netfilter: xtables: make ip_tables reentrant

Currently, the table traverser stores return addresses in the ruleset
itself (struct ip6t_entry->comefrom). This has a well-known drawback:
the jumpstack is overwritten on reentry, making it necessary for
targets to return absolute verdicts. Also, the ruleset (which might
be heavy memory-wise) needs to be replicated for each CPU that can
possibly invoke ip6t_do_table.

This patch decouples the jumpstack from struct ip6t_entry and instead
puts it into xt_table_info. Not being restricted by 'comefrom'
anymore, we can set up a stack as needed. By default, there is room
allocated for two entries into the traverser.

arp_tables is not touched though, because there is just one/two
modules and further patches seek to collapse the table traverser
anyhow.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>

1 files changed, 22 insertions, 34 deletions

diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index f2b815e7232..2a2770bcd64 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -351,15 +351,14 @@ ip6t_do_table(struct sk_buff *skb,
 	      const struct net_device *out,
 	      struct xt_table *table)
 {
-#define tb_comefrom ((struct ip6t_entry *)table_base)->comefrom
-
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	bool hotdrop = false;
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
 	unsigned int verdict = NF_DROP;
 	const char *indev, *outdev;
 	const void *table_base;
-	struct ip6t_entry *e, *back;
+	struct ip6t_entry *e, **jumpstack;
+	unsigned int *stackptr, origptr, cpu;
 	const struct xt_table_info *private;
 	struct xt_match_param mtpar;
 	struct xt_target_param tgpar;
@@ -383,19 +382,19 @@ ip6t_do_table(struct sk_buff *skb,
 
 	xt_info_rdlock_bh();
 	private = table->private;
-	table_base = private->entries[smp_processor_id()];
+	cpu        = smp_processor_id();
+	table_base = private->entries[cpu];
+	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
+	stackptr   = &private->stackptr[cpu];
+	origptr    = *stackptr;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
-	/* For return from builtin chain */
-	back = get_entry(table_base, private->underflow[hook]);
-
 	do {
 		const struct ip6t_entry_target *t;
 		const struct xt_entry_match *ematch;
 
 		IP_NF_ASSERT(e);
-		IP_NF_ASSERT(back);
 		if (!ip6_packet_match(skb, indev, outdev, &e->ipv6,
 		    &mtpar.thoff, &mtpar.fragoff, &hotdrop)) {
  no_match:
@@ -432,17 +431,20 @@ ip6t_do_table(struct sk_buff *skb,
 					verdict = (unsigned)(-v) - 1;
 					break;
 				}
-				e = back;
-				back = get_entry(table_base, back->comefrom);
+				if (*stackptr == 0)
+					e = get_entry(table_base,
+					    private->underflow[hook]);
+				else
+					e = ip6t_next_entry(jumpstack[--*stackptr]);
 				continue;
 			}
 			if (table_base + v != ip6t_next_entry(e) &&
 			    !(e->ipv6.flags & IP6T_F_GOTO)) {
-				/* Save old back ptr in next entry */
-				struct ip6t_entry *next = ip6t_next_entry(e);
-				next->comefrom = (void *)back - table_base;
-				/* set back pointer to next entry */
-				back = next;
+				if (*stackptr >= private->stacksize) {
+					verdict = NF_DROP;
+					break;
+				}
+				jumpstack[(*stackptr)++] = e;
 			}
 
 			e = get_entry(table_base, v);
@@ -454,19 +456,7 @@ ip6t_do_table(struct sk_buff *skb,
 		tgpar.target   = t->u.kernel.target;
 		tgpar.targinfo = t->data;
 
-#ifdef CONFIG_NETFILTER_DEBUG
-		tb_comefrom = 0xeeeeeeec;
-#endif
 		verdict = t->u.kernel.target->target(skb, &tgpar);
-
-#ifdef CONFIG_NETFILTER_DEBUG
-		if (tb_comefrom != 0xeeeeeeec && verdict == IP6T_CONTINUE) {
-			printk("Target %s reentered!\n",
-			       t->u.kernel.target->name);
-			verdict = NF_DROP;
-		}
-		tb_comefrom = 0x57acc001;
-#endif
 		if (verdict == IP6T_CONTINUE)
 			e = ip6t_next_entry(e);
 		else
@@ -474,10 +464,8 @@ ip6t_do_table(struct sk_buff *skb,
 			break;
 	} while (!hotdrop);
 
-#ifdef CONFIG_NETFILTER_DEBUG
-	tb_comefrom = NETFILTER_LINK_POISON;
-#endif
 	xt_info_rdunlock_bh();
+	*stackptr = origptr;
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
@@ -486,8 +474,6 @@ ip6t_do_table(struct sk_buff *skb,
 		return NF_DROP;
 	else return verdict;
 #endif
-
-#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -869,6 +855,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		if (ret != 0)
 			return ret;
 		++i;
+		if (strcmp(ip6t_get_target(iter)->u.user.name,
+		    XT_ERROR_TARGET) == 0)
+			++newinfo->stacksize;
 	}
 
 	if (i != repl->num_entries) {
@@ -2120,8 +2109,7 @@ struct xt_table *ip6t_register_table(struct net *net,
 {
 	int ret;
 	struct xt_table_info *newinfo;
-	struct xt_table_info bootstrap
-		= { 0, 0, 0, { 0 }, { 0 }, { } };
+	struct xt_table_info bootstrap = {0};
 	void *loc_cpu_entry;
 	struct xt_table *new_table;