Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2013-12-19

1) Use the user supplied policy index instead of a generated one
   if present. From Fan Du.

2) Make xfrm migration namespace aware. From Fan Du.

3) Make the xfrm state and policy locks namespace aware. From Fan Du.

4) Remove ancient sleeping when the SA is in acquire state,
   we now queue packets to the policy instead. This replaces the
   sleeping code.

5) Remove FLOWI_FLAG_CAN_SLEEP. This was used to notify xfrm about the
   posibility to sleep. The sleeping code is gone, so remove it.

6) Check user specified spi for IPComp. Thr spi for IPcomp is only
   16 bit wide, so check for a valid value. From Fan Du.

7) Export verify_userspi_info to check for valid user supplied spi ranges
   with pfkey and netlink. From Fan Du.

8) RFC3173 states that if the total size of a compressed payload and the IPComp
   header is not smaller than the size of the original payload, the IP datagram
   must be sent in the original non-compressed form. These packets are dropped
   by the inbound policy check because they are not transformed. Document the need
   to set 'level use' for IPcomp to receive such packets anyway. From Fan Du.

Please pull or let me know if there are problems.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 79 insertions, 70 deletions

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 68c2f357a183..a62c25ea3631 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);
@@ -374,8 +372,6 @@ 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)
@@ -390,7 +386,6 @@ 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;
@@ -460,12 +455,8 @@ resched:
 	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)
@@ -535,14 +526,14 @@ 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
@@ -603,7 +594,7 @@ int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info)
 {
 	int i, err = 0, cnt = 0;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	err = xfrm_state_flush_secctx_check(net, proto, audit_info);
 	if (err)
 		goto out;
@@ -616,7 +607,7 @@ 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,
@@ -627,7 +618,7 @@ restart:
 				if (!err)
 					cnt++;
 
-				spin_lock_bh(&xfrm_state_lock);
+				spin_lock_bh(&net->xfrm.xfrm_state_lock);
 				goto restart;
 			}
 		}
@@ -636,19 +627,18 @@ 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);
 
@@ -801,7 +791,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 
 	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 &&
@@ -886,7 +876,7 @@ 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 +890,7 @@ 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(&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 &&
@@ -918,7 +908,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 
 	if (rx)
 		xfrm_state_hold(rx);
-	spin_unlock(&xfrm_state_lock);
+	spin_unlock(&net->xfrm.xfrm_state_lock);
 
 
 	return rx;
@@ -950,14 +940,12 @@ 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 +968,16 @@ 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 +1069,7 @@ 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 +1098,7 @@ 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);
@@ -1203,16 +1193,16 @@ out:
 	return NULL;
 }
 
-/* xfrm_state_lock is held */
-struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
+/* net->xfrm.xfrm_state_lock is held */
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
 {
 	unsigned int h;
 	struct xfrm_state *x;
 
 	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;
@@ -1227,9 +1217,9 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 			return x;
 		}
 	} 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;
@@ -1283,10 +1273,11 @@ 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 +1297,7 @@ 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);
@@ -1377,9 +1368,9 @@ 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 +1382,9 @@ 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 +1396,9 @@ 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 +1407,17 @@ 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 +1429,15 @@ 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(*dst);
+
 	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 +1469,9 @@ 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 +1489,30 @@ 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);
@@ -1536,10 +1553,10 @@ 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;
 	}
@@ -1562,7 +1579,7 @@ 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
@@ -1586,7 +1603,7 @@ 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);
@@ -1600,14 +1617,14 @@ void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
 }
 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)
 {
 	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);
 
@@ -1655,16 +1672,12 @@ 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 +1720,12 @@ 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);
 
@@ -2025,7 +2034,7 @@ 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: