Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

5 files changed, 239 insertions, 217 deletions

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 88843996f935..6c7ac016ce3a 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -67,7 +67,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
 	case IPPROTO_COMP:
 		if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr)))
 			return -EINVAL;
-		*spi = htonl(ntohs(*(__be16*)(skb_transport_header(skb) + 2)));
+		*spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2)));
 		*seq = 0;
 		return 0;
 	default:
@@ -77,8 +77,8 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
 	if (!pskb_may_pull(skb, hlen))
 		return -EINVAL;
 
-	*spi = *(__be32*)(skb_transport_header(skb) + offset);
-	*seq = *(__be32*)(skb_transport_header(skb) + offset_seq);
+	*spi = *(__be32 *)(skb_transport_header(skb) + offset);
+	*seq = *(__be32 *)(skb_transport_header(skb) + offset_seq);
 	return 0;
 }
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0d49945d0b9e..4b98b25793c5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -39,12 +39,7 @@
 #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
 #define XFRM_MAX_QUEUE_LEN	100
 
-DEFINE_MUTEX(xfrm_cfg_mutex);
-EXPORT_SYMBOL(xfrm_cfg_mutex);
-
-static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
 static struct dst_entry *xfrm_policy_sk_bundles;
-static DEFINE_RWLOCK(xfrm_policy_lock);
 
 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
 static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
@@ -176,7 +171,7 @@ static inline unsigned long make_jiffies(long secs)
 
 static void xfrm_policy_timer(unsigned long data)
 {
-	struct xfrm_policy *xp = (struct xfrm_policy*)data;
+	struct xfrm_policy *xp = (struct xfrm_policy *)data;
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
@@ -438,7 +433,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	if (!ndst)
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	for (i = hmask; i >= 0; i--)
 		xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);
@@ -446,7 +441,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	net->xfrm.policy_bydst[dir].table = ndst;
 	net->xfrm.policy_bydst[dir].hmask = nhashmask;
 
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
 }
@@ -463,7 +458,7 @@ static void xfrm_byidx_resize(struct net *net, int total)
 	if (!nidx)
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	for (i = hmask; i >= 0; i--)
 		xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);
@@ -471,7 +466,7 @@ static void xfrm_byidx_resize(struct net *net, int total)
 	net->xfrm.policy_byidx = nidx;
 	net->xfrm.policy_idx_hmask = nhashmask;
 
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
 }
@@ -504,7 +499,7 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total)
 
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 {
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
 	si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
 	si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
@@ -513,7 +508,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 	si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
 	si->spdhcnt = net->xfrm.policy_idx_hmask;
 	si->spdhmcnt = xfrm_policy_hashmax;
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 EXPORT_SYMBOL(xfrm_spd_getinfo);
 
@@ -538,7 +533,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 
 /* Generate new index... KAME seems to generate them ordered by cost
  * of an absolute inpredictability of ordering of rules. This will not pass. */
-static u32 xfrm_gen_index(struct net *net, int dir)
+static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
 {
 	static u32 idx_generator;
 
@@ -548,8 +543,14 @@ static u32 xfrm_gen_index(struct net *net, int dir)
 		u32 idx;
 		int found;
 
-		idx = (idx_generator | dir);
-		idx_generator += 8;
+		if (!index) {
+			idx = (idx_generator | dir);
+			idx_generator += 8;
+		} else {
+			idx = index;
+			index = 0;
+		}
+
 		if (idx == 0)
 			idx = 8;
 		list = net->xfrm.policy_byidx + idx_hash(net, idx);
@@ -630,7 +631,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct hlist_head *chain;
 	struct hlist_node *newpos;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
 	delpol = NULL;
 	newpos = NULL;
@@ -641,7 +642,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			if (excl) {
-				write_unlock_bh(&xfrm_policy_lock);
+				write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 				return -EEXIST;
 			}
 			delpol = pol;
@@ -672,14 +673,14 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		xfrm_policy_requeue(delpol, policy);
 		__xfrm_policy_unlink(delpol, dir);
 	}
-	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
+	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
 	hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
 	policy->curlft.add_time = get_seconds();
 	policy->curlft.use_time = 0;
 	if (!mod_timer(&policy->timer, jiffies + HZ))
 		xfrm_pol_hold(policy);
 	list_add(&policy->walk.all, &net->xfrm.policy_all);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (delpol)
 		xfrm_policy_kill(delpol);
@@ -699,7 +700,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 	struct hlist_head *chain;
 
