify);
+EXPORT_SYMBOL(km_state_notify);
+
+int xfrm_state_delete(struct xfrm_state *x)
+{
+	int err;
+
 	spin_lock_bh(&x->lock);
-	__xfrm_state_delete(x);
+	err = __xfrm_state_delete(x);
 	spin_unlock_bh(&x->lock);
+
+	return err;
 }
 EXPORT_SYMBOL(xfrm_state_delete);
 
@@ -402,6 +437,7 @@
 
 static struct xfrm_state *__xfrm_find_acq_byseq(u32 seq);
 
+
 int xfrm_state_add(struct xfrm_state *x)
 {
 	struct xfrm_state_afinfo *afinfo;
@@ -764,37 +800,45 @@
 }
 EXPORT_SYMBOL(xfrm_replay_advance);
 
-static struct list_head xfrm_km_list = LIST_HEAD_INIT(xfrm_km_list);
-static DEFINE_RWLOCK(xfrm_km_lock);
 
 static void km_state_expired(struct xfrm_state *x, int hard)
 {
-	struct xfrm_mgr *km;
+	struct km_event c;
 
 	if (hard)
 		x->km.state = XFRM_STATE_EXPIRED;
 	else
 		x->km.dying = 1;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list)
-		km->notify(x, hard);
-	read_unlock(&xfrm_km_lock);
+	/* XXX: Do we wanna do this right at the top??
+	 * if the state is dead we dont want to announce 
+	 * the expire - a delete may already have announced
+	 * it 
+	*/
+	if (x->km.state == XFRM_STATE_DEAD)
+		return;
+	c.data = hard;
+	c.event = XFRM_SAP_EXPIRED;
+	km_state_notify(x, &c);
 
 	if (hard)
 		wake_up(&km_waitq);
 }
 
+/*
+ * 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 err = -EINVAL;
+	int err = -EINVAL, acqret;
 	struct xfrm_mgr *km;
 
 	read_lock(&xfrm_km_lock);
 	list_for_each_entry(km, &xfrm_km_list, list) {
-		err = km->acquire(x, t, pol, XFRM_POLICY_OUT);
-		if (!err)
-			break;
+		acqret = km->acquire(x, t, pol, XFRM_POLICY_OUT);
+		if (!acqret)
+			err = acqret;
 	}
 	read_unlock(&xfrm_km_lock);
 	return err;
@@ -819,13 +863,20 @@
 
 void km_policy_expired(struct xfrm_policy *pol, int dir, int hard)
 {
-	struct xfrm_mgr *km;
+	struct km_event c;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list)
-		if (km->notify_policy)
-			km->notify_policy(pol, dir, hard);
-	read_unlock(&xfrm_km_lock);
+	/* XXX: Do we still wanna wakeup km_waitq?
+	 * if the policy is dead we dont want to announce 
+	 * the expire - a delete may already have announced
+	 * it 
+	*/
+	if (pol->dead)
+		return;
+
+	c.data = hard;
+	c.data = hard;
+	c.event = XFRM_SAP_EXPIRED;
+	km_policy_notify(pol, dir, &c);
 
 	if (hard)
 		wake_up(&km_waitq);
--- a/net/xfrm/xfrm_policy.c	2005-03-25 22:28:21.000000000 -0500
+++ b/net/xfrm/xfrm_policy.c	2005-04-02 12:16:30.000000000 -0500
@@ -298,7 +298,7 @@
  * entry dead. The rule must be unlinked from lists to the moment.
  */
 
