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

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter/IPVS updates for net-next,
they are:

1) Count pre-established connections as active in "least connection"
   schedulers such that pre-established connections to avoid overloading
   backend servers on peak demands, from Michal Kubecek via Simon Horman.

2) Address a race condition when resizing the conntrack table by caching
   the bucket size when fulling iterating over the hashtable in these
   three possible scenarios: 1) dump via /proc/net/nf_conntrack,
   2) unlinking userspace helper and 3) unlinking custom conntrack timeout.
   From Liping Zhang.

3) Revisit early_drop() path to perform lockless traversal on conntrack
   eviction under stress, use del_timer() as synchronization point to
   avoid two CPUs evicting the same entry, from Florian Westphal.

4) Move NAT hlist_head to nf_conn object, this simplifies the existing
   NAT extension and it doesn't increase size since recent patches to
   align nf_conn, from Florian.

5) Use rhashtable for the by-source NAT hashtable, also from Florian.

6) Don't allow --physdev-is-out from OUTPUT chain, just like
   --physdev-out is not either, from Hangbin Liu.

7) Automagically set on nf_conntrack counters if the user tries to
   match ct bytes/packets from nftables, from Liping Zhang.

8) Remove possible_net_t fields in nf_tables set objects since we just
   simply pass the net pointer to the backend set type implementations.

9) Fix possible off-by-one in h323, from Toby DiPasquale.

10) early_drop() may be called from ctnetlink patch, so we must hold
    rcu read size lock from them too, this amends Florian's patch #3
    coming in this batch, from Liping Zhang.

11) Use binary search to validate jump offset in x_tables, this
    addresses the O(n!) validation that was introduced recently
    resolve security issues with unpriviledge namespaces, from Florian.

12) Fix reference leak to connlabel in error path of nft_ct, from Zhang.

13) Three updates for nft_log: Fix log prefix leak in error path. Bail
    out on loglevel larger than debug in nft_log and set on the new
    NF_LOG_F_COPY_LEN flag when snaplen is specified. Again from Zhang.

14) Allow to filter rule dumps in nf_tables based on table and chain
    names.

15) Simplify connlabel to always use 128 bits to store labels and
    get rid of unused function in xt_connlabel, from Florian.

16) Replace set_expect_timeout() by mod_timer() from the h323 conntrack
    helper, by Gao Feng.

17) Put back x_tables module reference in nft_compat on error, from
    Liping Zhang.

18) Add a reference count to the x_tables extensions cache in
    nft_compat, so we can remove them when unused and avoid a crash
    if the extensions are rmmod, again from Zhang.
====================

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

3 files changed, 59 insertions, 47 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index c8dd9e26b185..b31df597fd37 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -299,23 +299,12 @@ static inline bool unconditional(const struct arpt_entry *e)
 	       memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
 }
 
-static bool find_jump_target(const struct xt_table_info *t,
-			     const struct arpt_entry *target)
-{
-	struct arpt_entry *iter;
-
-	xt_entry_foreach(iter, t->entries, t->size) {
-		 if (iter == target)
-			return true;
-	}
-	return false;
-}
-
 /* Figures out from what hook each rule can be called: returns 0 if
  * there are loops.  Puts hook bitmask in comefrom.
  */
 static int mark_source_chains(const struct xt_table_info *newinfo,
-			      unsigned int valid_hooks, void *entry0)
+			      unsigned int valid_hooks, void *entry0,
+			      unsigned int *offsets)
 {
 	unsigned int hook;
 
@@ -388,10 +377,11 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					   XT_STANDARD_TARGET) == 0 &&
 				    newpos >= 0) {
 					/* This a jump; chase it. */
+					if (!xt_find_jump_offset(offsets, newpos,
+								 newinfo->number))
+						return 0;
 					e = (struct arpt_entry *)
 						(entry0 + newpos);
-					if (!find_jump_target(newinfo, e))
-						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
@@ -543,6 +533,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 			   const struct arpt_replace *repl)
 {
 	struct arpt_entry *iter;
+	unsigned int *offsets;
 	unsigned int i;
 	int ret = 0;
 
@@ -555,6 +546,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		newinfo->underflow[i] = 0xFFFFFFFF;
 	}
 
+	offsets = xt_alloc_entry_offsets(newinfo->number);
+	if (!offsets)
+		return -ENOMEM;
 	i = 0;
 
 	/* Walk through entries, checking offsets. */
@@ -565,17 +559,20 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 						 repl->underflow,
 						 repl->valid_hooks);
 		if (ret != 0)
-			break;
+			goto out_free;
+		if (i < repl->num_entries)
+			offsets[i] = (void *)iter - entry0;
 		++i;
 		if (strcmp(arpt_get_target(iter)->u.user.name,
 		    XT_ERROR_TARGET) == 0)
 			++newinfo->stacksize;
 	}
 	if (ret != 0)
-		return ret;
+		goto out_free;
 
+	ret = -EINVAL;
 	if (i != repl->num_entries)
-		return -EINVAL;
+		goto out_free;
 
 	/* Check hooks all assigned */
 	for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
@@ -583,13 +580,16 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 		if (!(repl->valid_hooks & (1 << i)))
 			continue;
 		if (newinfo->hook_entry[i] == 0xFFFFFFFF)
-			return -EINVAL;
+			goto out_free;
 		if (newinfo->underflow[i] == 0xFFFFFFFF)
-			return -EINVAL;
+			goto out_free;
 	}
 
-	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
-		return -ELOOP;
+	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+		ret = -ELOOP;
+		goto out_free;
+	}
+	kvfree(offsets);
 
 	/* Finally, each sanity check must pass */
 	i = 0;
@@ -610,6 +610,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
 	}
 
 	return ret;
+ out_free:
+	kvfree(offsets);
+	return ret;
 }
 
 static void get_counters(const struct xt_table_info *t,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f0df66f54ce6..f993545a3373 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -373,23 +373,12 @@ ipt_do_table(struct sk_buff *skb,
 	else return verdict;
 }
 
-static bool find_jump_target(const struct xt_table_info *t,
-			     const struct ipt_entry *target)
-{
-	struct ipt_entry *iter;
-
-	xt_entry_foreach(iter, t->entries, t->size) {
-		 if (iter == target)
-			return true;
-	}
-	return false;
-}
-
 /* Figures out from what hook each rule can be called: returns 0 if
    there are loops.  Puts hook bitmask in comefrom. */
 static int
 mark_source_chains(const struct xt_table_info *newinfo,
-		   unsigned int valid_hooks, void *entry0)
+		   unsigned int valid_hooks, void *entry0,
+		   unsigned int *offsets)
 {
 	unsigned int hook;
 
@@ -458,10 +447,11 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					   XT_STANDARD_TARGET) == 0 &&
 				    newpos >= 0) {
 					/* This a jump; chase it. */
+					if (!xt_find_jump_offset(offsets, newpos,
+								 newinfo->number))
+						return 0;
 					e = (struct ipt_entry *)
 						(entry0 + newpos);
-					if (!find_jump_target(newinfo, e))
-						return 0;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;
@@ -694,6 +684,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		const struct ipt_replace *repl)
 {
 	struct ipt_entry *iter;
+	unsigned int *offsets;
 	unsigned int i;
 	int ret = 0;
 
@@ -706,6 +697,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		newinfo->underflow[i] = 0xFFFFFFFF;
 	}
 
+	offsets = xt_alloc_entry_offsets(newinfo->number);
+	if (!offsets)
+		return -ENOMEM;
 	i = 0;
 	/* Walk through entries, checking offsets. */
 	xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -715,15 +709,18 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 						 repl->underflow,
 						 repl->valid_hooks);
 		if (ret != 0)
-			return ret;
+			goto out_free;
+		if (i < repl->num_entries)
+			offsets[i] = (void *)iter - entry0;
 		++i;
 		if (strcmp(ipt_get_target(iter)->u.user.name,
 		    XT_ERROR_TARGET) == 0)
 			++newinfo->stacksize;
 	}
 
+	ret = -EINVAL;
 	if (i != repl->num_entries)
-		return -EINVAL;
+		goto out_free;
 
 	/* Check hooks all assigned */
 	for (i = 0; i < NF_INET_NUMHOOKS; i++) {
@@ -731,13 +728,16 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (!(repl->valid_hooks & (1 << i)))
 			continue;
 		if (newinfo->hook_entry[i] == 0xFFFFFFFF)
-			return -EINVAL;
+			goto out_free;
 		if (newinfo->underflow[i] == 0xFFFFFFFF)
-			return -EINVAL;
+			goto out_free;
 	}
 
-	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
-		return -ELOOP;
+	if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+		ret = -ELOOP;
+		goto out_free;
+	}
+	kvfree(offsets);
 
 	/* Finally, each sanity check must pass */
 	i = 0;
@@ -758,6 +758,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 	}
 
 	return ret;
+ out_free:
+	kvfree(offsets);
+	return ret;
 }
 
 static void
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index c6f3c406f707..63923710f325 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -26,6 +26,8 @@
 
 struct ct_iter_state {
 	struct seq_net_private p;
+	struct hlist_nulls_head *hash;
+	unsigned int htable_size;
 	unsigned int bucket;
 };
 
@@ -35,10 +37,10 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 	struct hlist_nulls_node *n;
 
 	for (st->bucket = 0;
-	     st->bucket < nf_conntrack_htable_size;
+	     st->bucket < st->htable_size;
 	     st->bucket++) {
 		n = rcu_dereference(
-			hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
+			hlist_nulls_first_rcu(&st->hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -53,11 +55,11 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
 	head = rcu_dereference(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
-			if (++st->bucket >= nf_conntrack_htable_size)
+			if (++st->bucket >= st->htable_size)
 				return NULL;
 		}
 		head = rcu_dereference(
-			hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
+			hlist_nulls_first_rcu(&st->hash[st->bucket]));
 	}
 	return head;
 }
@@ -75,7 +77,11 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
 static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
+	struct ct_iter_state *st = seq->private;
+
 	rcu_read_lock();
+
+	nf_conntrack_get_ht(&st->hash, &st->htable_size);
 	return ct_get_idx(seq, *pos);
 }