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

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 78 insertions, 87 deletions

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 3459692092ec..ae01bdbcb294 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -158,8 +158,8 @@ out_unlock:
 	mutex_unlock(&hash_resize_mutex);
 }
 
-static DEFINE_RWLOCK(xfrm_state_afinfo_lock);
-static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO];
+static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
+static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
 
 static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 
@@ -168,58 +168,45 @@ int __xfrm_state_delete(struct xfrm_state *x);
 int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 
-static struct xfrm_state_afinfo *xfrm_state_lock_afinfo(unsigned int family)
-{
-	struct xfrm_state_afinfo *afinfo;
-	if (unlikely(family >= NPROTO))
-		return NULL;
-	write_lock_bh(&xfrm_state_afinfo_lock);
-	afinfo = xfrm_state_afinfo[family];
-	if (unlikely(!afinfo))
-		write_unlock_bh(&xfrm_state_afinfo_lock);
-	return afinfo;
-}
-
-static void xfrm_state_unlock_afinfo(struct xfrm_state_afinfo *afinfo)
-	__releases(xfrm_state_afinfo_lock)
-{
-	write_unlock_bh(&xfrm_state_afinfo_lock);
-}
-
+static DEFINE_SPINLOCK(xfrm_type_lock);
 int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family);
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
 	const struct xfrm_type **typemap;
 	int err = 0;
 
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 	typemap = afinfo->type_map;
+	spin_lock_bh(&xfrm_type_lock);
 
 	if (likely(typemap[type->proto] == NULL))
 		typemap[type->proto] = type;
 	else
 		err = -EEXIST;
-	xfrm_state_unlock_afinfo(afinfo);
+	spin_unlock_bh(&xfrm_type_lock);
+	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_type);
 
 int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family);
+	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
 	const struct xfrm_type **typemap;
 	int err = 0;
 
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 	typemap = afinfo->type_map;
+	spin_lock_bh(&xfrm_type_lock);
 
 	if (unlikely(typemap[type->proto] != type))
 		err = -ENOENT;
 	else
 		typemap[type->proto] = NULL;
-	xfrm_state_unlock_afinfo(afinfo);
+	spin_unlock_bh(&xfrm_type_lock);
+	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_type);
@@ -256,6 +243,7 @@ static void xfrm_put_type(const struct xfrm_type *type)
 	module_put(type->owner);
 }
 
+static DEFINE_SPINLOCK(xfrm_mode_lock);
 int xfrm_register_mode(struct xfrm_mode *mode, int family)
 {
 	struct xfrm_state_afinfo *afinfo;
@@ -265,12 +253,13 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family)
 	if (unlikely(mode->encap >= XFRM_MODE_MAX))
 		return -EINVAL;
 
-	afinfo = xfrm_state_lock_afinfo(family);
+	afinfo = xfrm_state_get_afinfo(family);
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 
 	err = -EEXIST;
 	modemap = afinfo->mode_map;
+	spin_lock_bh(&xfrm_mode_lock);
 	if (modemap[mode->encap])
 		goto out;
 
@@ -283,7 +272,8 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family)
 	err = 0;
 
 out:
-	xfrm_state_unlock_afinfo(afinfo);
+	spin_unlock_bh(&xfrm_mode_lock);
+	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_mode);
@@ -297,19 +287,21 @@ int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
 	if (unlikely(mode->encap >= XFRM_MODE_MAX))
 		return -EINVAL;
 
-	afinfo = xfrm_state_lock_afinfo(family);
+	afinfo = xfrm_state_get_afinfo(family);
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 
 	err = -ENOENT;
 	modemap = afinfo->mode_map;
+	spin_lock_bh(&xfrm_mode_lock);
 	if (likely(modemap[mode->encap] == mode)) {
 		modemap[mode->encap] = NULL;
 		module_put(mode->afinfo->owner);
 		err = 0;
 	}
 
