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 your net-next
tree. This batch comes with more input sanitization for xtables to
address bug reports from fuzzers, preparation works to the flowtable
infrastructure and assorted updates. In no particular order, they are:

1) Make sure userspace provides a valid standard target verdict, from
   Florian Westphal.

2) Sanitize error target size, also from Florian.

3) Validate that last rule in basechain matches underflow/policy since
   userspace assumes this when decoding the ruleset blob that comes
   from the kernel, from Florian.

4) Consolidate hook entry checks through xt_check_table_hooks(),
   patch from Florian.

5) Cap ruleset allocations at 512 mbytes, 134217728 rules and reject
   very large compat offset arrays, so we have a reasonable upper limit
   and fuzzers don't exercise the oom-killer. Patches from Florian.

6) Several WARN_ON checks on xtables mutex helper, from Florian.

7) xt_rateest now has a hashtable per net, from Cong Wang.

8) Consolidate counter allocation in xt_counters_alloc(), from Florian.

9) Earlier xt_table_unlock() call in {ip,ip6,arp,eb}tables, patch
   from Xin Long.

10) Set FLOW_OFFLOAD_DIR_* to IP_CT_DIR_* definitions, patch from
    Felix Fietkau.

11) Consolidate code through flow_offload_fill_dir(), also from Felix.

12) Inline ip6_dst_mtu_forward() just like ip_dst_mtu_maybe_forward()
    to remove a dependency with flowtable and ipv6.ko, from Felix.

13) Cache mtu size in flow_offload_tuple object, this is safe for
    forwarding as f87c10a8aa1e describes, from Felix.

14) Rename nf_flow_table.c to nf_flow_table_core.o, to simplify too
    modular infrastructure, from Felix.

15) Add rt0, rt2 and rt4 IPv6 routing extension support, patch from
    Ahmed Abdelsalam.

16) Remove unused parameter in nf_conncount_count(), from Yi-Hung Wei.

17) Support for counting only to nf_conncount infrastructure, patch
    from Yi-Hung Wei.

18) Add strict NFT_CT_{SRC_IP,DST_IP,SRC_IP6,DST_IP6} key datatypes
    to nft_ct.

19) Use boolean as return value from ipt_ah and from IPVS too, patch
    from Gustavo A. R. Silva.

20) Remove useless parameters in nfnl_acct_overquota() and
    nf_conntrack_broadcast_help(), from Taehee Yoo.

21) Use ipv6_addr_is_multicast() from xt_cluster, also from Taehee Yoo.

22) Statify nf_tables_obj_lookup_byhandle, patch from Fengguang Wu.

23) Fix typo in xt_limit, from Geert Uytterhoeven.

24) Do no use VLAs in Netfilter code, again from Gustavo.

25) Use ADD_COUNTER from ebtables, from Taehee Yoo.

26) Bitshift support for CONNMARK and MARK targets, from Jack Ma.

27) Use pr_*() and add pr_fmt(), from Arushi Singhal.

28) Add synproxy support to ctnetlink.

29) ICMP type and IGMP matching support for ebtables, patches from
    Matthias Schiffer.

30) Support for the revision infrastructure to ebtables, from
    Bernie Harris.

31) String match support for ebtables, also from Bernie.

32) Documentation for the new flowtable infrastructure.

33) Use generic comparison functions in ebt_stp, from Joe Perches.

34) Demodularize filter chains in nftables.

35) Register conntrack hooks in case nftables NAT chain is added.

36) Merge assignments with return in a couple of spots in the
    Netfilter codebase, also from Arushi.

37) Document that xtables percpu counters are stored in the same
    memory area, from Ben Hutchings.

38) Revert mark_source_chains() sanity checks that break existing
    rulesets, from Florian Westphal.

