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

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

1 files changed, 98 insertions, 93 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 4cbda4bd8926..dd2c43abf9e2 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -348,16 +348,10 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 
 	tmpl->status = IPS_TEMPLATE;
 	write_pnet(&tmpl->ct_net, net);
-
-	if (nf_ct_zone_add(tmpl, flags, zone) < 0)
-		goto out_free;
-
+	nf_ct_zone_add(tmpl, zone);
 	atomic_set(&tmpl->ct_general.use, 0);
 
 	return tmpl;
-out_free:
-	kfree(tmpl);
-	return NULL;
 }
 EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
 
@@ -487,6 +481,23 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
 	       net_eq(net, nf_ct_net(ct));
 }
 
+/* must be called with rcu read lock held */
+void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize)
+{
+	struct hlist_nulls_head *hptr;
+	unsigned int sequence, hsz;
+
+	do {
+		sequence = read_seqcount_begin(&nf_conntrack_generation);
+		hsz = nf_conntrack_htable_size;
+		hptr = nf_conntrack_hash;
+	} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
+
+	*hash = hptr;
+	*hsize = hsz;
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_get_ht);
+
 /*
  * Warning :
  * - Caller must take a reference on returned object
@@ -845,67 +856,69 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);
 
 /* There's a small race here where we may free a just-assured
    connection.  Too bad: we're in trouble anyway. */
-static noinline int early_drop(struct net *net, unsigned int _hash)
+static unsigned int early_drop_list(struct net *net,
+				    struct hlist_nulls_head *head)
 {
-	/* Use oldest entry, which is roughly LRU */
 	struct nf_conntrack_tuple_hash *h;
-	struct nf_conn *tmp;
 	struct hlist_nulls_node *n;
-	unsigned int i, hash, sequence;
-	struct nf_conn *ct = NULL;
-	spinlock_t *lockp;
-	bool ret = false;
+	unsigned int drops = 0;
+	struct nf_conn *tmp;
 
-	i = 0;
+	hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
+		tmp = nf_ct_tuplehash_to_ctrack(h);
 
-	local_bh_disable();
-restart:
-	sequence = read_seqcount_begin(&nf_conntrack_generation);
-	for (; i < NF_CT_EVICTION_RANGE; i++) {
-		hash = scale_hash(_hash++);
-		lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
-		nf_conntrack_lock(lockp);
-		if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
-			spin_unlock(lockp);
-			goto restart;
-		}
-		hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash],
-					       hnnode) {
-			tmp = nf_ct_tuplehash_to_ctrack(h);
-
-			if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
-			    !net_eq(nf_ct_net(tmp), net) ||
-			    nf_ct_is_dying(tmp))
-				continue;
-
-			if (atomic_inc_not_zero(&tmp->ct_general.use)) {
-				ct = tmp;
-				break;
-			}
-		}
+		if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
+		    !net_eq(nf_ct_net(tmp), net) ||
+		    nf_ct_is_dying(tmp))
+			continue;
 
-		spin_unlock(lockp);
-		if (ct)
-			break;
+		if (!atomic_inc_not_zero(&tmp->ct_general.use))
+			continue;
+
+		/* kill only if still in same netns -- might have moved due to
+		 * SLAB_DESTROY_BY_RCU rules.
+		 *
+		 * We steal the timer reference.  If that fails timer has
+		 * already fired or someone else deleted it. Just drop ref
+		 * and move to next entry.
+		 */
+		if (net_eq(nf_ct_net(tmp), net) &&
+		    nf_ct_is_confirmed(tmp) &&
+		    del_timer(&tmp->timeout) &&
+		    nf_ct_delete(tmp, 0, 0))
+			drops++;
+
+		nf_ct_put(tmp);
 	}
 
-	local_bh_enable();
+	return drops;
+}
 
-	if (!ct)
-		return false;
+static noinline int early_drop(struct net *net, unsigned int _hash)
+{
+	unsigned int i;
 
-	/* kill only if in same netns -- might have moved due to
-	 * SLAB_DESTROY_BY_RCU rules
-	 */
-	if (net_eq(nf_ct_net(ct), net) && del_timer(&ct->timeout)) {
-		if (nf_ct_delete(ct, 0, 0)) {
-			NF_CT_STAT_INC_ATOMIC(net, early_drop);
-			ret = true;
+	for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
+		struct hlist_nulls_head *ct_hash;
+		unsigned hash, sequence, drops;
+
+		rcu_read_lock();
+		do {
+			sequence = read_seqcount_begin(&nf_conntrack_generation);
+			hash = scale_hash(_hash++);
+			ct_hash = nf_conntrack_hash;
+		} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
+
+		drops = early_drop_list(net, &ct_hash[hash]);
+		rcu_read_unlock();
+
+		if (drops) {
+			NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops);
+			return true;
 		}
 	}
 
-	nf_ct_put(ct);
-	return ret;
+	return false;
 }
 
 static struct nf_conn *
@@ -951,16 +964,13 @@ __nf_conntrack_alloc(struct net *net,
 	       offsetof(struct nf_conn, proto) -
 	       offsetof(struct nf_conn, __nfct_init_offset[0]));
 
-	if (zone && nf_ct_zone_add(ct, GFP_ATOMIC, zone) < 0)
-		goto out_free;
+	nf_ct_zone_add(ct, zone);
 
 	/* Because we use RCU lookups, we set ct_general.use to zero before
 	 * this is inserted in any list.
 	 */
 	atomic_set(&ct->ct_general.use, 0);
 	return ct;
-out_free:
-	kmem_cache_free(nf_conntrack_cachep, ct);
 out:
 	atomic_dec(&net->ct.count);
 	return ERR_PTR(-ENOMEM);
@@ -1364,14 +1374,6 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
 }
 EXPORT_SYMBOL_GPL(__nf_ct_kill_acct);
 
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = {
-	.len	= sizeof(struct nf_conntrack_zone),
-	.align	= __alignof__(struct nf_conntrack_zone),
-	.id	= NF_CT_EXT_ZONE,
-};
-#endif
-
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
@@ -1554,9 +1556,6 @@ void nf_conntrack_cleanup_end(void)
 
 	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
 
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-	nf_ct_extend_unregister(&nf_ct_zone_extend);
-#endif
 	nf_conntrack_proto_fini();
 	nf_conntrack_seqadj_fini();
 	nf_conntrack_labels_fini();
@@ -1646,24 +1645,14 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
 }
 EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable);
 
-int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
+int nf_conntrack_hash_resize(unsigned int hashsize)
 {
-	int i, bucket, rc;
-	unsigned int hashsize, old_size;
+	int i, bucket;
+	unsigned int old_size;
 	struct hlist_nulls_head *hash, *old_hash;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 
-	if (current->nsproxy->net_ns != &init_net)
-		return -EOPNOTSUPP;
-
-	/* On boot, we can set this without any fancy locking. */
-	if (!nf_conntrack_htable_size)
-		return param_set_uint(val, kp);
-
-	rc = kstrtouint(val, 0, &hashsize);
-	if (rc)
-		return rc;
 	if (!hashsize)
 		return -EINVAL;
 
@@ -1671,6 +1660,12 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	if (!hash)
 		return -ENOMEM;
 
+	old_size = nf_conntrack_htable_size;
+	if (old_size == hashsize) {
+		nf_ct_free_hashtable(hash, hashsize);
+		return 0;
+	}
+
 	local_bh_disable();
 	nf_conntrack_all_lock();
 	write_seqcount_begin(&nf_conntrack_generation);
@@ -1706,6 +1701,25 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	nf_ct_free_hashtable(old_hash, old_size);
 	return 0;
 }
+
+int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
+{
+	unsigned int hashsize;
+	int rc;
+
+	if (current->nsproxy->net_ns != &init_net)
+		return -EOPNOTSUPP;
+
+	/* On boot, we can set this without any fancy locking. */
+	if (!nf_conntrack_htable_size)
+		return param_set_uint(val, kp);
+
+	rc = kstrtouint(val, 0, &hashsize);
+	if (rc)
+		return rc;
+
+	return nf_conntrack_hash_resize(hashsize);
+}
 EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
 
 module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
@@ -1762,7 +1776,7 @@ int nf_conntrack_init_start(void)
 
 	nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
 						sizeof(struct nf_conn), 0,
-						SLAB_DESTROY_BY_RCU, NULL);
+						SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
 	if (!nf_conntrack_cachep)
 		goto err_cachep;
 
@@ -1802,11 +1816,6 @@ int nf_conntrack_init_start(void)
 	if (ret < 0)
 		goto err_seqadj;
 
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-	ret = nf_ct_extend_register(&nf_ct_zone_extend);
-	if (ret < 0)
-		goto err_extend;
-#endif
 	ret = nf_conntrack_proto_init();
 	if (ret < 0)
 		goto err_proto;
@@ -1822,10 +1831,6 @@ int nf_conntrack_init_start(void)
 	return 0;
 
 err_proto:
-#ifdef CONFIG_NF_CONNTRACK_ZONES
-	nf_ct_extend_unregister(&nf_ct_zone_extend);
-err_extend:
-#endif
 	nf_conntrack_seqadj_fini();
 err_seqadj:
 	nf_conntrack_labels_fini();