-	xfrm_state_unlock_afinfo(afinfo);
+	spin_unlock_bh(&xfrm_mode_lock);
+	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_mode);
@@ -699,7 +691,7 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
 		    x->id.proto     != proto ||
-		    xfrm_addr_cmp(&x->id.daddr, daddr, family))
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family))
 			continue;
 
 		if ((mark & x->mark.m) != x->mark.v)
@@ -723,8 +715,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 	hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) {
 		if (x->props.family != family ||
 		    x->id.proto     != proto ||
-		    xfrm_addr_cmp(&x->id.daddr, daddr, family) ||
-		    xfrm_addr_cmp(&x->props.saddr, saddr, family))
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
+		    !xfrm_addr_equal(&x->props.saddr, saddr, family))
 			continue;
 
 		if ((mark & x->mark.m) != x->mark.v)
@@ -989,8 +981,8 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 		if (x->props.family	== family &&
 		    x->props.reqid	== reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
-		    !xfrm_addr_cmp(&x->id.daddr, &xnew->id.daddr, family) &&
-		    !xfrm_addr_cmp(&x->props.saddr, &xnew->props.saddr, family))
+		    xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) &&
+		    xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family))
 			x->genid++;
 	}
 }
@@ -1024,8 +1016,8 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m,
 		    x->id.spi       != 0 ||
 		    x->id.proto	    != proto ||
 		    (mark & x->mark.m) != x->mark.v ||
-		    xfrm_addr_cmp(&x->id.daddr, daddr, family) ||
-		    xfrm_addr_cmp(&x->props.saddr, saddr, family))
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
+		    !xfrm_addr_equal(&x->props.saddr, saddr, family))
 			continue;
 
 		xfrm_state_hold(x);
@@ -1108,7 +1100,7 @@ int xfrm_state_add(struct xfrm_state *x)
 	if (use_spi && x->km.seq) {
 		x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq);
 		if (x1 && ((x1->id.proto != x->id.proto) ||
-		    xfrm_addr_cmp(&x1->id.daddr, &x->id.daddr, family))) {
+		    !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) {
 			to_put = x1;
 			x1 = NULL;
 		}
@@ -1234,10 +1226,10 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 				continue;
 			if (m->reqid && x->props.reqid != m->reqid)
 				continue;
-			if (xfrm_addr_cmp(&x->id.daddr, &m->old_daddr,
-					  m->old_family) ||
-			    xfrm_addr_cmp(&x->props.saddr, &m->old_saddr,
-					  m->old_family))
+			if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
+					     m->old_family) ||
+			    !xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
+					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
 			return x;
@@ -1249,10 +1241,10 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
-			if (xfrm_addr_cmp(&x->id.daddr, &m->old_daddr,
-					  m->old_family) ||
-			    xfrm_addr_cmp(&x->props.saddr, &m->old_saddr,
-					  m->old_family))
+			if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
+					     m->old_family) ||
+			    !xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
+					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
 			return x;
@@ -1277,7 +1269,7 @@ struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
 	memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
 
 	/* add state */
-	if (!xfrm_addr_cmp(&x->id.daddr, &m->new_daddr, m->new_family)) {
+	if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
 		/* a care is needed when the destination address of the
 		   state is to be updated as it is a part of triplet */
 		xfrm_state_insert(xc);
@@ -1370,9 +1362,6 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (!x->curlft.use_time)
 		x->curlft.use_time = get_seconds();
 
-	if (x->km.state != XFRM_STATE_VALID)
-		return -EINVAL;
-
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
@@ -1648,27 +1637,26 @@ static void xfrm_replay_timer_handler(unsigned long data)
 }
 
 static LIST_HEAD(xfrm_km_list);
-static DEFINE_RWLOCK(xfrm_km_lock);
 
 void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
 {
 	struct xfrm_mgr *km;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list)
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list)
 		if (km->notify_policy)
 			km->notify_policy(xp, dir, c);
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 }
 
 void km_state_notify(struct xfrm_state *x, const struct km_event *c)
 {
 	struct xfrm_mgr *km;
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list)
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list)
 		if (km->notify)
 			km->notify(x, c);
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 }
 
 EXPORT_SYMBOL(km_policy_notify);
@@ -1698,13 +1686,13 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
 	int err = -EINVAL, acqret;
 	struct xfrm_mgr *km;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		acqret = km->acquire(x, t, pol);
 		if (!acqret)
 			err = acqret;
 	}
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(km_query);
@@ -1714,14 +1702,14 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
 	int err = -EINVAL;
 	struct xfrm_mgr *km;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		if (km->new_mapping)
 			err = km->new_mapping(x, ipaddr, sport);
 		if (!err)
 			break;
 	}
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(km_new_mapping);
@@ -1750,15 +1738,15 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	int ret;
 	struct xfrm_mgr *km;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		if (km->migrate) {
 			ret = km->migrate(sel, dir, type, m, num_migrate, k);
 			if (!ret)
 				err = ret;
 		}
 	}
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(km_migrate);
@@ -1770,15 +1758,15 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address
 	int ret;
 	struct xfrm_mgr *km;
 
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		if (km->report) {
 			ret = km->report(net, proto, sel, addr);
 			if (!ret)
 				err = ret;
 		}
 	}
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(km_report);
@@ -1802,14 +1790,14 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
 		goto out;
 
 	err = -EINVAL;
-	read_lock(&xfrm_km_lock);
-	list_for_each_entry(km, &xfrm_km_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		pol = km->compile_policy(sk, optname, data,
 					 optlen, &err);
 		if (err >= 0)
 			break;
 	}
-	read_unlock(&xfrm_km_lock);
+	rcu_read_unlock();
 
 	if (err >= 0) {
 		xfrm_sk_policy_insert(sk, err, pol);
@@ -1823,20 +1811,23 @@ out:
 }
 EXPORT_SYMBOL(xfrm_user_policy);
 
+static DEFINE_SPINLOCK(xfrm_km_lock);
+
 int xfrm_register_km(struct xfrm_mgr *km)
 {
-	write_lock_bh(&xfrm_km_lock);
-	list_add_tail(&km->list, &xfrm_km_list);
-	write_unlock_bh(&xfrm_km_lock);
+	spin_lock_bh(&xfrm_km_lock);
+	list_add_tail_rcu(&km->list, &xfrm_km_list);
+	spin_unlock_bh(&xfrm_km_lock);
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_register_km);
 
 int xfrm_unregister_km(struct xfrm_mgr *km)
 {
-	write_lock_bh(&xfrm_km_lock);
-	list_del(&km->list);
-	write_unlock_bh(&xfrm_km_lock);
+	spin_lock_bh(&xfrm_km_lock);
+	list_del_rcu(&km->list);
+	spin_unlock_bh(&xfrm_km_lock);
+	synchronize_rcu();
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_unregister_km);
@@ -1848,12 +1839,12 @@ int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo)
 		return -EINVAL;
 	if (unlikely(afinfo->family >= NPROTO))
 		return -EAFNOSUPPORT;
-	write_lock_bh(&xfrm_state_afinfo_lock);
+	spin_lock_bh(&xfrm_state_afinfo_lock);
 	if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL))
 		err = -ENOBUFS;
 	else
-		xfrm_state_afinfo[afinfo->family] = afinfo;
-	write_unlock_bh(&xfrm_state_afinfo_lock);
+		rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo);
+	spin_unlock_bh(&xfrm_state_afinfo_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_register_afinfo);
@@ -1865,14 +1856,15 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
 		return -EINVAL;
 	if (unlikely(afinfo->family >= NPROTO))
 		return -EAFNOSUPPORT;
-	write_lock_bh(&xfrm_state_afinfo_lock);
+	spin_lock_bh(&xfrm_state_afinfo_lock);
 	if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) {
 		if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo))
 			err = -EINVAL;
 		else
-			xfrm_state_afinfo[afinfo->family] = NULL;
+			RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL);
 	}
-	write_unlock_bh(&xfrm_state_afinfo_lock);
+	spin_unlock_bh(&xfrm_state_afinfo_lock);
+	synchronize_rcu();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_unregister_afinfo);
@@ -1882,17 +1874,16 @@ static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 	struct xfrm_state_afinfo *afinfo;
 	if (unlikely(family >= NPROTO))
 		return NULL;
-	read_lock(&xfrm_state_afinfo_lock);
-	afinfo = xfrm_state_afinfo[family];
+	rcu_read_lock();
+	afinfo = rcu_dereference(xfrm_state_afinfo[family]);
 	if (unlikely(!afinfo))
-		read_unlock(&xfrm_state_afinfo_lock);
+		rcu_read_unlock();
 	return afinfo;
 }
 
 static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
-	__releases(xfrm_state_afinfo_lock)
 {
-	read_unlock(&xfrm_state_afinfo_lock);
+	rcu_read_unlock();
 }
 
 /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */