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 your net tree:

1) Missing netlink attribute validation in nf_queue, uncovered by KASAN,
   from Eric Dumazet.

2) Use pointer to sysctl table, save us 192 bytes of memory per netns.
   Also from Eric.

3) Possible use-after-free when removing conntrack helper modules due
   to missing synchronize RCU call. From Taehee Yoo.

4) Fix corner case in systcl writes to nf_log that lead to appending
   data to uninitialized buffer, from Jann Horn.

5) Jann Horn says we may indefinitely block other users of nf_log_mutex
   if a userspace access in proc_dostring() blocked e.g. due to a
   userfaultfd.

6) Fix garbage collection race for unconfirmed conntrack entries,
   from Florian Westphal.
====================

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

include/net/net_namespace.h

@@ -128,6 +128,7 @@ struct net {
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	struct netns_nf_frag	nf_frag;
+	struct ctl_table_header *nf_frag_frags_hdr;
 #endif
 	struct sock		*nfnl;
 	struct sock		*nfnl_stash;

include/net/netns/ipv6.h

@@ -109,7 +109,6 @@ struct netns_ipv6 {
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 struct netns_nf_frag {
-	struct netns_sysctl_ipv6 sysctl;
 	struct netns_frags	frags;
 };
 #endif

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
 	if (hdr == NULL)
 		goto err_reg;
 
-	net->nf_frag.sysctl.frags_hdr = hdr;
+	net->nf_frag_frags_hdr = hdr;
 	return 0;
 
 err_reg:
@@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
 {
 	struct ctl_table *table;
 
-	table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
-	unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+	table = net->nf_frag_frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->nf_frag_frags_hdr);
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }

net/netfilter/nf_conncount.c

@@ -47,6 +47,8 @@ struct nf_conncount_tuple {
 	struct hlist_node		node;
 	struct nf_conntrack_tuple	tuple;
 	struct nf_conntrack_zone	zone;
+	int				cpu;
+	u32				jiffies32;
 };
 
 struct nf_conncount_rb {
@@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head,
 		return false;
 	conn->tuple = *tuple;
 	conn->zone = *zone;
+	conn->cpu = raw_smp_processor_id();
+	conn->jiffies32 = (u32)jiffies;
 	hlist_add_head(&conn->node, head);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
 
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+	const struct nf_conntrack_tuple_hash *found;
+	unsigned long a, b;
+	int cpu = raw_smp_processor_id();
+	__s32 age;
+
+	found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+	if (found)
+		return found;
+	b = conn->jiffies32;
+	a = (u32)jiffies;
+
+	/* conn might have been added just before by another cpu and
+	 * might still be unconfirmed.  In this case, nf_conntrack_find()
+	 * returns no result.  Thus only evict if this cpu added the
+	 * stale entry or if the entry is older than two jiffies.
+	 */
+	age = a - b;
+	if (conn->cpu == cpu || age >= 2) {
+		hlist_del(&conn->node);
+		kmem_cache_free(conncount_conn_cachep, conn);
+		return ERR_PTR(-ENOENT);
+	}
+
+	return ERR_PTR(-EAGAIN);
+}
+
 unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 				 const struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_zone *zone,
@@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn;
-	struct hlist_node *n;
 	struct nf_conn *found_ct;
+	struct hlist_node *n;
 	unsigned int length = 0;
 
 	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	hlist_for_each_entry_safe(conn, n, head, node) {
-		found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
-		if (found == NULL) {
-			hlist_del(&conn->node);
-			kmem_cache_free(conncount_conn_cachep, conn);
+		found = find_or_evict(net, conn);
+		if (IS_ERR(found)) {
+			/* Not found, but might be about to be confirmed */
+			if (PTR_ERR(found) == -EAGAIN) {
+				length++;
+				if (!tuple)
+					continue;
+
+				if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+				    nf_ct_zone_id(zone, zone->dir))
+					*addit = false;
+			}
 			continue;
 		}
 

net/netfilter/nf_conntrack_helper.c

@@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 
 	nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
 	nf_ct_iterate_destroy(unhelp, me);
+
+	/* Maybe someone has gotten the helper already when unhelp above.
+	 * So need to wait it.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 

net/netfilter/nf_log.c

@@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 	if (write) {
 		struct ctl_table tmp = *table;
 
+		/* proc_dostring() can append to existing strings, so we need to
+		 * initialize it as an empty string.
+		 */
+		buf[0] = '\0';
 		tmp.data = buf;
 		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
 		if (r)
@@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 		rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
 		mutex_unlock(&nf_log_mutex);
 	} else {
+		struct ctl_table tmp = *table;
+
+		tmp.data = buf;
 		mutex_lock(&nf_log_mutex);
 		logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
 		if (!logger)
-			table->data = "NONE";
+			strlcpy(buf, "NONE", sizeof(buf));
 		else
-			table->data = logger->name;
-		r = proc_dostring(table, write, buffer, lenp, ppos);
+			strlcpy(buf, logger->name, sizeof(buf));
 		mutex_unlock(&nf_log_mutex);
+		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
 	}
 
 	return r;

net/netfilter/nfnetlink_queue.c

@@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl,
 static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 	[NFQA_CFG_CMD]		= { .len = sizeof(struct nfqnl_msg_config_cmd) },
 	[NFQA_CFG_PARAMS]	= { .len = sizeof(struct nfqnl_msg_config_params) },
+	[NFQA_CFG_QUEUE_MAXLEN]	= { .type = NLA_U32 },
+	[NFQA_CFG_MASK]		= { .type = NLA_U32 },
+	[NFQA_CFG_FLAGS]	= { .type = NLA_U32 },
 };
 
 static const struct nf_queue_handler nfqh = {