-static void xfrm_policy_kill(struct xfrm_policy *policy)
+static void xfrm_policy_kill(struct xfrm_policy *policy, int dir)
 {
 	write_lock_bh(&policy->lock);
 	if (policy->dead)
@@ -378,7 +378,7 @@
 	write_unlock_bh(&xfrm_policy_lock);
 
 	if (delpol) {
-		xfrm_policy_kill(delpol);
+		xfrm_policy_kill(delpol, dir);
 	}
 	return 0;
 }
@@ -402,7 +402,7 @@
 
 	if (pol && delete) {
 		atomic_inc(&flow_cache_genid);
-		xfrm_policy_kill(pol);
+		xfrm_policy_kill(pol, dir);
 	}
 	return pol;
 }
@@ -425,7 +425,7 @@
 
 	if (pol && delete) {
 		atomic_inc(&flow_cache_genid);
-		xfrm_policy_kill(pol);
+		xfrm_policy_kill(pol, dir);
 	}
 	return pol;
 }
@@ -442,7 +442,7 @@
 			xfrm_policy_list[dir] = xp->next;
 			write_unlock_bh(&xfrm_policy_lock);
 
-			xfrm_policy_kill(xp);
+			xfrm_policy_kill(xp, dir);
 
 			write_lock_bh(&xfrm_policy_lock);
 		}
@@ -558,7 +558,7 @@
 	if (pol) {
 		if (dir < XFRM_POLICY_MAX)
 			atomic_inc(&flow_cache_genid);
-		xfrm_policy_kill(pol);
+		xfrm_policy_kill(pol, dir);
 	}
 }
 
@@ -579,7 +579,7 @@
 	write_unlock_bh(&xfrm_policy_lock);
 
 	if (old_pol) {
-		xfrm_policy_kill(old_pol);
+		xfrm_policy_kill(old_pol, dir);
 	}
 	return 0;
 }
--- a/net/xfrm/xfrm_user.c	2005-03-25 22:28:22.000000000 -0500
+++ b/net/xfrm/xfrm_user.c	2005-04-02 12:21:32.000000000 -0500
@@ -268,6 +268,7 @@
 	struct xfrm_usersa_info *p = NLMSG_DATA(nlh);
 	struct xfrm_state *x;
 	int err;
+	struct km_event c;
 
 	err = verify_newsa_info(p, (struct rtattr **) xfrma);
 	if (err)
@@ -285,14 +286,26 @@
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
 		xfrm_state_put(x);
+		return err;
 	}
 
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+	if (nlh->nlmsg_type == XFRM_MSG_NEWSA)
+		c.event = XFRM_SAP_ADDED;
+	else
+		c.event = XFRM_SAP_UPDATED;
+
+	km_state_notify(x, &c);
+
 	return err;
 }
 
 static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 {
 	struct xfrm_state *x;
+	int err;
+	struct km_event c;
 	struct xfrm_usersa_id *p = NLMSG_DATA(nlh);
 
 	x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family);
@@ -304,10 +317,20 @@
 		return -EPERM;
 	}
 
-	xfrm_state_delete(x);
+	err = xfrm_state_delete(x);
+	if (err < 0) {
+		x->km.state = XFRM_STATE_DEAD;
+		xfrm_state_put(x);
+		return err;
+	}
+
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+	c.event = XFRM_SAP_DELETED;
+	km_state_notify(x, &c);
 	xfrm_state_put(x);
 
-	return 0;
+	return err;
 }
 
 static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
@@ -672,6 +695,7 @@
 {
 	struct xfrm_userpolicy_info *p = NLMSG_DATA(nlh);
 	struct xfrm_policy *xp;
+	struct km_event c;
 	int err;
 	int excl;
 
@@ -683,6 +707,10 @@
 	if (!xp)
 		return err;
 
+	/* shouldnt excl be based on nlh flags?? 
+	 * Aha! this is anti-netlink really i.e  more pfkey derived
+	 * in netlink excl is a flag and you wouldnt need
+	 * a type XFRM_MSG_UPDPOLICY - JHS */
 	excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY;
 	err = xfrm_policy_insert(p->dir, xp, excl);
 	if (err) {
@@ -690,6 +718,16 @@
 		return err;
 	}
 
