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 net:

1) Switch to RCU in x_tables to fix possible NULL pointer dereference,
from Subash Abhinov Kasiviswanathan.

2) Fix netlink dump of dynset timeouts later than 23 days.

3) Add comment for the indirect serialization of the nft commit mutex
with rtnl_mutex.

4) Remove bogus check for confirmed conntrack when matching on the
conntrack ID, from Brett Mastbergen.
====================

Signed-off-by: David S. Miller <[e-mail]>

include/linux/netfilter/x_tables.h

···
 	unsigned int valid_hooks;
 
 	/* Man behind the curtain... */
-	struct xt_table_info *private;
+	struct xt_table_info __rcu *private;
 
 	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
 	struct module *me;
···
 }
 
 struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
+
+struct xt_table_info
+*xt_table_get_private_protected(const struct xt_table *table);
 
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>

include/net/netfilter/nf_tables.h

···
 void nft_chain_route_fini(void);
 
 void nf_tables_trans_destroy_flush_work(void);
+
+int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result);
+__be64 nf_jiffies64_to_msecs(u64 input);
+
 #endif /* _NET_NF_TABLES_H */

net/ipv4/netfilter/arp_tables.c

···
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu     = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct arpt_entry **)private->jumpstack[cpu];
···
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	 * (other than comefrom, which userspace doesn't care
···
 	unsigned int off, num;
 	const struct arpt_entry *e;
 	struct xt_counters *counters;
-	struct xt_table_info *private = table->private;
+	struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	void *loc_cpu_entry;
 
···
 	t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
 	if (!IS_ERR(t)) {
 		struct arpt_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
···
 
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
···
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
···
 				       void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;

net/ipv4/netfilter/ip_tables.c

···
 	WARN_ON(!(table->valid_hooks & (1 << hook)));
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
···
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
···
 	unsigned int off, num;
 	const struct ipt_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	const void *loc_cpu_entry;
 
···
 	t = xt_request_find_table_lock(net, AF_INET, name);
 	if (!IS_ERR(t)) {
 		struct ipt_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
···
 
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
···
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
···
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;

net/ipv6/netfilter/ip6_tables.c

···
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
···
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
···
 	unsigned int off, num;
 	const struct ip6t_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	const void *loc_cpu_entry;
 
···
 	t = xt_request_find_table_lock(net, AF_INET6, name);
 	if (!IS_ERR(t)) {
 		struct ip6t_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
···
 
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		struct xt_table_info *private = t->private;
+		struct xt_table_info *private = xt_table_get_private_protected(t);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
···
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
···
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;

net/netfilter/nf_tables_api.c

···
 	}
 
 	nla_strlcpy(ifname, attr, IFNAMSIZ);
+	/* nf_tables_netdev_event() is called under rtnl_mutex, this is
+	 * indirectly serializing all the other holders of the commit_mutex with
+	 * the rtnl_mutex.
+	 */
 	dev = __dev_get_by_name(net, ifname);
 	if (!dev) {
 		err = -ENOENT;
···
 	return 0;
 }
 
-static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
+int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
 {
 	u64 ms = be64_to_cpu(nla_get_be64(nla));
 	u64 max = (u64)(~((u64)0));
···
 	return 0;
 }
 
-static __be64 nf_jiffies64_to_msecs(u64 input)
+__be64 nf_jiffies64_to_msecs(u64 input)
 {
 	return cpu_to_be64(jiffies64_to_msecs(input));
 }

net/netfilter/nft_ct.c

···
 	}
 #endif
 	case NFT_CT_ID:
-		if (!nf_ct_is_confirmed(ct))
-			goto err;
 		*dest = nf_ct_get_id(ct);
 		return;
 	default:

net/netfilter/nft_dynset.c

···
 	if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
-		timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
-						tb[NFTA_DYNSET_TIMEOUT])));
+
+		err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout);
+		if (err)
+			return err;
 	}
 
 	priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
···
 	if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
 		goto nla_put_failure;
 	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT,
-			 cpu_to_be64(jiffies_to_msecs(priv->timeout)),
+			 nf_jiffies64_to_msecs(priv->timeout),
 			 NFTA_DYNSET_PAD))
 		goto nla_put_failure;
 	if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))

net/netfilter/x_tables.c

···
 }
 EXPORT_SYMBOL(xt_counters_alloc);
 
+struct xt_table_info
+*xt_table_get_private_protected(const struct xt_table *table)
+{
+	return rcu_dereference_protected(table->private,
+					 mutex_is_locked(&xt[table->af].mutex));
+}
+EXPORT_SYMBOL(xt_table_get_private_protected);
+
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
···
 	      int *error)
 {
 	struct xt_table_info *private;
-	unsigned int cpu;
 	int ret;
 
 	ret = xt_jumpstack_alloc(newinfo);
···
 	}
 
 	/* Do the substitution. */
-	local_bh_disable();
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 
 	/* Check inside lock: is the old number correct? */
 	if (num_counters != private->number) {
 		pr_debug("num_counters != table->private->number (%u/%u)\n",
 			 num_counters, private->number);
-		local_bh_enable();
 		*error = -EAGAIN;
 		return NULL;
 	}
 
 	newinfo->initial_entries = private->initial_entries;
-	/*
-	 * Ensure contents of newinfo are visible before assigning to
-	 * private.
-	 */
-	smp_wmb();
-	table->private = newinfo;
 
-	/* make sure all cpus see new ->private value */
-	smp_wmb();
-
-	/*
-	 * Even though table entries have now been swapped, other CPU's
-	 * may still be using the old entries...
-	 */
-	local_bh_enable();
-
-	/* ... so wait for even xt_recseq on all cpus */
-	for_each_possible_cpu(cpu) {
-		seqcount_t *s = &per_cpu(xt_recseq, cpu);
-		u32 seq = raw_read_seqcount(s);
-
-		if (seq & 1) {
-			do {
-				cond_resched();
-				cpu_relax();
-			} while (seq == raw_read_seqcount(s));
-		}
-	}
+	rcu_assign_pointer(table->private, newinfo);
+	synchronize_rcu();
 
 	audit_log_nfcfg(table->name, table->af, private->number,
 			!private->number ? AUDIT_XT_OP_REGISTER :
···
 	}
 
 	/* Simplifies replace_table code. */
-	table->private = bootstrap;
+	rcu_assign_pointer(table->private, bootstrap);
 
 	if (!xt_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
 
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 	pr_debug("table->private->number = %u\n", private->number);
 
 	/* save number of initial entries */
···
 	struct xt_table_info *private;
 
 	mutex_lock(&xt[table->af].mutex);
-	private = table->private;
+	private = xt_table_get_private_protected(table);
+	RCU_INIT_POINTER(table->private, NULL);
 	list_del(&table->list);
 	mutex_unlock(&xt[table->af].mutex);
 	audit_log_nfcfg(table->name, table->af, private->number,