Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for you net tree, they
are:

1) Restore __GFP_NORETRY in xt_table allocations to mitigate effects of
   large memory allocation requests, from Michal Hocko.

2) Release IPv6 fragment queue in case of error in fragmentation header,
   this is a follow up to amend patch 83f1999caeb1, from Subash Abhinov
   Kasiviswanathan.

3) Flowtable infrastructure depends on NETFILTER_INGRESS as it registers
   a hook for each flowtable, reported by John Crispin.

4) Missing initialization of info->priv in xt_cgroup version 1, from
   Cong Wang.

5) Give a chance to garbage collector to run after scheduling flowtable
   cleanup.

6) Releasing flowtable content on nft_flow_offload module removal is
   not required at all, there is not dependencies between this module
   and flowtables, remove it.

7) Fix missing xt_rateest_mutex grabbing for hash insertions, also from
   Cong Wang.

8) Move nf_flow_table_cleanup() routine to flowtable core, this patch is
   a dependency for the next patch in this list.

9) Flowtable resources are not properly released on removal from the
   control plane. Fix this resource leak by scheduling removal of all
   entries and explicit call to the garbage collector.

10) nf_ct_nat_offset() declaration is dead code, this function prototype
    is not used anywhere, remove it. From Taehee Yoo.

11) Fix another flowtable resource leak on entry insertion failures,
    this patch also fixes a possible use-after-free. Patch from Felix
    Fietkau.
====================

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

13 files changed, 92 insertions, 73 deletions

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 5f52236780b4..dfe6fa4ea554 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -80,8 +80,7 @@ endif # NF_TABLES
 
 config NF_FLOW_TABLE_IPV4
 	tristate "Netfilter flow table IPv4 module"
-	depends on NF_CONNTRACK && NF_TABLES
-	select NF_FLOW_TABLE
+	depends on NF_FLOW_TABLE
 	help
 	  This option adds the flow table IPv4 support.
 
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index b2d01eb25f2c..25d2975da156 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -260,6 +260,7 @@ static struct nf_flowtable_type flowtable_ipv4 = {
 	.family		= NFPROTO_IPV4,
 	.params		= &nf_flow_offload_rhash_params,
 	.gc		= nf_flow_offload_work_gc,
+	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ip_hook,
 	.owner		= THIS_MODULE,
 };
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 4a634b7a2c80..d395d1590699 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -73,8 +73,7 @@ endif # NF_TABLES
 
 config NF_FLOW_TABLE_IPV6
 	tristate "Netfilter flow table IPv6 module"
-	depends on NF_CONNTRACK && NF_TABLES
-	select NF_FLOW_TABLE
+	depends on NF_FLOW_TABLE
 	help
 	  This option adds the flow table IPv6 support.
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ce53dcfda88a..b84ce3e6d728 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -264,6 +264,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 			 * this case. -DaveM
 			 */
 			pr_debug("end of fragment not rounded to 8 bytes.\n");
+			inet_frag_kill(&fq->q, &nf_frags);
 			return -EPROTO;
 		}
 		if (end > fq->q.len) {
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index fff21602875a..d346705d6ee6 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -253,6 +253,7 @@ static struct nf_flowtable_type flowtable_ipv6 = {
 	.family		= NFPROTO_IPV6,
 	.params		= &nf_flow_offload_rhash_params,
 	.gc		= nf_flow_offload_work_gc,
+	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ipv6_hook,
 	.owner		= THIS_MODULE,
 };
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 9019fa98003d..d3220b43c832 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -666,8 +666,8 @@ endif # NF_TABLES
 
 config NF_FLOW_TABLE_INET
 	tristate "Netfilter flow table mixed IPv4/IPv6 module"
-	depends on NF_FLOW_TABLE_IPV4 && NF_FLOW_TABLE_IPV6
-	select NF_FLOW_TABLE
+	depends on NF_FLOW_TABLE_IPV4
+	depends on NF_FLOW_TABLE_IPV6
 	help
           This option adds the flow table mixed IPv4/IPv6 support.
 
@@ -675,7 +675,9 @@ config NF_FLOW_TABLE_INET
 
 config NF_FLOW_TABLE
 	tristate "Netfilter flow table module"
-	depends on NF_CONNTRACK && NF_TABLES
+	depends on NETFILTER_INGRESS
+	depends on NF_CONNTRACK
+	depends on NF_TABLES
 	help
 	  This option adds the flow table core infrastructure.
 
diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table.c
index 2f5099cb85b8..ec410cae9307 100644
--- a/net/netfilter/nf_flow_table.c
+++ b/net/netfilter/nf_flow_table.c
@@ -4,6 +4,7 @@
 #include <linux/netfilter.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
@@ -124,7 +125,9 @@ void flow_offload_free(struct flow_offload *flow)
 	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
 	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
 	e = container_of(flow, struct flow_offload_entry, flow);
-	kfree(e);
+	nf_ct_delete(e->ct, 0, 0);
+	nf_ct_put(e->ct);
+	kfree_rcu(e, rcu_head);
 }
 EXPORT_SYMBOL_GPL(flow_offload_free);
 
@@ -148,11 +151,9 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
 
-void flow_offload_del(struct nf_flowtable *flow_table,
-		      struct flow_offload *flow)
+static void flow_offload_del(struct nf_flowtable *flow_table,
+			     struct flow_offload *flow)
 {
-	struct flow_offload_entry *e;
-
 	rhashtable_remove_fast(&flow_table->rhashtable,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
 			       *flow_table->type->params);
@@ -160,10 +161,8 @@ void flow_offload_del(struct nf_flowtable *flow_table,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
 			       *flow_table->type->params);
 
-	e = container_of(flow, struct flow_offload_entry, flow);
-	kfree_rcu(e, rcu_head);
+	flow_offload_free(flow);
 }
-EXPORT_SYMBOL_GPL(flow_offload_del);
 
 struct flow_offload_tuple_rhash *
 flow_offload_lookup(struct nf_flowtable *flow_table,
@@ -174,15 +173,6 @@ flow_offload_lookup(struct nf_flowtable *flow_table,
 }
 EXPORT_SYMBOL_GPL(flow_offload_lookup);
 
-static void nf_flow_release_ct(const struct flow_offload *flow)
-{
-	struct flow_offload_entry *e;
-
-	e = container_of(flow, struct flow_offload_entry, flow);
-	nf_ct_delete(e->ct, 0, 0);
-	nf_ct_put(e->ct);
-}
-
 int nf_flow_table_iterate(struct nf_flowtable *flow_table,
 			  void (*iter)(struct flow_offload *flow, void *data),
 			  void *data)
@@ -231,19 +221,16 @@ static inline bool nf_flow_is_dying(const struct flow_offload *flow)
 	return flow->flags & FLOW_OFFLOAD_DYING;
 }
 
-void nf_flow_offload_work_gc(struct work_struct *work)
+static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
 {
 	struct flow_offload_tuple_rhash *tuplehash;
-	struct nf_flowtable *flow_table;
 	struct rhashtable_iter hti;
 	struct flow_offload *flow;
 	int err;
 
-	flow_table = container_of(work, struct nf_flowtable, gc_work.work);
-
 	err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
 	if (err)
-		goto schedule;
+		return 0;
 
 	rhashtable_walk_start(&hti);
 
@@ -261,15 +248,22 @@ void nf_flow_offload_work_gc(struct work_struct *work)
 		flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
 
 		if (nf_flow_has_expired(flow) ||
-		    nf_flow_is_dying(flow)) {
+		    nf_flow_is_dying(flow))
 			flow_offload_del(flow_table, flow);
-			nf_flow_release_ct(flow);
-		}
 	}
 out:
 	rhashtable_walk_stop(&hti);
 	rhashtable_walk_exit(&hti);
-schedule:
+
+	return 1;
+}
+
+void nf_flow_offload_work_gc(struct work_struct *work)
+{
+	struct nf_flowtable *flow_table;
+
+	flow_table = container_of(work, struct nf_flowtable, gc_work.work);
+	nf_flow_offload_gc_step(flow_table);
 	queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
 }
 EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);
@@ -425,5 +419,35 @@ int nf_flow_dnat_port(const struct flow_offload *flow,
 }
 EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
 
+static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
+{
+	struct net_device *dev = data;
+
+	if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
+		return;
+
+	flow_offload_dead(flow);
+}
+
+static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
+					  void *data)
+{
+	nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data);
+	flush_delayed_work(&flowtable->gc_work);
+}
+
+void nf_flow_table_cleanup(struct net *net, struct net_device *dev)
+{
+	nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev);
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
+
+void nf_flow_table_free(struct nf_flowtable *flow_table)
+{
+	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
+	WARN_ON(!nf_flow_offload_gc_step(flow_table));
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_free);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 281209aeba8f..375a1881d93d 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -24,6 +24,7 @@ static struct nf_flowtable_type flowtable_inet = {
 	.family		= NFPROTO_INET,
 	.params		= &nf_flow_offload_rhash_params,
 	.gc		= nf_flow_offload_work_gc,
+	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_inet_hook,
 	.owner		= THIS_MODULE,
 };
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0791813a1e7d..8b9fe30de0cd 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5006,13 +5006,13 @@ void nft_flow_table_iterate(struct net *net,
 	struct nft_flowtable *flowtable;
 	const struct nft_table *table;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(table, &net->nft.tables, list) {
-		list_for_each_entry_rcu(flowtable, &table->flowtables, list) {
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_for_each_entry(table, &net->nft.tables, list) {
+		list_for_each_entry(flowtable, &table->flowtables, list) {
 			iter(&flowtable->data, data);
 		}
 	}
-	rcu_read_unlock();
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_flow_table_iterate);
 
@@ -5399,17 +5399,12 @@ err:
 	nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
 }
 
-static void nft_flowtable_destroy(void *ptr, void *arg)
-{
-	kfree(ptr);
-}
-
 static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 {
 	cancel_delayed_work_sync(&flowtable->data.gc_work);
 	kfree(flowtable->name);
-	rhashtable_free_and_destroy(&flowtable->data.rhashtable,
-				    nft_flowtable_destroy, NULL);
+	flowtable->data.type->free(&flowtable->data);
+	rhashtable_destroy(&flowtable->data.rhashtable);
 	module_put(flowtable->data.type->owner);
 }
 
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 4503b8dcf9c0..b65829b2be22 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -194,22 +194,6 @@ static struct nft_expr_type nft_flow_offload_type __read_mostly = {
 	.owner		= THIS_MODULE,
 };
 
-static void flow_offload_iterate_cleanup(struct flow_offload *flow, void *data)
-{
-	struct net_device *dev = data;
-
-	if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
-		return;
-
-	flow_offload_dead(flow);
-}
-
-static void nft_flow_offload_iterate_cleanup(struct nf_flowtable *flowtable,
-					     void *data)
-{
-	nf_flow_table_iterate(flowtable, flow_offload_iterate_cleanup, data);
-}
-
 static int flow_offload_netdev_event(struct notifier_block *this,
 				     unsigned long event, void *ptr)
 {
@@ -218,7 +202,7 @@ static int flow_offload_netdev_event(struct notifier_block *this,
 	if (event != NETDEV_DOWN)
 		return NOTIFY_DONE;
 
-	nft_flow_table_iterate(dev_net(dev), nft_flow_offload_iterate_cleanup, dev);
+	nf_flow_table_cleanup(dev_net(dev), dev);
 
 	return NOTIFY_DONE;
 }
@@ -246,14 +230,8 @@ register_expr:
 
 static void __exit nft_flow_offload_module_exit(void)
 {
-	struct net *net;
-
 	nft_unregister_expr(&nft_flow_offload_type);
 	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
-	rtnl_lock();
-	for_each_net(net)
-		nft_flow_table_iterate(net, nft_flow_offload_iterate_cleanup, NULL);
-	rtnl_unlock();
 }
 
 module_init(nft_flow_offload_module_init);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8fa4d37141a7..2f685ee1f9c8 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1008,7 +1008,12 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size)
 	if ((size >> PAGE_SHIFT) + 2 > totalram_pages)
 		return NULL;
 
-	info = kvmalloc(sz, GFP_KERNEL);
+	/* __GFP_NORETRY is not fully supported by kvmalloc but it should
+	 * work reasonably well if sz is too large and bail out rather
+	 * than shoot all processes down before realizing there is nothing
+	 * more to reclaim.
+	 */
+	info = kvmalloc(sz, GFP_KERNEL | __GFP_NORETRY);
 	if (!info)
 		return NULL;
 
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 498b54fd04d7..141c295191f6 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -39,23 +39,31 @@ static void xt_rateest_hash_insert(struct xt_rateest *est)
 	hlist_add_head(&est->list, &rateest_hash[h]);
 }
 
-struct xt_rateest *xt_rateest_lookup(const char *name)
+static struct xt_rateest *__xt_rateest_lookup(const char *name)
 {
 	struct xt_rateest *est;
 	unsigned int h;
 
 	h = xt_rateest_hash(name);
-	mutex_lock(&xt_rateest_mutex);
 	hlist_for_each_entry(est, &rateest_hash[h], list) {
 		if (strcmp(est->name, name) == 0) {
 			est->refcnt++;
-			mutex_unlock(&xt_rateest_mutex);
 			return est;
 		}
 	}
-	mutex_unlock(&xt_rateest_mutex);
+
 	return NULL;
 }
+
+struct xt_rateest *xt_rateest_lookup(const char *name)
+{
+	struct xt_rateest *est;
+
+	mutex_lock(&xt_rateest_mutex);
+	est = __xt_rateest_lookup(name);
+	mutex_unlock(&xt_rateest_mutex);
+	return est;
+}
 EXPORT_SYMBOL_GPL(xt_rateest_lookup);
 
 void xt_rateest_put(struct xt_rateest *est)
@@ -100,8 +108,10 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 
 	net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
 
-	est = xt_rateest_lookup(info->name);
+	mutex_lock(&xt_rateest_mutex);
+	est = __xt_rateest_lookup(info->name);
 	if (est) {
+		mutex_unlock(&xt_rateest_mutex);
 		/*
 		 * If estimator parameters are specified, they must match the
 		 * existing estimator.
@@ -139,11 +149,13 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 
 	info->est = est;
 	xt_rateest_hash_insert(est);
+	mutex_unlock(&xt_rateest_mutex);
 	return 0;
 
 err2:
 	kfree(est);
 err1:
+	mutex_unlock(&xt_rateest_mutex);
 	return ret;
 }
 
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 1db1ce59079f..891f4e7e8ea7 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -52,6 +52,7 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	}
 
+	info->priv = NULL;
 	if (info->has_path) {
 		cgrp = cgroup_get_from_path(info->path);
 		if (IS_ERR(cgrp)) {