+
+	if (!excl)
+		c.event = XFRM_SAP_UPDATED;
+	else
+		c.event = XFRM_SAP_ADDED;
+
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+	km_policy_notify(xp, p->dir, &c);
+
 	xfrm_pol_put(xp);
 
 	return 0;
@@ -807,8 +845,10 @@
 	struct xfrm_policy *xp;
 	struct xfrm_userpolicy_id *p;
 	int err;
+	struct km_event c;
 	int delete;
 
+
 	p = NLMSG_DATA(nlh);
 	delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY;
 
@@ -834,6 +874,11 @@
 					      NETLINK_CB(skb).pid,
 					      MSG_DONTWAIT);
 		}
+	} else {
+		c.event = XFRM_SAP_DELETED;
+		c.seq = nlh->nlmsg_seq;
+		c.pid = nlh->nlmsg_pid;
+		km_policy_notify(xp, p->dir, &c);
 	}
 
 	xfrm_pol_put(xp);
@@ -843,15 +888,28 @@
 
 static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 {
+	struct km_event c;
 	struct xfrm_usersa_flush *p = NLMSG_DATA(nlh);
 
 	xfrm_state_flush(p->proto);
+	c.data = p->proto;
+	c.event = XFRM_SAP_FLUSHED;
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+	km_state_notify(NULL, &c);
+
 	return 0;
 }
 
 static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 {
+	struct km_event c;
+
 	xfrm_policy_flush();
+	c.event = XFRM_SAP_FLUSHED;
+	c.seq = nlh->nlmsg_seq;
+	c.pid = nlh->nlmsg_pid;
+	km_policy_notify(NULL, 0, &c);
 	return 0;
 }
 
@@ -1053,10 +1111,11 @@
 	return -1;
 }
 
-static int xfrm_send_state_notify(struct xfrm_state *x, int hard)
+static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c)
 {
 	struct sk_buff *skb;
-
+	int hard = c ->data;
+	/* fix to do alloc using NLM macros */
 	skb = alloc_skb(sizeof(struct xfrm_user_expire) + 16, GFP_ATOMIC);
 	if (skb == NULL)
 		return -ENOMEM;
@@ -1069,6 +1128,94 @@
 	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC);
 }
 
+static int xfrm_notify_sa_flush(struct km_event *c)
+{
+	struct xfrm_usersa_flush *p;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	unsigned char *b;
+	int len = NLMSG_LENGTH(sizeof(struct xfrm_usersa_flush));
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+	b = skb->tail;
+
+	nlh = NLMSG_PUT(skb, c->pid,  c->seq,
+			XFRM_MSG_FLUSHSA, sizeof(*p));
+	nlh->nlmsg_flags = 0;
+
+	p = NLMSG_DATA(nlh);
+	p->proto = c->data;
+
+	nlh->nlmsg_len = skb->tail - b;
+
+	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC);
+
+nlmsg_failure:
+	kfree_skb(skb);
+	return -1;
+}
+
+static int xfrm_notify_sa( struct xfrm_state *x, struct km_event *c)
+{
+	struct xfrm_usersa_info *p;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	u32 nlt;
+	unsigned char *b;
+	int len = NLMSG_LENGTH(sizeof(struct xfrm_usersa_info));
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+	b = skb->tail;
+
+	if (c->event == XFRM_SAP_ADDED)
+		nlt = XFRM_MSG_NEWSA;
+	else if (c->event == XFRM_SAP_UPDATED)
+		nlt = XFRM_MSG_UPDSA;
+	else if (c->event == XFRM_SAP_DELETED)
+		nlt = XFRM_MSG_DELSA;
+	else
+		goto nlmsg_failure;
+
+	nlh = NLMSG_PUT(skb, c->pid, c->seq, nlt, sizeof(*p));
+	nlh->nlmsg_flags = 0;
+
+	p = NLMSG_DATA(nlh);
+	copy_to_user_state(x, p);
+
+	nlh->nlmsg_len = skb->tail - b;
+
+	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC);
+
+nlmsg_failure:
+	kfree_skb(skb);
+	return -1;
+}
+
+static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c)
+{
+
+	switch (c->event) {
+	case XFRM_SAP_EXPIRED:
+		return xfrm_exp_state_notify(x, c);
+	case XFRM_SAP_DELETED:
+	case XFRM_SAP_UPDATED:
+	case XFRM_SAP_ADDED:
+		return xfrm_notify_sa(x, c);
+	case XFRM_SAP_FLUSHED:
+		return xfrm_notify_sa_flush(c);
+	default:
+		 printk("pfkey: Unknown SA event %d\n",c->event);
+		 break;
+	}
+
+	return 0;
+
+}
+
 static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
 			 struct xfrm_tmpl *xt, struct xfrm_policy *xp,
 			 int dir)
@@ -1202,7 +1349,8 @@
 	return -1;
 }
 