39) Use is_zero_ether_addr() in the ipset codebase, from Joe Perches.
====================

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

1 files changed, 174 insertions, 17 deletions

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 4aa01c90e9d1ed..71325fef647da7 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -40,6 +40,7 @@ MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
 MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
 
 #define XT_PCPU_BLOCK_SIZE 4096
+#define XT_MAX_TABLE_SIZE	(512 * 1024 * 1024)
 
 struct compat_delta {
 	unsigned int offset; /* offset in kernel */
@@ -548,19 +549,104 @@ static int xt_check_entry_match(const char *match, const char *target,
 	return 0;
 }
 
+/** xt_check_table_hooks - check hook entry points are sane
+ *
+ * @info xt_table_info to check
+ * @valid_hooks - hook entry points that we can enter from
+ *
+ * Validates that the hook entry and underflows points are set up.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks)
+{
+	const char *err = "unsorted underflow";
+	unsigned int i, max_uflow, max_entry;
+	bool check_hooks = false;
+
+	BUILD_BUG_ON(ARRAY_SIZE(info->hook_entry) != ARRAY_SIZE(info->underflow));
+
+	max_entry = 0;
+	max_uflow = 0;
+
+	for (i = 0; i < ARRAY_SIZE(info->hook_entry); i++) {
+		if (!(valid_hooks & (1 << i)))
+			continue;
+
+		if (info->hook_entry[i] == 0xFFFFFFFF)
+			return -EINVAL;
+		if (info->underflow[i] == 0xFFFFFFFF)
+			return -EINVAL;
+
+		if (check_hooks) {
+			if (max_uflow > info->underflow[i])
+				goto error;
+
+			if (max_uflow == info->underflow[i]) {
+				err = "duplicate underflow";
+				goto error;
+			}
+			if (max_entry > info->hook_entry[i]) {
+				err = "unsorted entry";
+				goto error;
+			}
+			if (max_entry == info->hook_entry[i]) {
+				err = "duplicate entry";
+				goto error;
+			}
+		}
+		max_entry = info->hook_entry[i];
+		max_uflow = info->underflow[i];
+		check_hooks = true;
+	}
+
+	return 0;
+error:
+	pr_err_ratelimited("%s at hook %d\n", err, i);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(xt_check_table_hooks);
+
+static bool verdict_ok(int verdict)
+{
+	if (verdict > 0)
+		return true;
+
+	if (verdict < 0) {
+		int v = -verdict - 1;
+
+		if (verdict == XT_RETURN)
+			return true;
+
+		switch (v) {
+		case NF_ACCEPT: return true;
+		case NF_DROP: return true;
+		case NF_QUEUE: return true;
+		default:
+			break;
+		}
+
+		return false;
+	}
+
+	return false;
+}
+
+static bool error_tg_ok(unsigned int usersize, unsigned int kernsize,
+			const char *msg, unsigned int msglen)
+{
+	return usersize == kernsize && strnlen(msg, msglen) < msglen;
+}
+
 #ifdef CONFIG_COMPAT
 int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
 {
 	struct xt_af *xp = &xt[af];
 
-	if (!xp->compat_tab) {
-		if (!xp->number)
-			return -EINVAL;
-		xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number);
-		if (!xp->compat_tab)
-			return -ENOMEM;
-		xp->cur = 0;
-	}
+	WARN_ON(!mutex_is_locked(&xt[af].compat_mutex));
+
+	if (WARN_ON(!xp->compat_tab))
+		return -ENOMEM;
 
 	if (xp->cur >= xp->number)
 		return -EINVAL;
@@ -576,6 +662,8 @@ EXPORT_SYMBOL_GPL(xt_compat_add_offset);
 
 void xt_compat_flush_offsets(u_int8_t af)
 {
+	WARN_ON(!mutex_is_locked(&xt[af].compat_mutex));
+
 	if (xt[af].compat_tab) {
 		vfree(xt[af].compat_tab);
 		xt[af].compat_tab = NULL;
@@ -603,10 +691,30 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
 }
 EXPORT_SYMBOL_GPL(xt_compat_calc_jump);
 
-void xt_compat_init_offsets(u_int8_t af, unsigned int number)
+int xt_compat_init_offsets(u8 af, unsigned int number)
 {
+	size_t mem;
+
+	WARN_ON(!mutex_is_locked(&xt[af].compat_mutex));
+
+	if (!number || number > (INT_MAX / sizeof(struct compat_delta)))
+		return -EINVAL;
+
+	if (WARN_ON(xt[af].compat_tab))
+		return -EINVAL;
+
+	mem = sizeof(struct compat_delta) * number;
+	if (mem > XT_MAX_TABLE_SIZE)
+		return -ENOMEM;
+
+	xt[af].compat_tab = vmalloc(mem);
+	if (!xt[af].compat_tab)
+		return -ENOMEM;
+
 	xt[af].number = number;
 	xt[af].cur = 0;
+
+	return 0;
 }
 EXPORT_SYMBOL(xt_compat_init_offsets);
 
@@ -684,6 +792,11 @@ struct compat_xt_standard_target {
 	compat_uint_t verdict;
 };
 
+struct compat_xt_error_target {
+	struct compat_xt_entry_target t;
+	char errorname[XT_FUNCTION_MAXNAMELEN];
+};
+
 int xt_compat_check_entry_offsets(const void *base, const char *elems,
 				  unsigned int target_offset,
 				  unsigned int next_offset)
@@ -705,9 +818,21 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems,
 	if (target_offset + t->u.target_size > next_offset)
 		return -EINVAL;
 
-	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
-		return -EINVAL;
+	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) {
+		const struct compat_xt_standard_target *st = (const void *)t;
+
+		if (COMPAT_XT_ALIGN(target_offset + sizeof(*st)) != next_offset)
+			return -EINVAL;
+
+		if (!verdict_ok(st->verdict))
+			return -EINVAL;
+	} else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) {
+		const struct compat_xt_error_target *et = (const void *)t;
+
+		if (!error_tg_ok(t->u.target_size, sizeof(*et),
+				 et->errorname, sizeof(et->errorname)))
+			return -EINVAL;
+	}
 
 	/* compat_xt_entry match has less strict alignment requirements,
 	 * otherwise they are identical.  In case of padding differences
@@ -787,9 +912,21 @@ int xt_check_entry_offsets(const void *base,
 	if (target_offset + t->u.target_size > next_offset)
 		return -EINVAL;
 
-	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
-		return -EINVAL;
+	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) {
+		const struct xt_standard_target *st = (const void *)t;
+
+		if (XT_ALIGN(target_offset + sizeof(*st)) != next_offset)
+			return -EINVAL;
+
+		if (!verdict_ok(st->verdict))
+			return -EINVAL;
+	} else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) {
+		const struct xt_error_target *et = (const void *)t;
+
+		if (!error_tg_ok(t->u.target_size, sizeof(*et),
+				 et->errorname, sizeof(et->errorname)))
+			return -EINVAL;
+	}
 
 	return xt_check_entry_match(elems, base + target_offset,
 				    __alignof__(struct xt_entry_match));
@@ -805,6 +942,9 @@ EXPORT_SYMBOL(xt_check_entry_offsets);
  */
 unsigned int *xt_alloc_entry_offsets(unsigned int size)
 {
+	if (size > XT_MAX_TABLE_SIZE / sizeof(unsigned int))
+		return NULL;
+
 	return kvmalloc_array(size, sizeof(unsigned int), GFP_KERNEL | __GFP_ZERO);
 
 }
@@ -1029,7 +1169,7 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size)
 	struct xt_table_info *info = NULL;
 	size_t sz = sizeof(*info) + size;
 
-	if (sz < sizeof(*info))
+	if (sz < sizeof(*info) || sz >= XT_MAX_TABLE_SIZE)
 		return NULL;
 
 	/* __GFP_NORETRY is not fully supported by kvmalloc but it should
@@ -1198,6 +1338,21 @@ static int xt_jumpstack_alloc(struct xt_table_info *i)
 	return 0;
 }
 
+struct xt_counters *xt_counters_alloc(unsigned int counters)
+{
+	struct xt_counters *mem;
+
+	if (counters == 0 || counters > INT_MAX / sizeof(*mem))
+		return NULL;
+
+	counters *= sizeof(*mem);
+	if (counters > XT_MAX_TABLE_SIZE)
+		return NULL;
+
+	return vzalloc(counters);
+}
+EXPORT_SYMBOL(xt_counters_alloc);
+
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
@@ -1729,7 +1884,9 @@ EXPORT_SYMBOL_GPL(xt_proto_fini);
  * to fetch the real percpu counter.
  *
  * To speed up allocation and improve data locality, a 4kb block is
- * allocated.
+ * allocated.  Freeing any counter may free an entire block, so all
+ * counters allocated using the same state must be freed at the same
+ * time.
  *
  * xt_percpu_counter_alloc_state contains the base address of the
  * allocated page and the current sub-offset.