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

Pablo Neira Ayuso says:

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

The following patchset contains large batch with Netfilter fixes for
your net tree, mostly due to syzbot report fixups and pr_err()
ratelimiting, more specifically, they are:

1) Get rid of superfluous unnecessary check in x_tables before vmalloc(),
   we don't hit BUG there anymore, patch from Michal Hock, suggested by
   Andrew Morton.

2) Race condition in proc file creation in ipt_CLUSTERIP, from Cong Wang.

3) Drop socket lock that results in circular locking dependency, patch
   from Paolo Abeni.

4) Drop packet if case of malformed blob that makes backpointer jump
   in x_tables, from Florian Westphal.

5) Fix refcount leak due to race in ipt_CLUSTERIP in
   clusterip_config_find_get(), from Cong Wang.

6) Several patches to ratelimit pr_err() for x_tables since this can be
   a problem where CAP_NET_ADMIN semantics can protect us in untrusted
   namespace, from Florian Westphal.

7) Missing .gitignore update for new autogenerated asn1 state machine
   for the SNMP NAT helper, from Zhu Lingshan.

8) Missing timer initialization in xt_LED, from Paolo Abeni.

9) Do not allow negative port range in NAT, also from Paolo.

10) Lock imbalance in the xt_hashlimit rate match mode, patch from
    Eric Dumazet.

11) Initialize workqueue before timer in the idletimer match,
    from Eric Dumazet.
====================

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

7 files changed, 33 insertions, 27 deletions

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 008be04ac1cc..9c41a0cef1a5 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1567,10 +1567,7 @@ int ip_getsockopt(struct sock *sk, int level,
 		if (get_user(len, optlen))
 			return -EFAULT;
 
-		lock_sock(sk);
-		err = nf_getsockopt(sk, PF_INET, optname, optval,
-				&len);
-		release_sock(sk);
+		err = nf_getsockopt(sk, PF_INET, optname, optval, &len);
 		if (err >= 0)
 			err = put_user(len, optlen);
 		return err;
@@ -1602,9 +1599,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname,
 		if (get_user(len, optlen))
 			return -EFAULT;
 
-		lock_sock(sk);
 		err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len);
-		release_sock(sk);
 		if (err >= 0)
 			err = put_user(len, optlen);
 		return err;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 4ffe302f9b82..e3e420f3ba7b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -252,6 +252,10 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 			}
 			if (table_base + v
 			    != arpt_next_entry(e)) {
+				if (unlikely(stackidx >= private->stacksize)) {
+					verdict = NF_DROP;
+					break;
+				}
 				jumpstack[stackidx++] = e;
 			}
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 9a71f3149507..e38395a8dcf2 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -330,8 +330,13 @@ ipt_do_table(struct sk_buff *skb,
 				continue;
 			}
 			if (table_base + v != ipt_next_entry(e) &&
-			    !(e->ip.flags & IPT_F_GOTO))
+			    !(e->ip.flags & IPT_F_GOTO)) {
+				if (unlikely(stackidx >= private->stacksize)) {
+					verdict = NF_DROP;
+					break;
+				}
 				jumpstack[stackidx++] = e;
+			}
 
 			e = get_entry(table_base, v);
 			continue;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 3a84a60f6b39..4b02ab39ebc5 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -107,12 +107,6 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
 
 	local_bh_disable();
 	if (refcount_dec_and_lock(&c->entries, &cn->lock)) {
-		list_del_rcu(&c->list);
-		spin_unlock(&cn->lock);
-		local_bh_enable();
-
-		unregister_netdevice_notifier(&c->notifier);
-
 		/* In case anyone still accesses the file, the open/close
 		 * functions are also incrementing the refcount on their own,
 		 * so it's safe to remove the entry even if it's in use. */
@@ -120,6 +114,12 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c)
 		if (cn->procdir)
 			proc_remove(c->pde);
 #endif
+		list_del_rcu(&c->list);
+		spin_unlock(&cn->lock);
+		local_bh_enable();
+
+		unregister_netdevice_notifier(&c->notifier);
+
 		return;
 	}
 	local_bh_enable();
@@ -154,8 +154,12 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 #endif
 		if (unlikely(!refcount_inc_not_zero(&c->refcount)))
 			c = NULL;
-		else if (entry)
-			refcount_inc(&c->entries);
+		else if (entry) {
+			if (unlikely(!refcount_inc_not_zero(&c->entries))) {
+				clusterip_config_put(c);
+				c = NULL;
+			}
+		}
 	}
 	rcu_read_unlock_bh();
 
diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c
index 270765236f5e..aaaf9a81fbc9 100644
--- a/net/ipv4/netfilter/ipt_ECN.c
+++ b/net/ipv4/netfilter/ipt_ECN.c
@@ -98,17 +98,15 @@ static int ecn_tg_check(const struct xt_tgchk_param *par)
 	const struct ipt_ECN_info *einfo = par->targinfo;
 	const struct ipt_entry *e = par->entryinfo;
 
-	if (einfo->operation & IPT_ECN_OP_MASK) {
-		pr_info("unsupported ECN operation %x\n", einfo->operation);
+	if (einfo->operation & IPT_ECN_OP_MASK)
 		return -EINVAL;
-	}
-	if (einfo->ip_ect & ~IPT_ECN_IP_MASK) {
-		pr_info("new ECT codepoint %x out of mask\n", einfo->ip_ect);
+
+	if (einfo->ip_ect & ~IPT_ECN_IP_MASK)
 		return -EINVAL;
-	}
+
 	if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) &&
 	    (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) {
-		pr_info("cannot use TCP operations on a non-tcp rule\n");
+		pr_info_ratelimited("cannot use operation on non-tcp rule\n");
 		return -EINVAL;
 	}
 	return 0;
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 8bd0d7b26632..e8bed3390e58 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -74,13 +74,13 @@ static int reject_tg_check(const struct xt_tgchk_param *par)
 	const struct ipt_entry *e = par->entryinfo;
 
 	if (rejinfo->with == IPT_ICMP_ECHOREPLY) {
-		pr_info("ECHOREPLY no longer supported.\n");
+		pr_info_ratelimited("ECHOREPLY no longer supported.\n");
 		return -EINVAL;
 	} else if (rejinfo->with == IPT_TCP_RESET) {
 		/* Must specify that it's a TCP packet */
 		if (e->ip.proto != IPPROTO_TCP ||
 		    (e->ip.invflags & XT_INV_PROTO)) {
-			pr_info("TCP_RESET invalid for non-tcp\n");
+			pr_info_ratelimited("TCP_RESET invalid for non-tcp\n");
 			return -EINVAL;
 		}
 	}
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 37fb9552e858..fd01f13c896a 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -105,14 +105,14 @@ static int rpfilter_check(const struct xt_mtchk_param *par)
 	const struct xt_rpfilter_info *info = par->matchinfo;
 	unsigned int options = ~XT_RPFILTER_OPTION_MASK;
 	if (info->flags & options) {
-		pr_info("unknown options encountered");
+		pr_info_ratelimited("unknown options\n");
 		return -EINVAL;
 	}
 
 	if (strcmp(par->table, "mangle") != 0 &&
 	    strcmp(par->table, "raw") != 0) {
-		pr_info("match only valid in the \'raw\' "
-			"or \'mangle\' tables, not \'%s\'.\n", par->table);
+		pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n",
+				    par->table);
 		return -EINVAL;
 	}