-static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard)
+
+static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
 {
 	struct sk_buff *skb;
 	size_t len;
@@ -1213,7 +1361,7 @@
 	if (skb == NULL)
 		return -ENOMEM;
 
-	if (build_polexpire(skb, xp, dir, hard) < 0)
+	if (build_polexpire(skb, xp, dir, c->data) < 0)
 		BUG();
 
 	NETLINK_CB(skb).dst_groups = XFRMGRP_EXPIRE;
@@ -1221,6 +1369,90 @@
 	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC);
 }
 
+static int xfrm_notify_policy( struct xfrm_policy *xp, int dir, struct km_event *c)
+{
+	struct xfrm_userpolicy_info *p;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	u32 nlt = 0 ;
+	unsigned char *b;
+	int len = NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_info));
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+	b = skb->tail;
+
+	if (c->event == XFRM_SAP_ADDED)
+		nlt = XFRM_MSG_NEWPOLICY;
+	else if (c->event == XFRM_SAP_UPDATED)
+		nlt = XFRM_MSG_UPDPOLICY;
+	else if (c->event == XFRM_SAP_DELETED)
+		nlt = XFRM_MSG_DELPOLICY;
+	else
+		goto nlmsg_failure;
+
+	nlh = NLMSG_PUT(skb, c->pid, c->seq, nlt, sizeof(*p));
+
+	p = NLMSG_DATA(nlh);
+
+	nlh->nlmsg_flags = 0;
+
+	copy_to_user_policy(xp, p, dir);
+
+	nlh->nlmsg_len = skb->tail - b;
+
+	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC);
+
+nlmsg_failure:
+	kfree_skb(skb);
+	return -1;
+}
+
+static int xfrm_notify_policy_flush(struct km_event *c)
+{
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	unsigned char *b;
+	int len = NLMSG_LENGTH(0);
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (skb == NULL)
+		return -ENOMEM;
+	b = skb->tail;
+
+
+	nlh = NLMSG_PUT(skb, c->pid, c->seq, XFRM_MSG_FLUSHPOLICY, 0);
+
+	nlh->nlmsg_len = skb->tail - b;
+
+	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC);
+
+nlmsg_failure:
+	kfree_skb(skb);
+	return -1;
+}
+
+static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
+{
+
+	switch (c->event) {
+	case XFRM_SAP_ADDED:
+	case XFRM_SAP_UPDATED:
+	case XFRM_SAP_DELETED:
+		return xfrm_notify_policy(xp, dir, c);
+	case XFRM_SAP_FLUSHED:
+		return xfrm_notify_policy_flush(c);
+	case XFRM_SAP_EXPIRED:
+		return xfrm_exp_policy_notify(xp, dir, c);
+	default:
+		printk("Netlink Unknown Policy event %d\n",c->event);
+	}
+
+	return 0;
+
+}
+
 static struct xfrm_mgr netlink_mgr = {
 	.id		= "netlink",
 	.notify		= xfrm_send_state_notify,
--- a/net/key/af_key.c	2005-03-25 22:28:39.000000000 -0500
+++ b/net/key/af_key.c	2005-04-02 12:25:49.000000000 -0500
@@ -1240,13 +1240,85 @@
 	return 0;
 }
 
+static inline int event2poltype (int event)
+{
+	switch (event) {
+	case XFRM_SAP_DELETED:
+		return SADB_X_SPDDELETE;
+	case XFRM_SAP_ADDED:
+		return SADB_X_SPDADD;
+	case XFRM_SAP_UPDATED:
+		return SADB_X_SPDUPDATE;
+	case XFRM_SAP_EXPIRED:
+	//	return SADB_X_SPDEXPIRE;
+	default:
+		printk("pfkey: Unknown policy event %d\n",event);
+		break;
+	}
+
+	return 0;
+}
+
+static inline int event2keytype (int event)
+{
+	switch (event) {
+	case XFRM_SAP_DELETED:
+		return SADB_DELETE;
+	case XFRM_SAP_ADDED:
+		return SADB_ADD;
+	case XFRM_SAP_UPDATED:
+		return SADB_UPDATE;
+	case XFRM_SAP_EXPIRED:
+		return SADB_EXPIRE;
+	default:
+		printk("pfkey: Unknown SA event %d\n",event);
+		break;
+	}
+
+	return 0;
+}
+
+/* ADD/UPD/DEL */
+static int key_notify_sa(struct xfrm_state *x, struct km_event *c)
+{
+	struct sk_buff *skb;
+	struct sadb_msg *hdr;
+	int hsc = 3;
+
+	if (c->event == XFRM_SAP_DELETED)
+		hsc = 0;
+
+	if (c->event == XFRM_SAP_EXPIRED) {
+		if (c->data)
+			hsc = 2;
+		else
+			hsc = 1;
+	}
+
+	skb = pfkey_xfrm_state2msg(x, 0, hsc);
+
+	if (IS_ERR(skb))
+		return  PTR_ERR(skb);
+
+	hdr = (struct sadb_msg *) skb->data;
+	hdr->sadb_msg_version = PF_KEY_V2;
+	hdr->sadb_msg_type = event2keytype(c->event);
+	hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto);
+	hdr->sadb_msg_errno = 0;
+	hdr->sadb_msg_reserved = 0;
+	hdr->sadb_msg_seq = c->seq;
+	hdr->sadb_msg_pid = c->pid;
+
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL);
+
+	return 0;
+}
 
 static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
 {
-	struct sk_buff *out_skb;
-	struct sadb_msg *out_hdr;
 	struct xfrm_state *x;
 	int err;
+	struct km_event c;
 
 	xfrm_probe_algs();
 	
@@ -1256,7 +1328,7 @@
 
 	if (hdr->sadb_msg_type == SADB_ADD)
 		err = xfrm_state_add(x);
-	else
+	else 
 		err = xfrm_state_update(x);
 
 	if (err < 0) {
@@ -1265,27 +1337,22 @@
 		return err;
 	}
 
-	out_skb = pfkey_xfrm_state2msg(x, 0, 3);
-	if (IS_ERR(out_skb))
-		return  PTR_ERR(out_skb); /* XXX Should we return 0 here ? */
-
-	out_hdr = (struct sadb_msg *) out_skb->data;
-	out_hdr->sadb_msg_version = hdr->sadb_msg_version;
-	out_hdr->sadb_msg_type = hdr->sadb_msg_type;
-	out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto);
-	out_hdr->sadb_msg_errno = 0;
-	out_hdr->sadb_msg_reserved = 0;
-	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
-	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-
-	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk);
+	if (hdr->sadb_msg_type == SADB_ADD)
+		c.event = XFRM_SAP_ADDED;
+	else
+		c.event = XFRM_SAP_UPDATED;
+	c.seq = hdr->sadb_msg_seq;
+	c.pid = hdr->sadb_msg_pid;
+	km_state_notify(x, &c);
 
-	return 0;
+	return err;
 }
 
 static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
 {
 	struct xfrm_state *x;
+	struct km_event c;
+	int err;
 
 	if (!ext_hdrs[SADB_EXT_SA-1] ||
 	    !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1],
@@ -1301,13 +1368,20 @@
 		return -EPERM;
 	}
 	
-	xfrm_state_delete(x);
-	xfrm_state_put(x);
+	err = xfrm_state_delete(x);
+	if (err < 0) {
+		x->km.state = XFRM_STATE_DEAD;
+		xfrm_state_put(x);
+		return err;
+	}
 
-	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, 
-			BROADCAST_ALL, sk);
+	c.seq = hdr->sadb_msg_seq;
+	c.pid = hdr->sadb_msg_pid;
+	c.event = XFRM_SAP_DELETED;
+	km_state_notify(x, &c);
+	xfrm_state_put(x);
 
-	return 0;
+	return err;
 }
 
 static int pfkey_get(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
@@ -1445,28 +1519,42 @@
 	return 0;
 }
 
+static int key_notify_sa_flush(struct km_event *c)
+{
+	struct sk_buff *skb;
+	struct sadb_msg *hdr;
+
+	skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+	hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg));
+	// XXX:do we have to pass proto as well?
+	hdr->sadb_msg_seq = c->seq;
+	hdr->sadb_msg_pid = c->pid;
+	hdr->sadb_msg_version = PF_KEY_V2;
+	hdr->sadb_msg_errno = (uint8_t) 0;
+	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
+
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL);
+
+	return 0;
+}
+
 static int pfkey_flush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
 {
 	unsigned proto;
-	struct sk_buff *skb_out;
-	struct sadb_msg *hdr_out;
+	struct km_event c;
 
 	proto = pfkey_satype2proto(hdr->sadb_msg_satype);
 	if (proto == 0)
 		return -EINVAL;
 
-	skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL);
-	if (!skb_out)
-		return -ENOBUFS;
-
 	xfrm_state_flush(proto);
-
-	hdr_out = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg));
-	pfkey_hdr_dup(hdr_out, hdr);
-	hdr_out->sadb_msg_errno = (uint8_t) 0;
-	hdr_out->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
-
-	pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL);
+	c.data = proto;
+	c.seq = hdr->sadb_msg_seq;
+	c.pid = hdr->sadb_msg_pid;
+	c.event = XFRM_SAP_FLUSHED;
+	km_state_notify(NULL, &c);
 
 	return 0;
 }
@@ -1859,6 +1947,31 @@
 	hdr->sadb_msg_reserved = atomic_read(&xp->refcnt);
 }
 
+static int key_notify_policy( struct xfrm_policy *xp, int dir, struct km_event *c)
+{
+	struct sk_buff *out_skb;
+	struct sadb_msg *out_hdr;
+	int err;
+
+	out_skb = pfkey_xfrm_policy2msg_prep(xp);
+	if (IS_ERR(out_skb)) {
+		err =  PTR_ERR(out_skb);
+		goto out;
+	}
+	pfkey_xfrm_policy2msg(out_skb, xp, dir);
+
+	out_hdr = (struct sadb_msg *) out_skb->data;
+	out_hdr->sadb_msg_version =  PF_KEY_V2;
+	out_hdr->sadb_msg_type = event2poltype(c->event);
+	out_hdr->sadb_msg_errno = 0;
+	out_hdr->sadb_msg_seq = c->seq;
+	out_hdr->sadb_msg_pid = c->pid;
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL);
+out:
+	return 0;
+
+}
+
 static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
 {
 	int err;
@@ -1866,8 +1979,7 @@
 	struct sadb_address *sa;
 	struct sadb_x_policy *pol;
 	struct xfrm_policy *xp;
-	struct sk_buff *out_skb;
-	struct sadb_msg *out_hdr;
+	struct km_event c;
 
 	if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1],
 				     ext_hdrs[SADB_EXT_ADDRESS_DST-1]) ||
@@ -1935,31 +2047,25 @@
 	    (err = parse_ipsecrequests(xp, pol)) < 0)
 		goto out;
 
-	out_skb = pfkey_xfrm_policy2msg_prep(xp);
-	if (IS_ERR(out_skb)) {
-		err =  PTR_ERR(out_skb);
-		goto out;
-	}
 
 	err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp,
 				 hdr->sadb_msg_type != SADB_X_SPDUPDATE);
+
 	if (err) {
-		kfree_skb(out_skb);
-		goto out;
+		kfree(xp);
+		return err;
 	}
 
-	pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1);
+	if (hdr->sadb_msg_type == SADB_X_SPDUPDATE) 
+		c.event = XFRM_SAP_UPDATED;
+	else 
+		c.event = XFRM_SAP_ADDED;
 
-	xfrm_pol_put(xp);
+	c.seq = hdr->sadb_msg_seq;
+	c.pid = hdr->sadb_msg_pid;
 
-	out_hdr = (struct sadb_msg *) out_skb->data;
-	out_hdr->sadb_msg_version = hdr->sadb_msg_version;
-	out_hdr->sadb_msg_type = hdr->sadb_msg_type;
-	out_hdr->sadb_msg_satype = 0;
-	out_hdr->sadb_msg_errno = 0;
-	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
-	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk);
+	km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c);
+	xfrm_pol_put(xp);
 	return 0;
 
 out:
@@ -1973,9 +2079,8 @@
 	struct sadb_address *sa;
 	struct sadb_x_policy *pol;
 	struct xfrm_policy *xp;
-	struct sk_buff *out_skb;
-	struct sadb_msg *out_hdr;
 	struct xfrm_selector sel;
+	struct km_event c;
 
 	if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1],
 				     ext_hdrs[SADB_EXT_ADDRESS_DST-1]) ||
@@ -2010,24 +2115,11 @@
 
 	err = 0;
 
-	out_skb = pfkey_xfrm_policy2msg_prep(xp);
-	if (IS_ERR(out_skb)) {
-		err =  PTR_ERR(out_skb);
-		goto out;
-	}
-	pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1);
-
-	out_hdr = (struct sadb_msg *) out_skb->data;
-	out_hdr->sadb_msg_version = hdr->sadb_msg_version;
-	out_hdr->sadb_msg_type = SADB_X_SPDDELETE;
-	out_hdr->sadb_msg_satype = 0;
-	out_hdr->sadb_msg_errno = 0;
-	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
-	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk);
-	err = 0;
+	c.seq = hdr->sadb_msg_seq;
+	c.pid = hdr->sadb_msg_pid;
+	c.event = XFRM_SAP_DELETED;
+	km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c);
 
-out:
 	xfrm_pol_put(xp);
 	return err;
 }
@@ -2037,8 +2129,7 @@
 	int err;
 	struct sadb_x_policy *pol;
 	struct xfrm_policy *xp;
-	struct sk_buff *out_skb;
-	struct sadb_msg *out_hdr;
+	struct km_event c;
 
 	if ((pol = ext_hdrs[SADB_X_EXT_POLICY-1]) == NULL)
 		return -EINVAL;
@@ -2050,24 +2141,19 @@
 
 	err = 0;
 
-	out_skb = pfkey_xfrm_policy2msg_prep(xp);
-	if (IS_ERR(out_skb)) {
-		err =  PTR_ERR(out_skb);
-		goto out;
+	/* 
+	 * XXX: previous get was doing a broadcast-all _always_
+	 * which didnt seem right for non-deletion case - JHS
+	 * This is like the way netlink behaves ..
+	 * Shall i restore original behavior?
+	*/
+	if (hdr->sadb_msg_type == SADB_X_SPDDELETE2) {
+		c.seq = hdr->sadb_msg_seq;
+		c.pid = hdr->sadb_msg_pid;
+		c.event = XFRM_SAP_DELETED;
+		km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c);
 	}
-	pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1);
-
-	out_hdr = (struct sadb_msg *) out_skb->data;
-	out_hdr->sadb_msg_version = hdr->sadb_msg_version;
-	out_hdr->sadb_msg_type = hdr->sadb_msg_type;
-	out_hdr->sadb_msg_satype = 0;
-	out_hdr->sadb_msg_errno = 0;
-	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
-	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk);
-	err = 0;
 
