* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cache.h>
#include <linux/capability.h>
#include <linux/skbuff.h>
#define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg)))
if (FWINV((ip->saddr&ipinfo->smsk.s_addr) != ipinfo->src.s_addr,
- IPT_INV_SRCIP)
- || FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr,
- IPT_INV_DSTIP)) {
+ IPT_INV_SRCIP) ||
+ FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr,
+ IPT_INV_DSTIP)) {
dprintf("Source or dest mismatch.\n");
dprintf("SRC: %pI4. Mask: %pI4. Target: %pI4.%s\n",
}
/* Check specific protocol */
- if (ipinfo->proto
- && FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) {
+ if (ipinfo->proto &&
+ FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) {
dprintf("Packet protocol %hi does not match %hi.%s\n",
ip->protocol, ipinfo->proto,
ipinfo->invflags&IPT_INV_PROTO ? " (INV)":"");
/* All zeroes == unconditional rule. */
/* Mildly perf critical (only if packet tracing is on) */
-static inline int
-unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_ip *ip)
{
- unsigned int i;
+ static const struct ipt_ip uncond;
- for (i = 0; i < sizeof(*ip)/sizeof(__u32); i++)
- if (((__u32 *)ip)[i])
- return 0;
-
- return 1;
+ return memcmp(ip, &uncond, sizeof(uncond)) == 0;
#undef FWINV
}
/* Mildly perf critical (only if packet tracing is on) */
static inline int
get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
- char *hookname, char **chainname,
- char **comment, unsigned int *rulenum)
+ const char *hookname, const char **chainname,
+ const char **comment, unsigned int *rulenum)
{
struct ipt_standard_target *t = (void *)ipt_get_target(s);
} else if (s == e) {
(*rulenum)++;
- if (s->target_offset == sizeof(struct ipt_entry)
- && strcmp(t->target.u.kernel.target->name,
- IPT_STANDARD_TARGET) == 0
- && t->verdict < 0
- && unconditional(&s->ip)) {
+ if (s->target_offset == sizeof(struct ipt_entry) &&
+ strcmp(t->target.u.kernel.target->name,
+ IPT_STANDARD_TARGET) == 0 &&
+ t->verdict < 0 &&
+ unconditional(&s->ip)) {
/* Tail of chains: STANDARD target (return/policy) */
*comment = *chainname == hookname
- ? (char *)comments[NF_IP_TRACE_COMMENT_POLICY]
- : (char *)comments[NF_IP_TRACE_COMMENT_RETURN];
+ ? comments[NF_IP_TRACE_COMMENT_POLICY]
+ : comments[NF_IP_TRACE_COMMENT_RETURN];
}
return 1;
} else
{
void *table_base;
const struct ipt_entry *root;
- char *hookname, *chainname, *comment;
+ const char *hookname, *chainname, *comment;
unsigned int rulenum = 0;
- table_base = (void *)private->entries[smp_processor_id()];
+ table_base = private->entries[smp_processor_id()];
root = get_entry(table_base, private->hook_entry[hook]);
- hookname = chainname = (char *)hooknames[hook];
- comment = (char *)comments[NF_IP_TRACE_COMMENT_RULE];
+ hookname = chainname = hooknames[hook];
+ comment = comments[NF_IP_TRACE_COMMENT_RULE];
IPT_ENTRY_ITERATE(root,
private->size - private->hook_entry[hook],
}
#endif
+static inline __pure
+struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry)
+{
+ return (void *)entry + entry->next_offset;
+}
+
/* Returns one of the generic firewall policies, like NF_ACCEPT. */
unsigned int
ipt_do_table(struct sk_buff *skb,
const struct net_device *out,
struct xt_table *table)
{
+#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom
+
static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
const struct iphdr *ip;
- u_int16_t datalen;
bool hotdrop = false;
/* Initializing verdict to NF_DROP keeps gcc happy. */
unsigned int verdict = NF_DROP;
/* Initialization */
ip = ip_hdr(skb);
- datalen = skb->len - ip->ihl * 4;
indev = in ? in->name : nulldevname;
outdev = out ? out->name : nulldevname;
/* We handle fragments by dealing with the first fragment as
mtpar.in = tgpar.in = in;
mtpar.out = tgpar.out = out;
mtpar.family = tgpar.family = NFPROTO_IPV4;
- tgpar.hooknum = hook;
+ mtpar.hooknum = tgpar.hooknum = hook;
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
-
- rcu_read_lock_bh();
- 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]);
do {
+ struct ipt_entry_target *t;
+
IP_NF_ASSERT(e);
IP_NF_ASSERT(back);
- if (ip_packet_match(ip, indev, outdev,
- &e->ip, mtpar.fragoff)) {
- struct ipt_entry_target *t;
-
- if (IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0)
- goto no_match;
+ if (!ip_packet_match(ip, indev, outdev,
+ &e->ip, mtpar.fragoff) ||
+ IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) {
+ e = ipt_next_entry(e);
+ continue;
+ }
- ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
+ ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
- t = ipt_get_target(e);
- IP_NF_ASSERT(t->u.kernel.target);
+ t = ipt_get_target(e);
+ IP_NF_ASSERT(t->u.kernel.target);
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
- /* The packet is traced: log it */
- if (unlikely(skb->nf_trace))
- trace_packet(skb, hook, in, out,
- table->name, private, e);
+ /* The packet is traced: log it */
+ if (unlikely(skb->nf_trace))
+ trace_packet(skb, hook, in, out,
+ table->name, private, e);
#endif
- /* Standard target? */
- if (!t->u.kernel.target->target) {
- int v;
-
- v = ((struct ipt_standard_target *)t)->verdict;
- if (v < 0) {
- /* Pop from stack? */
- if (v != IPT_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
- && !(e->ip.flags & IPT_F_GOTO)) {
- /* Save old back ptr in next entry */
- struct ipt_entry *next
- = (void *)e + e->next_offset;
- next->comefrom
- = (void *)back - table_base;
- /* set back pointer to next entry */
- back = next;
+ /* Standard target? */
+ if (!t->u.kernel.target->target) {
+ int v;
+
+ v = ((struct ipt_standard_target *)t)->verdict;
+ if (v < 0) {
+ /* Pop from stack? */
+ if (v != IPT_RETURN) {
+ verdict = (unsigned)(-v) - 1;
+ break;
}
+ e = back;
+ back = get_entry(table_base, back->comefrom);
+ continue;
+ }
+ if (table_base + v != ipt_next_entry(e) &&
+ !(e->ip.flags & IPT_F_GOTO)) {
+ /* Save old back ptr in next entry */
+ struct ipt_entry *next = ipt_next_entry(e);
+ next->comefrom = (void *)back - table_base;
+ /* set back pointer to next entry */
+ back = next;
+ }
+
+ e = get_entry(table_base, v);
+ continue;
+ }
+
+ /* Targets which reenter must return
+ abs. verdicts */
+ tgpar.target = t->u.kernel.target;
+ tgpar.targinfo = t->data;
+
- e = get_entry(table_base, v);
- } else {
- /* Targets which reenter must return
- abs. verdicts */
- tgpar.target = t->u.kernel.target;
- tgpar.targinfo = t->data;
#ifdef CONFIG_NETFILTER_DEBUG
- ((struct ipt_entry *)table_base)->comefrom
- = 0xeeeeeeec;
+ tb_comefrom = 0xeeeeeeec;
#endif
- verdict = t->u.kernel.target->target(skb,
- &tgpar);
+ verdict = t->u.kernel.target->target(skb, &tgpar);
#ifdef CONFIG_NETFILTER_DEBUG
- if (((struct ipt_entry *)table_base)->comefrom
- != 0xeeeeeeec
- && verdict == IPT_CONTINUE) {
- printk("Target %s reentered!\n",
- t->u.kernel.target->name);
- verdict = NF_DROP;
- }
- ((struct ipt_entry *)table_base)->comefrom
- = 0x57acc001;
-#endif
- /* Target might have changed stuff. */
- ip = ip_hdr(skb);
- datalen = skb->len - ip->ihl * 4;
-
- if (verdict == IPT_CONTINUE)
- e = (void *)e + e->next_offset;
- else
- /* Verdict */
- break;
- }
- } else {
-
- no_match:
- e = (void *)e + e->next_offset;
+ if (tb_comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) {
+ printk("Target %s reentered!\n",
+ t->u.kernel.target->name);
+ verdict = NF_DROP;
}
+ tb_comefrom = 0x57acc001;
+#endif
+ /* Target might have changed stuff. */
+ ip = ip_hdr(skb);
+ if (verdict == IPT_CONTINUE)
+ e = ipt_next_entry(e);
+ else
+ /* Verdict */
+ break;
} while (!hotdrop);
-
- rcu_read_unlock_bh();
+ xt_info_rdunlock_bh();
#ifdef DEBUG_ALLOW_ALL
return NF_ACCEPT;
return NF_DROP;
else return verdict;
#endif
+
+#undef tb_comefrom
}
/* Figures out from what hook each rule can be called: returns 0 if
e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct ipt_entry)
- && (strcmp(t->target.u.user.name,
- IPT_STANDARD_TARGET) == 0)
- && t->verdict < 0
- && unconditional(&e->ip)) || visited) {
+ if ((e->target_offset == sizeof(struct ipt_entry) &&
+ (strcmp(t->target.u.user.name,
+ IPT_STANDARD_TARGET) == 0) &&
+ t->verdict < 0 && unconditional(&e->ip)) ||
+ visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
int newpos = t->verdict;
if (strcmp(t->target.u.user.name,
- IPT_STANDARD_TARGET) == 0
- && newpos >= 0) {
+ IPT_STANDARD_TARGET) == 0 &&
+ newpos >= 0) {
if (newpos > newinfo->size -
sizeof(struct ipt_entry)) {
duprintf("mark_source_chains: "
}
static int
-find_check_entry(struct ipt_entry *e, const char *name, unsigned int size,
- unsigned int *i)
+find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
+ unsigned int size, unsigned int *i)
{
struct ipt_entry_target *t;
struct xt_target *target;
return ret;
j = 0;
+ mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ip;
mtpar.hook_mask = e->comefrom;
return ret;
}
+static bool check_underflow(struct ipt_entry *e)
+{
+ const struct ipt_entry_target *t;
+ unsigned int verdict;
+
+ if (!unconditional(&e->ip))
+ return false;
+ t = ipt_get_target(e);
+ if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
+ return false;
+ verdict = ((struct ipt_standard_target *)t)->verdict;
+ verdict = -verdict - 1;
+ return verdict == NF_DROP || verdict == NF_ACCEPT;
+}
+
static int
check_entry_size_and_hooks(struct ipt_entry *e,
struct xt_table_info *newinfo,
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 ipt_entry) != 0
- || (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+ if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
+ (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
/* Check hooks & underflows */
for (h = 0; h < NF_INET_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 IPT_RETURN). --RR */
-
/* Clear counters and comefrom */
e->counters = ((struct xt_counters) { 0, 0 });
e->comefrom = 0;
/* Checks and translates the user-supplied table segment (held in
newinfo) */
static int
-translate_table(const char *name,
+translate_table(struct net *net,
+ const char *name,
unsigned int valid_hooks,
struct xt_table_info *newinfo,
void *entry0,
newinfo,
entry0,
entry0 + size,
- hook_entries, underflows, &i);
+ hook_entries, underflows, valid_hooks, &i);
if (ret != 0)
return ret;
/* Finally, each sanity check must pass */
i = 0;
ret = IPT_ENTRY_ITERATE(entry0, newinfo->size,
- find_check_entry, name, size, &i);
+ find_check_entry, net, name, size, &i);
if (ret != 0) {
IPT_ENTRY_ITERATE(entry0, newinfo->size,
/* 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.
+ * with data used by 'current' CPU.
+ *
+ * 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;
IPT_ENTRY_ITERATE(t->entries[curcpu],
if (cpu == curcpu)
continue;
i = 0;
+ xt_info_wrlock(cpu);
IPT_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 ipt_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;
- IPT_ENTRY_ITERATE(t->entries[cpu],
- t->size,
- add_counter_to_entry,
- counters,
- &i);
local_bh_enable();
}
-
-static inline int
-zero_entry_counter(struct ipt_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);
- IPT_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
(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()];
IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,
goto free_newinfo;
}
- ret = translate_table(tmp.name, tmp.valid_hooks,
+ ret = translate_table(net, tmp.name, tmp.valid_hooks,
newinfo, loc_cpu_entry, tmp.size, tmp.num_entries,
tmp.hook_entry, tmp.underflow);
if (ret != 0)
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 ipt_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[raw_smp_processor_id()];
+ curcpu = smp_processor_id();
+ loc_cpu_entry = private->entries[curcpu];
+ xt_info_wrlock(curcpu);
IPT_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_ipt_entry) != 0
- || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+ if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
+ (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
}
static int
-compat_check_entry(struct ipt_entry *e, const char *name,
+compat_check_entry(struct ipt_entry *e, struct net *net, const char *name,
unsigned int *i)
{
struct xt_mtchk_param mtpar;
int ret;
j = 0;
+ mtpar.net = net;
mtpar.table = name;
mtpar.entryinfo = &e->ip;
mtpar.hook_mask = e->comefrom;
}
static int
-translate_compat_table(const char *name,
+translate_compat_table(struct net *net,
+ const char *name,
unsigned int valid_hooks,
struct xt_table_info **pinfo,
void **pentry0,
i = 0;
ret = IPT_ENTRY_ITERATE(entry1, newinfo->size, compat_check_entry,
- name, &i);
+ net, name, &i);
if (ret) {
j -= i;
COMPAT_IPT_ENTRY_ITERATE_CONTINUE(entry0, newinfo->size, i,
goto free_newinfo;
}
- ret = translate_compat_table(tmp.name, tmp.valid_hooks,
+ ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
&newinfo, &loc_cpu_entry, tmp.size,
tmp.num_entries, tmp.hook_entry,
tmp.underflow);
return ret;
}
-struct xt_table *ipt_register_table(struct net *net, struct xt_table *table,
+struct xt_table *ipt_register_table(struct net *net,
+ const struct xt_table *table,
const struct ipt_replace *repl)
{
int ret;
loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
memcpy(loc_cpu_entry, repl->entries, repl->size);
- ret = translate_table(table->name, table->valid_hooks,
+ ret = translate_table(net, table->name, table->valid_hooks,
newinfo, loc_cpu_entry, repl->size,
repl->num_entries,
repl->hook_entry,
static struct xt_target ipt_standard_target __read_mostly = {
.name = IPT_STANDARD_TARGET,
.targetsize = sizeof(int),
- .family = AF_INET,
+ .family = NFPROTO_IPV4,
#ifdef CONFIG_COMPAT
.compatsize = sizeof(compat_int_t),
.compat_from_user = compat_standard_from_user,
.name = IPT_ERROR_TARGET,
.target = ipt_error,
.targetsize = IPT_FUNCTION_MAXNAMELEN,
- .family = AF_INET,
+ .family = NFPROTO_IPV4,
};
static struct nf_sockopt_ops ipt_sockopts = {
.matchsize = sizeof(struct ipt_icmp),
.checkentry = icmp_checkentry,
.proto = IPPROTO_ICMP,
- .family = AF_INET,
+ .family = NFPROTO_IPV4,
};
static int __net_init ip_tables_net_init(struct net *net)
{
- return xt_proto_init(net, AF_INET);
+ return xt_proto_init(net, NFPROTO_IPV4);
}
static void __net_exit ip_tables_net_exit(struct net *net)
{
- xt_proto_fini(net, AF_INET);
+ xt_proto_fini(net, NFPROTO_IPV4);
}
static struct pernet_operations ip_tables_net_ops = {
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff