aboutsummaryrefslogtreecommitdiffstats
path: root/net/netfilter
diff options
context:
space:
mode:
authorFlorian Westphal <fw@strlen.de>2015-07-14 17:51:08 +0200
committerPablo Neira Ayuso <pablo@netfilter.org>2015-07-15 18:18:06 +0200
commit7814b6ec6d0d63444abdb49554166c8cfcbd063e (patch)
treec60aedd08c8c49b9a43e00c6cce865a96cdd43b7 /net/netfilter
parente7c8899f3e6f2830136cf6e115c4a55ce7a3920a (diff)
netfilter: xtables: don't save/restore jumpstack offset
In most cases there is no reentrancy into ip/ip6tables. For skbs sent by REJECT or SYNPROXY targets, there is one level of reentrancy, but its not relevant as those targets issue an absolute verdict, i.e. the jumpstack can be clobbered since its not used after the target issues absolute verdict (ACCEPT, DROP, STOLEN, etc). So the only special case where it is relevant is the TEE target, which returns XT_CONTINUE. This patch changes ip(6)_do_table to always use the jump stack starting from 0. When we detect we're operating on an skb sent via TEE (percpu nf_skb_duplicated is 1) we switch to an alternate stack to leave the original one alone. Since there is no TEE support for arptables, it doesn't need to test if tee is active. The jump stack overflow tests are no longer needed as well -- since ->stacksize is the largest call depth we cannot exceed it. A much better alternative to the external jumpstack would be to just declare a jumps[32] stack on the local stack frame, but that would mean we'd have to reject iptables rulesets that used to work before. Another alternative would be to start rejecting rulesets with a larger call depth, e.g. 1000 -- in this case it would be feasible to allocate the entire stack in the percpu area which would avoid one dereference. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/x_tables.c22
1 files changed, 11 insertions, 11 deletions
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 4db7d60d42fa..154447e519ab 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -67,9 +67,6 @@ static const char *const xt_prefix[NFPROTO_NUMPROTO] = {
[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)
{
@@ -688,8 +685,6 @@ void xt_free_table_info(struct xt_table_info *info)
kvfree(info->jumpstack);
}
- free_percpu(info->stackptr);
-
kvfree(info);
}
EXPORT_SYMBOL(xt_free_table_info);
@@ -737,10 +732,6 @@ static int xt_jumpstack_alloc(struct xt_table_info *i)
unsigned int size;
int cpu;
- i->stackptr = alloc_percpu(unsigned int);
- if (i->stackptr == NULL)
- return -ENOMEM;
-
size = sizeof(void **) * nr_cpu_ids;
if (size > PAGE_SIZE)
i->jumpstack = vzalloc(size);
@@ -753,8 +744,17 @@ static int xt_jumpstack_alloc(struct xt_table_info *i)
if (i->stacksize == 0)
return 0;
- i->stacksize *= xt_jumpstack_multiplier;
- size = sizeof(void *) * i->stacksize;
+ /* Jumpstack needs to be able to record two full callchains, one
+ * from the first rule set traversal, plus one table reentrancy
+ * via -j TEE without clobbering the callchain that brought us to
+ * TEE target.
+ *
+ * This is done by allocating two jumpstacks per cpu, on reentry
+ * the upper half of the stack is used.
+ *
+ * see the jumpstack setup in ipt_do_table() for more details.
+ */
+ size = sizeof(void *) * i->stacksize * 2u;
for_each_possible_cpu(cpu) {
if (size > PAGE_SIZE)
i->jumpstack[cpu] = vmalloc_node(size,

Privacy Policy