 	*err = 0;
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
@@ -712,7 +713,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 				*err = security_xfrm_policy_delete(
 								pol->security);
 				if (*err) {
-					write_unlock_bh(&xfrm_policy_lock);
+					write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 					return pol;
 				}
 				__xfrm_policy_unlink(pol, dir);
@@ -721,7 +722,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 			break;
 		}
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
@@ -740,7 +741,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 		return NULL;
 
 	*err = 0;
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = net->xfrm.policy_byidx + idx_hash(net, id);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, byidx) {
@@ -751,7 +752,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 				*err = security_xfrm_policy_delete(
 								pol->security);
 				if (*err) {
-					write_unlock_bh(&xfrm_policy_lock);
+					write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 					return pol;
 				}
 				__xfrm_policy_unlink(pol, dir);
@@ -760,7 +761,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 			break;
 		}
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
@@ -823,7 +824,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 {
 	int dir, err = 0, cnt = 0;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	err = xfrm_policy_flush_secctx_check(net, type, audit_info);
 	if (err)
@@ -839,7 +840,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 			if (pol->type != type)
 				continue;
 			__xfrm_policy_unlink(pol, dir);
-			write_unlock_bh(&xfrm_policy_lock);
+			write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 			cnt++;
 
 			xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
@@ -848,7 +849,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 
 			xfrm_policy_kill(pol);
 
-			write_lock_bh(&xfrm_policy_lock);
+			write_lock_bh(&net->xfrm.xfrm_policy_lock);
 			goto again1;
 		}
 
@@ -860,7 +861,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 				if (pol->type != type)
 					continue;
 				__xfrm_policy_unlink(pol, dir);
-				write_unlock_bh(&xfrm_policy_lock);
+				write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 				cnt++;
 
 				xfrm_audit_policy_delete(pol, 1,
@@ -869,7 +870,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 							 audit_info->secid);
 				xfrm_policy_kill(pol);
 
-				write_lock_bh(&xfrm_policy_lock);
+				write_lock_bh(&net->xfrm.xfrm_policy_lock);
 				goto again2;
 			}
 		}
@@ -878,7 +879,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 	if (!cnt)
 		err = -ESRCH;
 out:
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_flush);
@@ -898,7 +899,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 	if (list_empty(&walk->walk.all) && walk->seq != 0)
 		return 0;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	if (list_empty(&walk->walk.all))
 		x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
 	else
@@ -924,7 +925,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 	}
 	list_del_init(&walk->walk.all);
 out:
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return error;
 }
 EXPORT_SYMBOL(xfrm_policy_walk);
@@ -938,14 +939,14 @@ void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type)
 }
 EXPORT_SYMBOL(xfrm_policy_walk_init);
 
-void xfrm_policy_walk_done(struct xfrm_policy_walk *walk)
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
 {
 	if (list_empty(&walk->walk.all))
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
 	list_del(&walk->walk.all);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 EXPORT_SYMBOL(xfrm_policy_walk_done);
 
@@ -990,7 +991,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	if (unlikely(!daddr || !saddr))
 		return NULL;
 
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_direct(net, daddr, saddr, family, dir);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
@@ -1026,7 +1027,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	if (ret)
 		xfrm_pol_hold(ret);
 fail:
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	return ret;
 }
@@ -1103,8 +1104,9 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
 						 const struct flowi *fl)
 {
 	struct xfrm_policy *pol;
+	struct net *net = sock_net(sk);
 
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	if ((pol = sk->sk_policy[dir]) != NULL) {
 		bool match = xfrm_selector_match(&pol->selector, fl,
 						 sk->sk_family);
@@ -1128,7 +1130,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
 			pol = NULL;
 	}
 out:
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return pol;
 }
 
