* Copyright (C) 2002 David S. Miller (davem@redhat.com)
*
*/
-
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
/*
* Unfortunatly, _b and _mask are not aligned to an int (or long int)
* Some arches dont care, unrolling the loop is a win on them.
+ * For other arches, we only have a 16bit alignement.
*/
static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask)
{
unsigned long ret = ifname_compare_aligned(_a, _b, _mask);
#else
unsigned long ret = 0;
+ const u16 *a = (const u16 *)_a;
+ const u16 *b = (const u16 *)_b;
+ const u16 *mask = (const u16 *)_mask;
int i;
- for (i = 0; i < IFNAMSIZ; i++)
- ret |= (_a[i] ^ _b[i]) & _mask[i];
+ for (i = 0; i < IFNAMSIZ/sizeof(u16); i++)
+ ret |= (a[i] ^ b[i]) & mask[i];
#endif
return ret;
}
return (struct arpt_entry *)(base + offset);
}
+static inline __pure
+struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry)
+{
+ return (void *)entry + entry->next_offset;
+}
+
unsigned int arpt_do_table(struct sk_buff *skb,
unsigned int hook,
const struct net_device *in,
indev = in ? in->name : nulldevname;
outdev = out ? out->name : nulldevname;
- rcu_read_lock();
- private = rcu_dereference(table->private);
- table_base = rcu_dereference(private->entries[smp_processor_id()]);
+ xt_info_rdlock_bh();
+ private = table->private;
+ table_base = private->entries[smp_processor_id()];
e = get_entry(table_base, private->hook_entry[hook]);
back = get_entry(table_base, private->underflow[hook]);
arp = arp_hdr(skb);
do {
- if (arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
- struct arpt_entry_target *t;
- int hdr_len;
-
- hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
- (2 * skb->dev->addr_len);
- ADD_COUNTER(e->counters, hdr_len, 1);
-
- t = arpt_get_target(e);
-
- /* Standard target? */
- if (!t->u.kernel.target->target) {
- int v;
-
- v = ((struct arpt_standard_target *)t)->verdict;
- if (v < 0) {
- /* Pop from stack? */
- if (v != ARPT_RETURN) {
- verdict = (unsigned)(-v) - 1;
- break;
- }
- e = back;
- back = get_entry(table_base,
- back->comefrom);
- continue;
- }
- if (table_base + v
- != (void *)e + e->next_offset) {
- /* Save old back ptr in next entry */
- struct arpt_entry *next
- = (void *)e + e->next_offset;
- next->comefrom =
- (void *)back - table_base;
-
- /* set back pointer to next entry */
- back = next;
- }
+ struct arpt_entry_target *t;
+ int hdr_len;
- e = get_entry(table_base, v);
- } else {
- /* Targets which reenter must return
- * abs. verdicts
- */
- tgpar.target = t->u.kernel.target;
- tgpar.targinfo = t->data;
- verdict = t->u.kernel.target->target(skb,
- &tgpar);
-
- /* Target might have changed stuff. */
- arp = arp_hdr(skb);
-
- if (verdict == ARPT_CONTINUE)
- e = (void *)e + e->next_offset;
- else
- /* Verdict */
+ if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
+ e = arpt_next_entry(e);
+ continue;
+ }
+
+ hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
+ (2 * skb->dev->addr_len);
+ ADD_COUNTER(e->counters, hdr_len, 1);
+
+ t = arpt_get_target(e);
+
+ /* Standard target? */
+ if (!t->u.kernel.target->target) {
+ int v;
+
+ v = ((struct arpt_standard_target *)t)->verdict;
+ if (v < 0) {
+ /* Pop from stack? */
+ if (v != ARPT_RETURN) {
+ verdict = (unsigned)(-v) - 1;
break;
+ }
+ e = back;
+ back = get_entry(table_base, back->comefrom);
+ continue;
+ }
+ if (table_base + v
+ != arpt_next_entry(e)) {
+ /* Save old back ptr in next entry */
+ struct arpt_entry *next = arpt_next_entry(e);
+ next->comefrom = (void *)back - table_base;
+
+ /* set back pointer to next entry */
+ back = next;
}
- } else {
- e = (void *)e + e->next_offset;
+
+ e = get_entry(table_base, v);
+ continue;
}
- } while (!hotdrop);
- rcu_read_unlock();
+ /* Targets which reenter must return
+ * abs. verdicts
+ */
+ tgpar.target = t->u.kernel.target;
+ tgpar.targinfo = t->data;
+ verdict = t->u.kernel.target->target(skb, &tgpar);
+
+ /* Target might have changed stuff. */
+ arp = arp_hdr(skb);
+
+ if (verdict == ARPT_CONTINUE)
+ e = arpt_next_entry(e);
+ else
+ /* Verdict */
+ break;
+ } while (!hotdrop);
+ xt_info_rdunlock_bh();
if (hotdrop)
return NF_DROP;
}
/* All zeroes == unconditional rule. */
-static inline int unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_arp *arp)
{
- unsigned int i;
+ static const struct arpt_arp uncond;
- for (i = 0; i < sizeof(*arp)/sizeof(__u32); i++)
- if (((__u32 *)arp)[i])
- return 0;
-
- return 1;
+ return memcmp(arp, &uncond, sizeof(uncond)) == 0;
}
/* Figures out from what hook each rule can be called: returns 0 if
|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct arpt_entry)
- && (strcmp(t->target.u.user.name,
- ARPT_STANDARD_TARGET) == 0)
- && t->verdict < 0
- && unconditional(&e->arp)) || visited) {
+ if ((e->target_offset == sizeof(struct arpt_entry) &&
+ (strcmp(t->target.u.user.name,
+ ARPT_STANDARD_TARGET) == 0) &&
+ t->verdict < 0 && unconditional(&e->arp)) ||
+ visited) {
unsigned int oldpos, size;
- if (t->verdict < -NF_MAX_VERDICT - 1) {
+ if ((strcmp(t->target.u.user.name,
+ ARPT_STANDARD_TARGET) == 0) &&
+ t->verdict < -NF_MAX_VERDICT - 1) {
duprintf("mark_source_chains: bad "
"negative verdict (%i)\n",
t->verdict);
int newpos = t->verdict;
if (strcmp(t->target.u.user.name,
- ARPT_STANDARD_TARGET) == 0
- && newpos >= 0) {
+ ARPT_STANDARD_TARGET) == 0 &&
+ newpos >= 0) {
if (newpos > newinfo->size -
sizeof(struct arpt_entry)) {
duprintf("mark_source_chains: "
return ret;
}
+static bool check_underflow(struct arpt_entry *e)
+{
+ const struct arpt_entry_target *t;
+ unsigned int verdict;
+
+ if (!unconditional(&e->arp))
+ return false;
+ t = arpt_get_target(e);
+ if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
+ return false;
+ verdict = ((struct arpt_standard_target *)t)->verdict;
+ verdict = -verdict - 1;
+ return verdict == NF_DROP || verdict == NF_ACCEPT;
+}
+
static inline int check_entry_size_and_hooks(struct arpt_entry *e,
struct xt_table_info *newinfo,
unsigned char *base,
unsigned char *limit,
const unsigned int *hook_entries,
const unsigned int *underflows,
+ unsigned int valid_hooks,
unsigned int *i)
{
unsigned int h;
- if ((unsigned long)e % __alignof__(struct arpt_entry) != 0
- || (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+ if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
+ (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
/* Check hooks & underflows */
for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
+ if (!(valid_hooks & (1 << h)))
+ continue;
if ((unsigned char *)e - base == hook_entries[h])
newinfo->hook_entry[h] = hook_entries[h];
- if ((unsigned char *)e - base == underflows[h])
+ if ((unsigned char *)e - base == underflows[h]) {
+ if (!check_underflow(e)) {
+ pr_err("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
+ return -EINVAL;
+ }
newinfo->underflow[h] = underflows[h];
+ }
}
- /* FIXME: underflows must be unconditional, standard verdicts
- < 0 (not ARPT_RETURN). --RR */
-
/* Clear counters and comefrom */
e->counters = ((struct xt_counters) { 0, 0 });
e->comefrom = 0;
newinfo,
entry0,
entry0 + size,
- hook_entries, underflows, &i);
+ hook_entries, underflows, valid_hooks, &i);
duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
if (ret != 0)
return ret;
/* Instead of clearing (by a previous call to memset())
* the counters and using adds, we set the counters
* with data used by 'current' CPU
- * We dont care about preemption here.
+ *
+ * Bottom half has to be disabled to prevent deadlock
+ * if new softirq were to run and call ipt_do_table
*/
- curcpu = raw_smp_processor_id();
+ local_bh_disable();
+ curcpu = smp_processor_id();
i = 0;
ARPT_ENTRY_ITERATE(t->entries[curcpu],
if (cpu == curcpu)
continue;
i = 0;
+ xt_info_wrlock(cpu);
ARPT_ENTRY_ITERATE(t->entries[cpu],
t->size,
add_entry_to_counter,
counters,
&i);
+ xt_info_wrunlock(cpu);
}
-}
-
-
-/* We're lazy, and add to the first CPU; overflow works its fey magic
- * and everything is OK. */
-static int
-add_counter_to_entry(struct arpt_entry *e,
- const struct xt_counters addme[],
- unsigned int *i)
-{
- ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
-
- (*i)++;
- return 0;
-}
-
-/* Take values from counters and add them back onto the current cpu */
-static void put_counters(struct xt_table_info *t,
- const struct xt_counters counters[])
-{
- unsigned int i, cpu;
-
- local_bh_disable();
- cpu = smp_processor_id();
- i = 0;
- ARPT_ENTRY_ITERATE(t->entries[cpu],
- t->size,
- add_counter_to_entry,
- counters,
- &i);
local_bh_enable();
}
-static inline int
-zero_entry_counter(struct arpt_entry *e, void *arg)
-{
- e->counters.bcnt = 0;
- e->counters.pcnt = 0;
- return 0;
-}
-
-static void
-clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info)
-{
- unsigned int cpu;
- const void *loc_cpu_entry = info->entries[raw_smp_processor_id()];
-
- memcpy(newinfo, info, offsetof(struct xt_table_info, entries));
- for_each_possible_cpu(cpu) {
- memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size);
- ARPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size,
- zero_entry_counter, NULL);
- }
-}
-
static struct xt_counters *alloc_counters(struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
struct xt_table_info *private = table->private;
- struct xt_table_info *info;
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
counters = vmalloc_node(countersize, numa_node_id());
if (counters == NULL)
- goto nomem;
-
- info = xt_alloc_table_info(private->size);
- if (!info)
- goto free_counters;
-
- clone_counters(info, private);
+ return ERR_PTR(-ENOMEM);
- mutex_lock(&table->lock);
- xt_table_entry_swap_rcu(private, info);
- synchronize_net(); /* Wait until smoke has cleared */
-
- get_counters(info, counters);
- put_counters(private, counters);
- mutex_unlock(&table->lock);
-
- xt_free_table_info(info);
+ get_counters(private, counters);
return counters;
-
- free_counters:
- vfree(counters);
- nomem:
- return ERR_PTR(-ENOMEM);
}
static int copy_entries_to_user(unsigned int total_size,
if (t && !IS_ERR(t)) {
struct arpt_getinfo info;
const struct xt_table_info *private = t->private;
-
#ifdef CONFIG_COMPAT
+ struct xt_table_info tmp;
+
if (compat) {
- struct xt_table_info tmp;
ret = compat_table_info(private, &tmp);
xt_compat_flush_offsets(NFPROTO_ARP);
private = &tmp;
(newinfo->number <= oldinfo->initial_entries))
module_put(t->me);
- /* Get the old counters. */
+ /* Get the old counters, and synchronize with replace */
get_counters(oldinfo, counters);
+
/* Decrease module usage counts and free resource */
loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
return ret;
}
+/* We're lazy, and add to the first CPU; overflow works its fey magic
+ * and everything is OK. */
+static int
+add_counter_to_entry(struct arpt_entry *e,
+ const struct xt_counters addme[],
+ unsigned int *i)
+{
+ ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt);
+
+ (*i)++;
+ return 0;
+}
+
static int do_add_counters(struct net *net, void __user *user, unsigned int len,
int compat)
{
- unsigned int i;
+ unsigned int i, curcpu;
struct xt_counters_info tmp;
struct xt_counters *paddc;
unsigned int num_counters;
goto free;
}
- mutex_lock(&t->lock);
+ local_bh_disable();
private = t->private;
if (private->number != num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
- preempt_disable();
i = 0;
/* Choose the copy that is on our node */
- loc_cpu_entry = private->entries[smp_processor_id()];
+ curcpu = smp_processor_id();
+ loc_cpu_entry = private->entries[curcpu];
+ xt_info_wrlock(curcpu);
ARPT_ENTRY_ITERATE(loc_cpu_entry,
private->size,
add_counter_to_entry,
paddc,
&i);
- preempt_enable();
+ xt_info_wrunlock(curcpu);
unlock_up_free:
- mutex_unlock(&t->lock);
-
+ local_bh_enable();
xt_table_unlock(t);
module_put(t->me);
free:
int ret, off, h;
duprintf("check_compat_entry_size_and_hooks %p\n", e);
- if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0
- || (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+ if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
+ (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
return ret;
}
-struct xt_table *arpt_register_table(struct net *net, struct xt_table *table,
+struct xt_table *arpt_register_table(struct net *net,
+ const struct xt_table *table,
const struct arpt_replace *repl)
{
int ret;