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

Pablo Neira Ayuso says:

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

The following patchset contains accumulated Netfilter fixes for your
net tree:

1) Ensure quota dump and reset happens iff we can deliver numbers to
   userspace.

2) Silence splat on incorrect use of smp_processor_id() from nft_queue.

3) Fix an out-of-bound access reported by KASAN in
   nf_tables_rule_destroy(), patch from Florian Westphal.

4) Fix layer 4 checksum mangling in the nf_tables payload expression
   with IPv6.

5) Fix a race in the CLUSTERIP target from control plane path when two
   threads run to add a new configuration object. Serialize invocations
   of clusterip_config_init() using spin_lock. From Xin Long.

6) Call br_nf_pre_routing_finish_bridge_finish() once we are done with
   the br_nf_pre_routing_finish() hook. From Artur Molchanov.
====================

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

net/bridge/br_netfilter_hooks.c

@@ -399,7 +399,7 @@ bridged_dnat:
 				br_nf_hook_thresh(NF_BR_PRE_ROUTING,
 						  net, sk, skb, skb->dev,
 						  NULL,
-						  br_nf_pre_routing_finish);
+						  br_nf_pre_routing_finish_bridge);
 				return 0;
 			}
 			ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);

net/ipv4/netfilter/ipt_CLUSTERIP.c

@@ -144,7 +144,7 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 	rcu_read_lock_bh();
 	c = __clusterip_config_find(net, clusterip);
 	if (c) {
-		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
+		if (!c->pde || unlikely(!atomic_inc_not_zero(&c->refcount)))
 			c = NULL;
 		else if (entry)
 			atomic_inc(&c->entries);
@@ -166,14 +166,15 @@ clusterip_config_init_nodelist(struct clusterip_config *c,
 
 static struct clusterip_config *
 clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
-			struct net_device *dev)
+		      struct net_device *dev)
 {
+	struct net *net = dev_net(dev);
 	struct clusterip_config *c;
-	struct clusterip_net *cn = net_generic(dev_net(dev), clusterip_net_id);
+	struct clusterip_net *cn = net_generic(net, clusterip_net_id);
 
 	c = kzalloc(sizeof(*c), GFP_ATOMIC);
 	if (!c)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	c->dev = dev;
 	c->clusterip = ip;
@@ -185,6 +186,17 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 	atomic_set(&c->refcount, 1);
 	atomic_set(&c->entries, 1);
 
+	spin_lock_bh(&cn->lock);
+	if (__clusterip_config_find(net, ip)) {
+		spin_unlock_bh(&cn->lock);
+		kfree(c);
+
+		return ERR_PTR(-EBUSY);
+	}
+
+	list_add_rcu(&c->list, &cn->configs);
+	spin_unlock_bh(&cn->lock);
+
 #ifdef CONFIG_PROC_FS
 	{
 		char buffer[16];
@@ -195,16 +207,16 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 					  cn->procdir,
 					  &clusterip_proc_fops, c);
 		if (!c->pde) {
+			spin_lock_bh(&cn->lock);
+			list_del_rcu(&c->list);
+			spin_unlock_bh(&cn->lock);
 			kfree(c);
-			return NULL;
+
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 #endif
 
-	spin_lock_bh(&cn->lock);
-	list_add_rcu(&c->list, &cn->configs);
-	spin_unlock_bh(&cn->lock);
-
 	return c;
 }
 
@@ -410,9 +422,9 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par)
 
 			config = clusterip_config_init(cipinfo,
 							e->ip.dst.s_addr, dev);
-			if (!config) {
+			if (IS_ERR(config)) {
 				dev_put(dev);
-				return -ENOMEM;
+				return PTR_ERR(config);
 			}
 			dev_mc_add(config->dev, config->clustermac);
 		}

net/netfilter/nf_tables_api.c

@@ -2115,7 +2115,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 * is called on error from nf_tables_newrule().
 	 */
 	expr = nft_expr_first(rule);
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (expr != nft_expr_last(rule) && expr->ops) {
 		nf_tables_expr_destroy(ctx, expr);
 		expr = nft_expr_next(expr);
 	}

net/netfilter/nft_payload.c

@@ -250,6 +250,22 @@ static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt,
 	return 0;
 }
 