@@ -1166,9 +1168,11 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 
 int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 {
-	write_lock_bh(&xfrm_policy_lock);
+	struct net *net = xp_net(pol);
+
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	pol = __xfrm_policy_unlink(pol, dir);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	if (pol) {
 		xfrm_policy_kill(pol);
 		return 0;
@@ -1187,12 +1191,12 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		return -EINVAL;
 #endif
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	old_pol = sk->sk_policy[dir];
 	sk->sk_policy[dir] = pol;
 	if (pol) {
 		pol->curlft.add_time = get_seconds();
-		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
+		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
 		__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
 	}
 	if (old_pol) {
@@ -1204,7 +1208,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		 */
 		__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (old_pol) {
 		xfrm_policy_kill(old_pol);
@@ -1215,6 +1219,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 {
 	struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
+	struct net *net = xp_net(old);
 
 	if (newp) {
 		newp->selector = old->selector;
@@ -1233,9 +1238,9 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 		newp->type = old->type;
 		memcpy(newp->xfrm_vec, old->xfrm_vec,
 		       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
-		write_lock_bh(&xfrm_policy_lock);
+		write_lock_bh(&net->xfrm.xfrm_policy_lock);
 		__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
-		write_unlock_bh(&xfrm_policy_lock);
+		write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 		xfrm_pol_put(newp);
 	}
 	return newp;
@@ -1281,7 +1286,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 	xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
 	xfrm_address_t tmp;
 
-	for (nx=0, i = 0; i < policy->xfrm_nr; i++) {
+	for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
 		struct xfrm_state *x;
 		xfrm_address_t *remote = daddr;
 		xfrm_address_t *local  = saddr;
@@ -1311,9 +1316,9 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 			error = (x->km.state == XFRM_STATE_ERROR ?
 				 -EINVAL : -EAGAIN);
 			xfrm_state_put(x);
-		}
-		else if (error == -ESRCH)
+		} else if (error == -ESRCH) {
 			error = -EAGAIN;
+		}
 
 		if (!tmpl->optional)
 			goto fail;
@@ -1321,7 +1326,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 	return nx;
 
 fail:
-	for (nx--; nx>=0; nx--)
+	for (nx--; nx >= 0; nx--)
 		xfrm_state_put(xfrm[nx]);
 	return error;
 }
@@ -1358,7 +1363,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
 	return cnx;
 
  fail:
-	for (cnx--; cnx>=0; cnx--)
+	for (cnx--; cnx >= 0; cnx--)
 		xfrm_state_put(tpp[cnx]);
 	return error;
 
@@ -1636,20 +1641,22 @@ free_dst:
 	goto out;
 }
 
-static int inline
-xfrm_dst_alloc_copy(void **target, const void *src, int size)
+#ifdef CONFIG_XFRM_SUB_POLICY
+static int xfrm_dst_alloc_copy(void **target, const void *src, int size)
 {
 	if (!*target) {
 		*target = kmalloc(size, GFP_ATOMIC);
 		if (!*target)
 			return -ENOMEM;
 	}
+
 	memcpy(*target, src, size);
 	return 0;
 }
+#endif
 
-static int inline
-xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel)
+static int xfrm_dst_update_parent(struct dst_entry *dst,
+				  const struct xfrm_selector *sel)
 {
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
@@ -1660,8 +1667,8 @@ xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel)
 #endif
 }
 
-static int inline
-xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl)
+static int xfrm_dst_update_origin(struct dst_entry *dst,
+				  const struct flowi *fl)
 {
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
@@ -1699,7 +1706,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 				xfrm_pols_put(pols, *num_pols);
 				return PTR_ERR(pols[1]);
 			}
-			(*num_pols) ++;
+			(*num_pols)++;
 			(*num_xfrms) += pols[1]->xfrm_nr;
 		}
 	}
@@ -1753,7 +1760,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	}
 
 	xdst->num_pols = num_pols;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 	xdst->policy_genid = atomic_read(&pols[0]->genid);
 
 	return xdst;
@@ -1896,8 +1903,7 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
 	if (IS_ERR(xdst))
 		return xdst;
 
-	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 ||
-	    (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP))
+	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0)
 		return xdst;
 
 	dst1 = &xdst->u.dst;
@@ -2023,7 +2029,7 @@ make_dummy_bundle:
 	}
 	xdst->num_pols = num_pols;
 	xdst->num_xfrms = num_xfrms;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 
 	dst_hold(&xdst->u.dst);
 	return &xdst->flo;
@@ -2072,7 +2078,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
 	int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
 
-restart:
 	dst = NULL;
 	xdst = NULL;
 	route = NULL;
@@ -2106,10 +2111,10 @@ restart:
 
 			dst_hold(&xdst->u.dst);
 
-			spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+			spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
 			xdst->u.dst.next = xfrm_policy_sk_bundles;
 			xfrm_policy_sk_bundles = &xdst->u.dst;
-			spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+			spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
 
 			route = xdst->route;
 		}
@@ -2133,7 +2138,7 @@ restart:
 
 		num_pols = xdst->num_pols;
 		num_xfrms = xdst->num_xfrms;
-		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
 		route = xdst->route;
 	}
 
@@ -2152,23 +2157,8 @@ restart:
 
 			return make_blackhole(net, family, dst_orig);
 		}
-		if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) {
-			DECLARE_WAITQUEUE(wait, current);
 
-			add_wait_queue(&net->xfrm.km_waitq, &wait);
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-			set_current_state(TASK_RUNNING);
-			remove_wait_queue(&net->xfrm.km_waitq, &wait);
-
-			if (!signal_pending(current)) {
-				dst_release(dst);
-				goto restart;
-			}
-
-			err = -ERESTART;
-		} else
-			err = -EAGAIN;
+		err = -EAGAIN;
 
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 		goto error;
@@ -2344,7 +2334,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	if (skb->sp) {
 		int i;
 
-		for (i=skb->sp->len-1; i>=0; i--) {
+		for (i = skb->sp->len-1; i >= 0; i--) {
 			struct xfrm_state *x = skb->sp->xvec[i];
 			if (!xfrm_selector_match(&x->sel, &fl, family)) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
@@ -2390,7 +2380,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	pol->curlft.use_time = get_seconds();
 
 	pols[0] = pol;
-	npols ++;
+	npols++;
 #ifdef CONFIG_XFRM_SUB_POLICY
 	if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
 		pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
@@ -2402,7 +2392,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 				return 0;
 			}
 			pols[1]->curlft.use_time = get_seconds();
-			npols ++;
+			npols++;
 		}
 	}
 #endif
@@ -2434,7 +2424,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		}
 		xfrm_nr = ti;
 		if (npols > 1) {
-			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
+			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net);
 			tpp = stp;
 		}
 
@@ -2563,10 +2553,10 @@ static void __xfrm_garbage_collect(struct net *net)
 {
 	struct dst_entry *head, *next;
 
-	spin_lock_bh(&xfrm_policy_sk_bundle_lock);
+	spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
 	head = xfrm_policy_sk_bundles;
 	xfrm_policy_sk_bundles = NULL;
-	spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
 
 	while (head) {
 		next = head->next;
@@ -2950,6 +2940,13 @@ static int __net_init xfrm_net_init(struct net *net)
 	rv = xfrm_sysctl_init(net);
 	if (rv < 0)
 		goto out_sysctl;
+
+	/* Initialize the per-net locks here */
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	rwlock_init(&net->xfrm.xfrm_policy_lock);
+	spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock);
+	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
 	return 0;
 
 out_sysctl:
@@ -2992,7 +2989,7 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp,
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(sel->family) {
+	switch (sel->family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4);
 		if (sel->prefixlen_s != 32)
@@ -3069,15 +3066,15 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
 	return false;
 }
 
-static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel,
-						     u8 dir, u8 type)
+static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
+						    u8 dir, u8 type, struct net *net)
 {
 	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;
 	u32 priority = ~0U;
 
-	read_lock_bh(&xfrm_policy_lock);
-	chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/
+	chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type) {
@@ -3086,7 +3083,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
 			break;
 		}
 	}
-	chain = &init_net.xfrm.policy_inexact[dir];
+	chain = &net->xfrm.policy_inexact[dir];
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type &&
@@ -3099,7 +3096,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
 	if (ret)
 		xfrm_pol_hold(ret);
 
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	return ret;
 }
@@ -3210,7 +3207,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate)
 
 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
-		 struct xfrm_kmaddress *k)
+		 struct xfrm_kmaddress *k, struct net *net)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -3223,14 +3220,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		goto out;
 
 	/* Stage 1 - find policy */
-	if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) {
+	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
 		err = -ENOENT;
 		goto out;
 	}
 
 	/* Stage 2 - find and update state(s) */
 	for (i = 0, mp = m; i < num_migrate; i++, mp++) {
-		if ((x = xfrm_migrate_state_find(mp))) {
+		if ((x = xfrm_migrate_state_find(mp, net))) {
 			x_cur[nx_cur] = x;
 			nx_cur++;
 			if ((xc = xfrm_state_migrate(x, mp))) {
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index 80cd1e55b834..fc5abd0b456f 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -52,7 +52,7 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
 	int i;
-	for (i=0; xfrm_mib_list[i].name; i++)
+	for (i = 0; xfrm_mib_list[i].name; i++)
 		seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name,
 			   snmp_fold_field((void __percpu **)
 					   net->mib.xfrm_statistics,
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8ed9d0dd4566..a26b7aa79475 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)
@@ -386,11 +382,10 @@ static inline unsigned long make_jiffies(long secs)
 		return secs*HZ;
 }
 
-static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
+static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
 	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
 	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
-	struct net *net = xs_net(x);
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
@@ -453,19 +448,15 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
 	if (warn)
 		km_state_expired(x, 0, 0);
 resched:
-	if (next != LONG_MAX){
+	if (next != LONG_MAX) {
 		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
 	}
 
 	goto out;
 
 expired:
-	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) {
+	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0)
 		x->km.state = XFRM_STATE_EXPIRED;
-		wake_up(&net->xfrm.km_waitq);
-		next = 2;
-		goto resched;
-	}
 
 	err = __xfrm_state_delete(x);
 	if (!err)
@@ -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_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family == family &&
@@ -918,13 +908,35 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 
 	if (rx)
 		xfrm_state_hold(rx);
-	spin_unlock(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 
 	return rx;
 }
 EXPORT_SYMBOL(xfrm_stateonly_find);
 
+struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+					      unsigned short family)
+{
+	struct xfrm_state *x;
+	struct xfrm_state_walk *w;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	list_for_each_entry(w, &net->xfrm.state_all, all) {
+		x = container_of(w, struct xfrm_state, km);
+		if (x->props.family != family ||
+			x->id.spi != spi)
+			continue;
+
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		xfrm_state_hold(x);
+		return x;
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(xfrm_state_lookup_byspi);
+
 static void __xfrm_state_insert(struct xfrm_state *x)
 {
 	struct net *net = xs_net(x);
@@ -950,14 +962,12 @@ 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 +990,16 @@ 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 +1091,7 @@ 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 +1120,7 @@ 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 +1215,16 @@ 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 +1239,9 @@ 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;
@@ -1247,8 +1259,8 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 }
 EXPORT_SYMBOL(xfrm_migrate_state_find);
 
-struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
-				       struct xfrm_migrate *m)
+struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+				      struct xfrm_migrate *m)
 {
 	struct xfrm_state *xc;
 	int err;
@@ -1283,10 +1295,11 @@ 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 +1319,7 @@ int xfrm_state_update(struct xfrm_state *x)
 	err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (to_put)
 		xfrm_state_put(to_put);
@@ -1357,7 +1370,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL);
+		tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
 		return -EINVAL;
 	}
 
@@ -1377,9 +1390,9 @@ 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 +1404,9 @@ 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 +1418,9 @@ 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 +1429,17 @@ 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 +1451,15 @@ 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 +1491,9 @@ 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 +1511,30 @@ u32 xfrm_get_acqseq(void)
 }
 EXPORT_SYMBOL(xfrm_get_acqseq);
 
+int verify_spi_info(u8 proto, u32 min, u32 max)
+{
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+		break;
+
+	case IPPROTO_COMP:
+		/* IPCOMP spi is 16-bits. */
+		if (max >= 0x10000)
+			return -EINVAL;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (min > max)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(verify_spi_info);
+
 int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 {
 	struct net *net = xs_net(x);
@@ -1525,8 +1564,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 		x->id.spi = minspi;
 	} else {
 		u32 spi = 0;
-		for (h=0; h<high-low+1; h++) {
-			spi = low + net_random()%(high-low+1);
+		for (h = 0; h < high-low+1; h++) {
+			spi = low + prandom_u32()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
 				x->id.spi = htonl(spi);
@@ -1536,10 +1575,10 @@ 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 +1601,7 @@ 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 +1625,7 @@ 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);
@@ -1600,20 +1639,20 @@ 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);
 
 static void xfrm_replay_timer_handler(unsigned long data)
 {
-	struct xfrm_state *x = (struct xfrm_state*)data;
+	struct xfrm_state *x = (struct xfrm_state *)data;
 
 	spin_lock(&x->lock);
 
