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>
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8e23d8f..edde5c6 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -62,6 +62,9 @@
[NFPROTO_IPV6] = "ip6",
};
+/* Allow this many total (re)entries. */
+static const unsigned int xt_jumpstack_multiplier = 2;
+
/* Registration hooks for targets. */
int
xt_register_target(struct xt_target *target)
@@ -680,6 +683,26 @@
else
vfree(info->entries[cpu]);
}
+
+ if (info->jumpstack != NULL) {
+ if (sizeof(void *) * info->stacksize > PAGE_SIZE) {
+ for_each_possible_cpu(cpu)
+ vfree(info->jumpstack[cpu]);
+ } else {
+ for_each_possible_cpu(cpu)
+ kfree(info->jumpstack[cpu]);
+ }
+ }
+
+ if (sizeof(void **) * nr_cpu_ids > PAGE_SIZE)
+ vfree(info->jumpstack);
+ else
+ kfree(info->jumpstack);
+ if (sizeof(unsigned int) * nr_cpu_ids > PAGE_SIZE)
+ vfree(info->stackptr);
+ else
+ kfree(info->stackptr);
+
kfree(info);
}
EXPORT_SYMBOL(xt_free_table_info);
@@ -724,6 +747,49 @@
DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks);
EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks);
+static int xt_jumpstack_alloc(struct xt_table_info *i)
+{
+ unsigned int size;
+ int cpu;
+
+ size = sizeof(unsigned int) * nr_cpu_ids;
+ if (size > PAGE_SIZE)
+ i->stackptr = vmalloc(size);
+ else
+ i->stackptr = kmalloc(size, GFP_KERNEL);
+ if (i->stackptr == NULL)
+ return -ENOMEM;
+ memset(i->stackptr, 0, size);
+
+ size = sizeof(void **) * nr_cpu_ids;
+ if (size > PAGE_SIZE)
+ i->jumpstack = vmalloc(size);
+ else
+ i->jumpstack = kmalloc(size, GFP_KERNEL);
+ if (i->jumpstack == NULL)
+ return -ENOMEM;
+ memset(i->jumpstack, 0, size);
+
+ i->stacksize *= xt_jumpstack_multiplier;
+ size = sizeof(void *) * i->stacksize;
+ for_each_possible_cpu(cpu) {
+ if (size > PAGE_SIZE)
+ i->jumpstack[cpu] = vmalloc_node(size,
+ cpu_to_node(cpu));
+ else
+ i->jumpstack[cpu] = kmalloc_node(size,
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (i->jumpstack[cpu] == NULL)
+ /*
+ * Freeing will be done later on by the callers. The
+ * chain is: xt_replace_table -> __do_replace ->
+ * do_replace -> xt_free_table_info.
+ */
+ return -ENOMEM;
+ }
+
+ return 0;
+}
struct xt_table_info *
xt_replace_table(struct xt_table *table,
@@ -732,6 +798,7 @@
int *error)
{
struct xt_table_info *private;
+ int ret;
/* Do the substitution. */
local_bh_disable();
@@ -746,6 +813,12 @@
return NULL;
}
+ ret = xt_jumpstack_alloc(newinfo);
+ if (ret < 0) {
+ *error = ret;
+ return NULL;
+ }
+
table->private = newinfo;
newinfo->initial_entries = private->initial_entries;
@@ -770,6 +843,10 @@
struct xt_table_info *private;
struct xt_table *t, *table;
+ ret = xt_jumpstack_alloc(newinfo);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
/* Don't add one object to multiple lists. */
table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL);
if (!table) {