-out:
 	xfrm_pol_put(xp);
 	return err;
 }
@@ -2102,22 +2188,33 @@
 	return xfrm_policy_walk(dump_sp, &data);
 }
 
-static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
+static int key_notify_policy_flush(struct km_event *c)
 {
 	struct sk_buff *skb_out;
-	struct sadb_msg *hdr_out;
-
-	skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL);
+	struct sadb_msg *hdr;
+	skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC);
 	if (!skb_out)
 		return -ENOBUFS;
+	hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg));
+	hdr->sadb_msg_seq = c->seq;
+	hdr->sadb_msg_pid = c->pid;
+	hdr->sadb_msg_version = PF_KEY_V2;
+	hdr->sadb_msg_errno = (uint8_t) 0;
+	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
+	pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL);
+	return 0;
 
-	xfrm_policy_flush();
+}
 
-	hdr_out = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg));
-	pfkey_hdr_dup(hdr_out, hdr);
-	hdr_out->sadb_msg_errno = (uint8_t) 0;
-	hdr_out->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
-	pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL);
+static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
+{
+	struct km_event c;
+
+	xfrm_policy_flush();
+	c.event = XFRM_SAP_FLUSHED;
+	c.pid = hdr->sadb_msg_pid;
+	c.seq = hdr->sadb_msg_seq;
+	km_policy_notify(NULL, 0, &c);
 
 	return 0;
 }
@@ -2317,11 +2414,25 @@
 	}
 }
 
-static int pfkey_send_notify(struct xfrm_state *x, int hard)
+/* XXX: Noisy for now */
+static int key_notify_policy_expire(struct xfrm_policy *xp, struct km_event *c)
+{
+	printk("pfkey doesnt deal with expired policies ..\n");
+	return 0;
+}
+
+static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c)
 {
 	struct sk_buff *out_skb;
 	struct sadb_msg *out_hdr;
-	int hsc = (hard ? 2 : 1);
+	int hard;
+	int hsc;
+
+	hard = c->data;
+	if (hard)
+		hsc = 2;
+	else
+		hsc = 1;
 
 	out_skb = pfkey_xfrm_state2msg(x, 0, hsc);
 	if (IS_ERR(out_skb))
@@ -2340,6 +2451,43 @@
 	return 0;
 }
 
+static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c)
+{
+	switch (c->event) {
+	case XFRM_SAP_EXPIRED:
+		return key_notify_sa_expire(x, c);
+	case XFRM_SAP_DELETED:
+	case XFRM_SAP_ADDED:
+	case XFRM_SAP_UPDATED:
+		return key_notify_sa(x, c);
+	case XFRM_SAP_FLUSHED:
+		return key_notify_sa_flush(c);
+	default:
+		printk("pfkey: Unknown SA event %d\n",c->event);
+		break;
+	}
+
+	return 0;
+}
+
+static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
+{
+	switch (c->event) {
+	case XFRM_SAP_EXPIRED:
+		return key_notify_policy_expire(xp, c);
+	case XFRM_SAP_DELETED:
+	case XFRM_SAP_ADDED:
+	case XFRM_SAP_UPDATED:
+		return key_notify_policy(xp, dir, c);
+	case XFRM_SAP_FLUSHED:
+		return key_notify_policy_flush(c);
+	default:
+		printk("pfkey: Unknown policy event %d\n",c->event);
+		break;
+	}
+
+	return 0;
+}
 static u32 get_acqseq(void)
 {
 	u32 res;
@@ -2856,6 +3004,7 @@
 	.acquire	= pfkey_send_acquire,
 	.compile_policy	= pfkey_compile_policy,
 	.new_mapping	= pfkey_send_new_mapping,
+	.notify_policy	= pfkey_send_policy_notify,
 };
 
 static void __exit ipsec_pfkey_exit(void)