@@ -1655,16 +1694,12 @@ 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 +1742,12 @@ 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 +2056,7 @@ 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:
@@ -2070,7 +2101,7 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x,
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(x->props.family) {
+	switch (x->props.family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
 				 &x->props.saddr.a4, &x->id.daddr.a4);
@@ -2100,7 +2131,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 		iph6 = ipv6_hdr(skb);
 		audit_log_format(audit_buf,
 				 " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
-				 &iph6->saddr,&iph6->daddr,
+				 &iph6->saddr, &iph6->daddr,
 				 iph6->flow_lbl[0] & 0x0f,
 				 iph6->flow_lbl[1],
 				 iph6->flow_lbl[2]);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ec97e13743e6..1ae3ec7c18b0 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -181,7 +181,9 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AEAD]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
 		    attrs[XFRMA_ALG_COMP]	||
-		    attrs[XFRMA_TFCPAD])
+		    attrs[XFRMA_TFCPAD]		||
+		    (ntohl(p->id.spi) >= 0x10000))
+
 			goto out;
 		break;
 
@@ -877,7 +879,10 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
 static int xfrm_dump_sa_done(struct netlink_callback *cb)
 {
 	struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
-	xfrm_state_walk_done(walk);
+	struct sock *sk = cb->skb->sk;
+	struct net *net = sock_net(sk);
+
+	xfrm_state_walk_done(walk, net);
 	return 0;
 }
 
@@ -1074,29 +1079,6 @@ out_noput:
 	return err;
 }
 
-static int verify_userspi_info(struct xfrm_userspi_info *p)
-{
-	switch (p->info.id.proto) {
-	case IPPROTO_AH:
-	case IPPROTO_ESP:
-		break;
-
-	case IPPROTO_COMP:
-		/* IPCOMP spi is 16-bits. */
-		if (p->max >= 0x10000)
-			return -EINVAL;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	if (p->min > p->max)
-		return -EINVAL;
-
-	return 0;
-}
-
 static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct nlattr **attrs)
 {
@@ -1111,7 +1093,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_mark m;
 
 	p = nlmsg_data(nlh);
-	err = verify_userspi_info(p);
+	err = verify_spi_info(p->info.id.proto, p->min, p->max);
 	if (err)
 		goto out_noput;
 
@@ -1189,6 +1171,8 @@ static int verify_policy_type(u8 type)
 
 static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 {
+	int ret;
+
 	switch (p->share) {
 	case XFRM_SHARE_ANY:
 	case XFRM_SHARE_SESSION:
@@ -1224,7 +1208,13 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 		return -EINVAL;
 	}
 
-	return verify_policy_dir(p->dir);
+	ret = verify_policy_dir(p->dir);
+	if (ret)
+		return ret;
+	if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+		return -EINVAL;
+
+	return 0;
 }
 
 static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs)
@@ -1547,8 +1537,9 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 static int xfrm_dump_policy_done(struct netlink_callback *cb)
 {
 	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
+	struct net *net = sock_net(cb->skb->sk);
 
-	xfrm_policy_walk_done(walk);
+	xfrm_policy_walk_done(walk, net);
 	return 0;
 }
 
@@ -1740,11 +1731,11 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
 		return -EMSGSIZE;
 
 	id = nlmsg_data(nlh);
-	memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr));
+	memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr));
 	id->sa_id.spi = x->id.spi;
 	id->sa_id.family = x->props.family;
 	id->sa_id.proto = x->id.proto;
-	memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr));
+	memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr));
 	id->reqid = x->props.reqid;
 	id->flags = c->data.aevent;
 
@@ -1833,7 +1824,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_state *x;
 	struct km_event c;
-	int err = - EINVAL;
+	int err = -EINVAL;
 	u32 mark = 0;
 	struct xfrm_mark m;
 	struct xfrm_aevent_id *p = nlmsg_data(nlh);
@@ -2129,6 +2120,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u8 type;
 	int err;
 	int n = 0;
+	struct net *net = sock_net(skb->sk);
 
 	if (attrs[XFRMA_MIGRATE] == NULL)
 		return -EINVAL;
@@ -2146,7 +2138,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!n)
 		return 0;
 
-	xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp);
+	xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net);
 
 	return 0;
 }
@@ -2394,9 +2386,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 static void xfrm_netlink_rcv(struct sk_buff *skb)
 {
-	mutex_lock(&xfrm_cfg_mutex);
+	struct net *net = sock_net(skb->sk);
+
+	mutex_lock(&net->xfrm.xfrm_cfg_mutex);
 	netlink_rcv_skb(skb, &xfrm_user_rcv_msg);
-	mutex_unlock(&xfrm_cfg_mutex);
+	mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
 }
 
 static inline size_t xfrm_expire_msgsize(void)