[IPSEC] Add complete xfrm event notification

Heres the final patch.
What this patch provides

- netlink xfrm events
- ability to have events generated by netlink propagated to pfkey
  and vice versa.
- fixes the acquire lets-be-happy-with-one-success issue

Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

5 files changed, 616 insertions, 118 deletions

diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h
index fd2ef742a9fd..03bc600516ea 100644
--- a/include/linux/xfrm.h
+++ b/include/linux/xfrm.h
@@ -257,5 +257,7 @@ struct xfrm_usersa_flush {
 
 #define XFRMGRP_ACQUIRE		1
 #define XFRMGRP_EXPIRE		2
+#define XFRMGRP_SA		4
+#define XFRMGRP_POLICY		8
 
 #endif /* _LINUX_XFRM_H */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index d675836ba6c3..a159655ebede 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -158,6 +158,27 @@ enum {
 	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 {
@@ -179,6 +200,8 @@ struct xfrm_policy_afinfo {
 
 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
 
@@ -290,11 +313,11 @@ 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);
@@ -817,7 +840,7 @@ extern int xfrm_state_add(struct xfrm_state *x);
 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);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index ce980aa94ed8..d086c117f5f0 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1240,13 +1240,85 @@ static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, struct sadb_msg *
 	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();
 	
@@ -1254,6 +1326,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr,
 	if (IS_ERR(x))
 		return PTR_ERR(x);
 
+	xfrm_state_hold(x);
 	if (hdr->sadb_msg_type == SADB_ADD)
 		err = xfrm_state_add(x);
 	else
@@ -1265,27 +1338,23 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr,
 		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);
+	xfrm_state_put(x);
 
-	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 +1370,19 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 		return -EPERM;
 	}
 	
-	xfrm_state_delete(x);
-	xfrm_state_put(x);
+	err = xfrm_state_delete(x);
+	if (err < 0) {
+		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 +1520,42 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, struct sadb_msg
 	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_ATOMIC);
+	if (!skb)
+		return -ENOBUFS;
+	hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg));
+	hdr->sadb_msg_satype = pfkey_proto2satype(c->data);
+	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_ATOMIC, 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 +1948,35 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i
 	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;
+
+	if (c->data && c->event == XFRM_SAP_DELETED)
+		out_hdr->sadb_msg_type = SADB_X_SPDDELETE2;
+	else
+		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 +1984,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 	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 +2052,23 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 	    (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 +2082,8 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg
 	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]) ||
@@ -2010,25 +2118,40 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg
 
 	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);
+
+	xfrm_pol_put(xp);
+	return err;
+}
+
+static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, struct sadb_msg *hdr, int dir)
+{
+	int err;
+	struct sk_buff *out_skb;
+	struct sadb_msg *out_hdr;
+	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);
+	pfkey_xfrm_policy2msg(out_skb, xp, dir);
 
 	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_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);
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk);
 	err = 0;
 
 out:
-	xfrm_pol_put(xp);
 	return err;
 }
 
@@ -2037,8 +2160,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 	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 +2172,16 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h
 
 	err = 0;
 
-	out_skb = pfkey_xfrm_policy2msg_prep(xp);
-	if (IS_ERR(out_skb)) {
-		err =  PTR_ERR(out_skb);
-		goto out;
+	c.seq = hdr->sadb_msg_seq;
+	c.pid = hdr->sadb_msg_pid;
+	if (hdr->sadb_msg_type == SADB_X_SPDDELETE2) {
+		c.data = 1; // to signal pfkey of SADB_X_SPDDELETE2
+		c.event = XFRM_SAP_DELETED;
+		km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c);
+	} else {
+		err = key_pol_get_resp(sk, xp, hdr, pol->sadb_x_policy_dir-1);
 	}
-	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 +2216,34 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, struct sadb_msg *
 	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;
+	struct sadb_msg *hdr;
 
-	skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL);
+	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_ATOMIC, BROADCAST_ALL, NULL);
+	return 0;
 
-	xfrm_policy_flush();
+}
+
+static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)
+{
+	struct km_event c;
 
-	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);
+	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 +2443,23 @@ static void dump_esp_combs(struct sk_buff *skb, struct xfrm_tmpl *t)
 	}
 }
 
-static int pfkey_send_notify(struct xfrm_state *x, int hard)
+static int key_notify_policy_expire(struct xfrm_policy *xp, struct km_event *c)
+{
+	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 +2478,44 @@ static int pfkey_send_notify(struct xfrm_state *x, int hard)
 	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 +3032,7 @@ static struct xfrm_mgr pfkeyv2_mgr =
 	.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)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index d11747c2a763..918a94c552a5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -50,7 +50,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 
 static int xfrm_state_gc_flush_bundles;
 
-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);
@@ -215,8 +215,10 @@ void __xfrm_state_destroy(struct xfrm_state *x)
 }
 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);
@@ -245,14 +247,21 @@ static void __xfrm_state_delete(struct xfrm_state *x)
 		 * is what we are dropping here.
 		 */
 		atomic_dec(&x->refcnt);
+		err = 0;
 	}
+
+	return err;
 }
 
-void xfrm_state_delete(struct xfrm_state *x)
+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);
 
@@ -796,34 +805,60 @@ 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)
+void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c)
 {
 	struct xfrm_mgr *km;
 
-	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)
+		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, hard);
+		if (km->notify)
+			km->notify(x, c);
 	read_unlock(&xfrm_km_lock);
+}
+
+EXPORT_SYMBOL(km_policy_notify);
+EXPORT_SYMBOL(km_state_notify);
+
+static void km_state_expired(struct xfrm_state *x, int hard)
+{
+	struct km_event c;
+
+	if (hard)
+		x->km.state = XFRM_STATE_EXPIRED;
+	else
+		x->km.dying = 1;
+	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;
@@ -848,13 +883,12 @@ EXPORT_SYMBOL(km_new_mapping);
 
 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);
+	c.data = hard;
+	c.data = hard;
+	c.event = XFRM_SAP_EXPIRED;
+	km_policy_notify(pol, dir, &c);
 
 	if (hard)
 		wake_up(&km_waitq);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 97509011c274..bd8e6882c083 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -277,6 +277,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 	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)
@@ -286,6 +287,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 	if (!x)
 		return err;
 
+	xfrm_state_hold(x);
 	if (nlh->nlmsg_type == XFRM_MSG_NEWSA)
 		err = xfrm_state_add(x);
 	else
@@ -294,14 +296,27 @@ 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);
+		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);
+	xfrm_state_put(x);
+
 	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);
@@ -313,10 +328,19 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma)
 		return -EPERM;
 	}
 
-	xfrm_state_delete(x);
+	err = xfrm_state_delete(x);
+	if (err < 0) {
+		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)
@@ -681,6 +705,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr
 {
 	struct xfrm_userpolicy_info *p = NLMSG_DATA(nlh);
 	struct xfrm_policy *xp;
+	struct km_event c;
 	int err;
 	int excl;
 
@@ -692,6 +717,10 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr
 	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) {
@@ -699,6 +728,15 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr
 		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;
@@ -816,6 +854,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr
 	struct xfrm_policy *xp;
 	struct xfrm_userpolicy_id *p;
 	int err;
+	struct km_event c;
 	int delete;
 
 	p = NLMSG_DATA(nlh);
@@ -843,6 +882,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr
 					      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);
@@ -852,15 +896,28 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr
 
 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;
 }
 
@@ -1069,10 +1126,12 @@ nlmsg_failure:
 	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;
@@ -1085,6 +1144,122 @@ static int xfrm_send_state_notify(struct xfrm_state *x, int hard)
 	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 inline xfrm_sa_len(struct xfrm_state *x)
+{
+	int l = NLMSG_LENGTH(sizeof(struct xfrm_usersa_info));
+	if (x->aalg)
+		l += RTA_SPACE(sizeof(*x->aalg) + (x->aalg->alg_key_len+7)/8);
+	if (x->ealg)
+		l += RTA_SPACE(sizeof(*x->ealg) + (x->ealg->alg_key_len+7)/8);
+	if (x->calg)
+		l += RTA_SPACE(sizeof(*x->calg));
+	if (x->encap)
+		l += RTA_SPACE(sizeof(*x->encap));
+
+	return l;
+}
+
+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 = xfrm_sa_len(x);
+
+	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);
+
+	if (x->aalg)
+		RTA_PUT(skb, XFRMA_ALG_AUTH,
+			sizeof(*(x->aalg))+(x->aalg->alg_key_len+7)/8, x->aalg);
+	if (x->ealg)
+		RTA_PUT(skb, XFRMA_ALG_CRYPT,
+			sizeof(*(x->ealg))+(x->ealg->alg_key_len+7)/8, x->ealg);
+	if (x->calg)
+		RTA_PUT(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg);
+
+	if (x->encap)
+		RTA_PUT(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap);
+
+	nlh->nlmsg_len = skb->tail - b;
+
+	return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC);
+
+nlmsg_failure:
+rtattr_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("xfrm_user: 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)
@@ -1218,7 +1393,7 @@ nlmsg_failure:
 	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;
@@ -1229,7 +1404,7 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard)
 	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;
@@ -1237,6 +1412,93 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard)
 	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 = RTA_SPACE(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr);
+	len += NLMSG_SPACE(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);
+	if (copy_to_user_tmpl(xp, skb) < 0)
+		goto nlmsg_failure;
+
+	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("xfrm_user: Unknown Policy event %d\n", c->event);
+	}
+
+	return 0;
+
+}
+
 static struct xfrm_mgr netlink_mgr = {
 	.id		= "netlink",
 	.notify		= xfrm_send_state_notify,