+static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src,
+				 __wsum fsum, __wsum tsum, int csum_offset)
+{
+	__sum16 sum;
+
+	if (skb_copy_bits(skb, csum_offset, &sum, sizeof(sum)) < 0)
+		return -1;
+
+	nft_csum_replace(&sum, fsum, tsum);
+	if (!skb_make_writable(skb, csum_offset + sizeof(sum)) ||
+	    skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0)
+		return -1;
+
+	return 0;
+}
+
 static void nft_payload_set_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
@@ -259,7 +275,6 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	const u32 *src = &regs->data[priv->sreg];
 	int offset, csum_offset;
 	__wsum fsum, tsum;
-	__sum16 sum;
 
 	switch (priv->base) {
 	case NFT_PAYLOAD_LL_HEADER:
@@ -282,18 +297,14 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	csum_offset = offset + priv->csum_offset;
 	offset += priv->offset;
 
-	if (priv->csum_type == NFT_PAYLOAD_CSUM_INET &&
+	if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) &&
 	    (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER ||
 	     skb->ip_summed != CHECKSUM_PARTIAL)) {
-		if (skb_copy_bits(skb, csum_offset, &sum, sizeof(sum)) < 0)
-			goto err;
-
 		fsum = skb_checksum(skb, offset, priv->len, 0);
 		tsum = csum_partial(src, priv->len, 0);
-		nft_csum_replace(&sum, fsum, tsum);
 
-		if (!skb_make_writable(skb, csum_offset + sizeof(sum)) ||
-		    skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0)
+		if (priv->csum_type == NFT_PAYLOAD_CSUM_INET &&
+		    nft_payload_csum_inet(skb, src, fsum, tsum, csum_offset))
 			goto err;
 
 		if (priv->csum_flags &&

net/netfilter/nft_queue.c

@@ -38,7 +38,7 @@ static void nft_queue_eval(const struct nft_expr *expr,
 
 	if (priv->queues_total > 1) {
 		if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) {
-			int cpu = smp_processor_id();
+			int cpu = raw_smp_processor_id();
 
 			queue = priv->queuenum + cpu % priv->queues_total;
 		} else {

net/netfilter/nft_quota.c

@@ -110,30 +110,32 @@ static int nft_quota_obj_init(const struct nlattr * const tb[],
 static int nft_quota_do_dump(struct sk_buff *skb, struct nft_quota *priv,
 			     bool reset)
 {
+	u64 consumed, consumed_cap;
 	u32 flags = priv->flags;
-	u64 consumed;
-
-	if (reset) {
-		consumed = atomic64_xchg(&priv->consumed, 0);
-		if (test_and_clear_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags))
-			flags |= NFT_QUOTA_F_DEPLETED;
-	} else {
-		consumed = atomic64_read(&priv->consumed);
-	}
 
 	/* Since we inconditionally increment consumed quota for each packet
 	 * that we see, don't go over the quota boundary in what we send to
 	 * userspace.
 	 */
-	if (consumed > priv->quota)
-		consumed = priv->quota;
+	consumed = atomic64_read(&priv->consumed);
+	if (consumed >= priv->quota) {
+		consumed_cap = priv->quota;
+		flags |= NFT_QUOTA_F_DEPLETED;
+	} else {
+		consumed_cap = consumed;
+	}
 
 	if (nla_put_be64(skb, NFTA_QUOTA_BYTES, cpu_to_be64(priv->quota),
 			 NFTA_QUOTA_PAD) ||
-	    nla_put_be64(skb, NFTA_QUOTA_CONSUMED, cpu_to_be64(consumed),
+	    nla_put_be64(skb, NFTA_QUOTA_CONSUMED, cpu_to_be64(consumed_cap),
 			 NFTA_QUOTA_PAD) ||
 	    nla_put_be32(skb, NFTA_QUOTA_FLAGS, htonl(flags)))
 		goto nla_put_failure;
+
+	if (reset) {
+		atomic64_sub(consumed, &priv->consumed);
+		clear_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags);
+	}
 	return 0;
 
 nla_put_failure: