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

Pablo Neira Ayuso says:

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

The following patchset contains Netfilter fixes for net:

1) refcount_inc_not_zero() is not semantically equivalent to
   atomic_int_not_zero(), from Florian Westphal. My understanding was
   that refcount_*() API provides a wrapper to easier debugging of
   reference count leaks, however, there are semantic differences
   between these two APIs, where refcount_inc_not_zero() needs a barrier.
   Reason for this subtle difference to me is unknown.

2) packet logging is not correct for ARP and IP packets, from the
   ARP family and netdev/egress respectively. Use skb_network_offset()
   to reach the headers accordingly.

3) set element extension length have been growing over time, replace
   a BUG_ON by EINVAL which might be triggerable from userspace.
====================

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

5 files changed, 81 insertions, 25 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 082a2fd8d85b..369aeabb94fe 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -729,6 +729,9 @@ static void nf_ct_gc_expired(struct nf_conn *ct)
 	if (!refcount_inc_not_zero(&ct->ct_general.use))
 		return;
 
+	/* load ->status after refcount increase */
+	smp_acquire__after_ctrl_dep();
+
 	if (nf_ct_should_gc(ct))
 		nf_ct_kill(ct);
 
@@ -795,6 +798,9 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
 		 */
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		if (likely(refcount_inc_not_zero(&ct->ct_general.use))) {
+			/* re-check key after refcount */
+			smp_acquire__after_ctrl_dep();
+
 			if (likely(nf_ct_key_equal(h, tuple, zone, net)))
 				goto found;
 
@@ -1387,6 +1393,9 @@ static unsigned int early_drop_list(struct net *net,
 		if (!refcount_inc_not_zero(&tmp->ct_general.use))
 			continue;
 
+		/* load ->ct_net and ->status after refcount increase */
+		smp_acquire__after_ctrl_dep();
+
 		/* kill only if still in same netns -- might have moved due to
 		 * SLAB_TYPESAFE_BY_RCU rules.
 		 *
@@ -1536,6 +1545,9 @@ static void gc_worker(struct work_struct *work)
 			if (!refcount_inc_not_zero(&tmp->ct_general.use))
 				continue;
 
+			/* load ->status after refcount increase */
+			smp_acquire__after_ctrl_dep();
+
 			if (gc_worker_skip_ct(tmp)) {
 				nf_ct_put(tmp);
 				continue;
@@ -1775,6 +1787,16 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	if (!exp)
 		__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
 
+	/* Other CPU might have obtained a pointer to this object before it was
+	 * released.  Because refcount is 0, refcount_inc_not_zero() will fail.
+	 *
+	 * After refcount_set(1) it will succeed; ensure that zeroing of
+	 * ct->status and the correct ct->net pointer are visible; else other
+	 * core might observe CONFIRMED bit which means the entry is valid and
+	 * in the hash table, but its not (anymore).
+	 */
+	smp_wmb();
+
 	/* Now it is going to be associated with an sk_buff, set refcount to 1. */
 	refcount_set(&ct->ct_general.use, 1);
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 722af5e309ba..f5905b5201a7 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1203,6 +1203,7 @@ restart:
 					   hnnode) {
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (nf_ct_is_expired(ct)) {
+				/* need to defer nf_ct_kill() until lock is released */
 				if (i < ARRAY_SIZE(nf_ct_evict) &&
 				    refcount_inc_not_zero(&ct->ct_general.use))
 					nf_ct_evict[i++] = ct;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 6ad7bbc90d38..05895878610c 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -306,6 +306,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use)))
 		return 0;
 
+	/* load ->status after refcount increase */
+	smp_acquire__after_ctrl_dep();
+
 	if (nf_ct_should_gc(ct)) {
 		nf_ct_kill(ct);
 		goto release;
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index 77bcb10fc586..cb894f0d63e9 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -67,7 +67,7 @@ dump_arp_packet(struct nf_log_buf *m,
 	unsigned int logflags;
 	struct arphdr _arph;
 
-	ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
+	ah = skb_header_pointer(skb, nhoff, sizeof(_arph), &_arph);
 	if (!ah) {
 		nf_log_buf_add(m, "TRUNCATED");
 		return;
@@ -96,7 +96,7 @@ dump_arp_packet(struct nf_log_buf *m,
 	    ah->ar_pln != sizeof(__be32))
 		return;
 
-	ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp);
+	ap = skb_header_pointer(skb, nhoff + sizeof(_arph), sizeof(_arpp), &_arpp);
 	if (!ap) {
 		nf_log_buf_add(m, " INCOMPLETE [%zu bytes]",
 			       skb->len - sizeof(_arph));
@@ -149,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
 				  prefix);
-	dump_arp_packet(m, loginfo, skb, 0);
+	dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
 }
@@ -850,7 +850,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 	if (in)
 		dump_mac_header(m, loginfo, skb);
 
-	dump_ipv4_packet(net, m, loginfo, skb, 0);
+	dump_ipv4_packet(net, m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d6b59beab3a9..646d5fd53604 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5833,8 +5833,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL))
 		return -EINVAL;
 
-	if (flags != 0)
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+	if (flags != 0) {
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+		if (err < 0)
+			return err;
+	}
 
 	if (set->flags & NFT_SET_MAP) {
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
@@ -5943,7 +5946,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			goto err_set_elem_expr;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		if (err < 0)
+			goto err_parse_key;
 	}
 
 	if (nla[NFTA_SET_ELEM_KEY_END]) {
@@ -5952,22 +5957,31 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			goto err_parse_key;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		if (err < 0)
+			goto err_parse_key_end;
 	}
 
 	if (timeout > 0) {
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
-		if (timeout != set->timeout)
-			nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
+		if (err < 0)
+			goto err_parse_key_end;
+
+		if (timeout != set->timeout) {
+			err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+			if (err < 0)
+				goto err_parse_key_end;
+		}
 	}
 
 	if (num_exprs) {
 		for (i = 0; i < num_exprs; i++)
 			size += expr_array[i]->ops->size;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
-				       sizeof(struct nft_set_elem_expr) +
-				       size);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
+					     sizeof(struct nft_set_elem_expr) + size);
+		if (err < 0)
+			goto err_parse_key_end;
 	}
 
 	if (nla[NFTA_SET_ELEM_OBJREF] != NULL) {
@@ -5982,7 +5996,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			err = PTR_ERR(obj);
 			goto err_parse_key_end;
 		}
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
+		if (err < 0)
+			goto err_parse_key_end;
 	}
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
@@ -6016,7 +6032,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 							  NFT_VALIDATE_NEED);
 		}
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len);
+		if (err < 0)
+			goto err_parse_data;
 	}
 
 	/* The full maximum length of userdata can exceed the maximum
@@ -6026,9 +6044,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	ulen = 0;
 	if (nla[NFTA_SET_ELEM_USERDATA] != NULL) {
 		ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]);
-		if (ulen > 0)
-			nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
-					       ulen);
+		if (ulen > 0) {
+			err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA,
+						     ulen);
+			if (err < 0)
+				goto err_parse_data;
+		}
 	}
 
 	err = -ENOMEM;
@@ -6256,8 +6277,11 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 
 	nft_set_ext_prepare(&tmpl);
 
-	if (flags != 0)
-		nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+	if (flags != 0) {
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
+		if (err < 0)
+			return err;
+	}
 
 	if (nla[NFTA_SET_ELEM_KEY]) {
 		err = nft_setelem_parse_key(ctx, set, &elem.key.val,
@@ -6265,16 +6289,20 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			return err;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen);
+		if (err < 0)
+			goto fail_elem;
 	}
 
 	if (nla[NFTA_SET_ELEM_KEY_END]) {
 		err = nft_setelem_parse_key(ctx, set, &elem.key_end.val,
 					    nla[NFTA_SET_ELEM_KEY_END]);
 		if (err < 0)
-			return err;
+			goto fail_elem;
 
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen);
+		if (err < 0)
+			goto fail_elem_key_end;
 	}
 
 	err = -ENOMEM;
@@ -6282,7 +6310,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 				      elem.key_end.val.data, NULL, 0, 0,
 				      GFP_KERNEL_ACCOUNT);
 	if (elem.priv == NULL)
-		goto fail_elem;
+		goto fail_elem_key_end;
 
 	ext = nft_set_elem_ext(set, elem.priv);
 	if (flags)
@@ -6306,6 +6334,8 @@ fail_ops:
 	kfree(trans);
 fail_trans:
 	kfree(elem.priv);
+fail_elem_key_end:
+	nft_data_release(&elem.key_end.val, NFT_DATA_VALUE);
 fail_elem:
 	nft_data_release(&elem.key.val, NFT_DATA_VALUE);
 	return err;