unsigned int initial_entries;
unsigned int hook_entry[NF_ARP_NUMHOOKS];
unsigned int underflow[NF_ARP_NUMHOOKS];
- char entries[0] __attribute__((aligned(SMP_CACHE_BYTES)));
+ void *entries[NR_CPUS];
};
static LIST_HEAD(arpt_target);
static LIST_HEAD(arpt_tables);
+#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0)
#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0)
-#ifdef CONFIG_SMP
-#define TABLE_OFFSET(t,p) (SMP_ALIGN((t)->size)*(p))
-#else
-#define TABLE_OFFSET(t,p) 0
-#endif
-
static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap,
char *hdr_addr, int len)
{
outdev = out ? out->name : nulldevname;
read_lock_bh(&table->lock);
- table_base = (void *)table->private->entries
- + TABLE_OFFSET(table->private,
- smp_processor_id());
+ table_base = (void *)table->private->entries[smp_processor_id()];
e = get_entry(table_base, table->private->hook_entry[hook]);
back = get_entry(table_base, table->private->underflow[hook]);
return verdict;
}
-static inline void *find_inlist_lock_noload(struct list_head *head,
- const char *name,
- int *error,
- struct semaphore *mutex)
+/*
+ * These are weird, but module loading must not be done with mutex
+ * held (since they will register), and we have to have a single
+ * function to use try_then_request_module().
+ */
+
+/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */
+static inline struct arpt_table *find_table_lock(const char *name)
{
- void *ret;
+ struct arpt_table *t;
- *error = down_interruptible(mutex);
- if (*error != 0)
- return NULL;
+ if (down_interruptible(&arpt_mutex) != 0)
+ return ERR_PTR(-EINTR);
- ret = list_named_find(head, name);
- if (!ret) {
- *error = -ENOENT;
- up(mutex);
- }
- return ret;
+ list_for_each_entry(t, &arpt_tables, list)
+ if (strcmp(t->name, name) == 0 && try_module_get(t->me))
+ return t;
+ up(&arpt_mutex);
+ return NULL;
}
-#ifndef CONFIG_KMOD
-#define find_inlist_lock(h,n,p,e,m) find_inlist_lock_noload((h),(n),(e),(m))
-#else
-static void *
-find_inlist_lock(struct list_head *head,
- const char *name,
- const char *prefix,
- int *error,
- struct semaphore *mutex)
+
+/* Find target, grabs ref. Returns ERR_PTR() on error. */
+static inline struct arpt_target *find_target(const char *name, u8 revision)
{
- void *ret;
+ struct arpt_target *t;
+ int err = 0;
- ret = find_inlist_lock_noload(head, name, error, mutex);
- if (!ret) {
- duprintf("find_inlist: loading `%s%s'.\n", prefix, name);
- request_module("%s%s", prefix, name);
- ret = find_inlist_lock_noload(head, name, error, mutex);
+ if (down_interruptible(&arpt_mutex) != 0)
+ return ERR_PTR(-EINTR);
+
+ list_for_each_entry(t, &arpt_target, list) {
+ if (strcmp(t->name, name) == 0) {
+ if (t->revision == revision) {
+ if (try_module_get(t->me)) {
+ up(&arpt_mutex);
+ return t;
+ }
+ } else
+ err = -EPROTOTYPE; /* Found something. */
+ }
}
+ up(&arpt_mutex);
+ return ERR_PTR(err);
+}
- return ret;
+struct arpt_target *arpt_find_target(const char *name, u8 revision)
+{
+ struct arpt_target *target;
+
+ target = try_then_request_module(find_target(name, revision),
+ "arpt_%s", name);
+ if (IS_ERR(target) || !target)
+ return NULL;
+ return target;
}
-#endif
-static inline struct arpt_table *arpt_find_table_lock(const char *name, int *error, struct semaphore *mutex)
+static int target_revfn(const char *name, u8 revision, int *bestp)
{
- return find_inlist_lock(&arpt_tables, name, "arptable_", error, mutex);
+ struct arpt_target *t;
+ int have_rev = 0;
+
+ list_for_each_entry(t, &arpt_target, list) {
+ if (strcmp(t->name, name) == 0) {
+ if (t->revision > *bestp)
+ *bestp = t->revision;
+ if (t->revision == revision)
+ have_rev =1;
+ }
+ }
+ return have_rev;
}
-static struct arpt_target *arpt_find_target_lock(const char *name, int *error, struct semaphore *mutex)
+/* Returns true or false (if no such extension at all) */
+static inline int find_revision(const char *name, u8 revision,
+ int (*revfn)(const char *, u8, int *),
+ int *err)
{
- return find_inlist_lock(&arpt_target, name, "arpt_", error, mutex);
+ int have_rev, best = -1;
+
+ if (down_interruptible(&arpt_mutex) != 0) {
+ *err = -EINTR;
+ return 1;
+ }
+ have_rev = revfn(name, revision, &best);
+ up(&arpt_mutex);
+
+ /* Nothing at all? Return 0 to try loading module. */
+ if (best == -1) {
+ *err = -ENOENT;
+ return 0;
+ }
+
+ *err = best;
+ if (!have_rev)
+ *err = -EPROTONOSUPPORT;
+ return 1;
}
+
/* All zeroes == unconditional rule. */
static inline int unconditional(const struct arpt_arp *arp)
{
/* Figures out from what hook each rule can be called: returns 0 if
* there are loops. Puts hook bitmask in comefrom.
*/
-static int mark_source_chains(struct arpt_table_info *newinfo, unsigned int valid_hooks)
+static int mark_source_chains(struct arpt_table_info *newinfo,
+ unsigned int valid_hooks, void *entry0)
{
unsigned int hook;
for (hook = 0; hook < NF_ARP_NUMHOOKS; hook++) {
unsigned int pos = newinfo->hook_entry[hook];
struct arpt_entry *e
- = (struct arpt_entry *)(newinfo->entries + pos);
+ = (struct arpt_entry *)(entry0 + pos);
if (!(valid_hooks & (1 << hook)))
continue;
goto next;
e = (struct arpt_entry *)
- (newinfo->entries + pos);
+ (entry0 + pos);
} while (oldpos == pos + e->next_offset);
/* Move along one */
size = e->next_offset;
e = (struct arpt_entry *)
- (newinfo->entries + pos + size);
+ (entry0 + pos + size);
e->counters.pcnt = pos;
pos += size;
} else {
newpos = pos + e->next_offset;
}
e = (struct arpt_entry *)
- (newinfo->entries + newpos);
+ (entry0 + newpos);
e->counters.pcnt = pos;
pos = newpos;
}
}
t = arpt_get_target(e);
- target = arpt_find_target_lock(t->u.user.name, &ret, &arpt_mutex);
- if (!target) {
+ target = try_then_request_module(find_target(t->u.user.name,
+ t->u.user.revision),
+ "arpt_%s", t->u.user.name);
+ if (IS_ERR(target) || !target) {
duprintf("check_entry: `%s' not found\n", t->u.user.name);
+ ret = target ? PTR_ERR(target) : -ENOENT;
goto out;
}
- if (!try_module_get((target->me))) {
- ret = -ENOENT;
- goto out_unlock;
- }
t->u.kernel.target = target;
- up(&arpt_mutex);
if (t->u.kernel.target == &arpt_standard_target) {
if (!standard_check(t, size)) {
(*i)++;
return 0;
-out_unlock:
- up(&arpt_mutex);
out:
return ret;
}
static int translate_table(const char *name,
unsigned int valid_hooks,
struct arpt_table_info *newinfo,
+ void *entry0,
unsigned int size,
unsigned int number,
const unsigned int *hook_entries,
i = 0;
/* Walk through entries, checking offsets. */
- ret = ARPT_ENTRY_ITERATE(newinfo->entries, newinfo->size,
+ ret = ARPT_ENTRY_ITERATE(entry0, newinfo->size,
check_entry_size_and_hooks,
newinfo,
- newinfo->entries,
- newinfo->entries + size,
+ entry0,
+ entry0 + size,
hook_entries, underflows, &i);
duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
if (ret != 0)
}
}
- if (!mark_source_chains(newinfo, valid_hooks)) {
+ if (!mark_source_chains(newinfo, valid_hooks, entry0)) {
duprintf("Looping hook\n");
return -ELOOP;
}
/* Finally, each sanity check must pass */
i = 0;
- ret = ARPT_ENTRY_ITERATE(newinfo->entries, newinfo->size,
+ ret = ARPT_ENTRY_ITERATE(entry0, newinfo->size,
check_entry, name, size, &i);
if (ret != 0) {
- ARPT_ENTRY_ITERATE(newinfo->entries, newinfo->size,
+ ARPT_ENTRY_ITERATE(entry0, newinfo->size,
cleanup_entry, &i);
return ret;
}
/* And one copy for every other CPU */
for_each_cpu(i) {
- if (i == 0)
- continue;
- memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i,
- newinfo->entries,
- SMP_ALIGN(newinfo->size));
+ if (newinfo->entries[i] && newinfo->entries[i] != entry0)
+ memcpy(newinfo->entries[i], entry0, newinfo->size);
}
return ret;
return 0;
}
+static inline int set_entry_to_counter(const struct arpt_entry *e,
+ struct arpt_counters total[],
+ unsigned int *i)
+{
+ SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt);
+
+ (*i)++;
+ return 0;
+}
+
static void get_counters(const struct arpt_table_info *t,
struct arpt_counters counters[])
{
unsigned int cpu;
unsigned int i;
+ unsigned int curcpu;
+
+ /* 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.
+ */
+ curcpu = raw_smp_processor_id();
+
+ i = 0;
+ ARPT_ENTRY_ITERATE(t->entries[curcpu],
+ t->size,
+ set_entry_to_counter,
+ counters,
+ &i);
for_each_cpu(cpu) {
+ if (cpu == curcpu)
+ continue;
i = 0;
- ARPT_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu),
+ ARPT_ENTRY_ITERATE(t->entries[cpu],
t->size,
add_entry_to_counter,
counters,
struct arpt_entry *e;
struct arpt_counters *counters;
int ret = 0;
+ void *loc_cpu_entry;
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
return -ENOMEM;
/* First, sum counters... */
- memset(counters, 0, countersize);
write_lock_bh(&table->lock);
get_counters(table->private, counters);
write_unlock_bh(&table->lock);
- /* ... then copy entire thing from CPU 0... */
- if (copy_to_user(userptr, table->private->entries, total_size) != 0) {
+ loc_cpu_entry = table->private->entries[raw_smp_processor_id()];
+ /* ... then copy entire thing ... */
+ if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) {
ret = -EFAULT;
goto free_counters;
}
for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){
struct arpt_entry_target *t;
- e = (struct arpt_entry *)(table->private->entries + off);
+ e = (struct arpt_entry *)(loc_cpu_entry + off);
if (copy_to_user(userptr + off
+ offsetof(struct arpt_entry, counters),
&counters[num],
int ret;
struct arpt_table *t;
- t = arpt_find_table_lock(entries->name, &ret, &arpt_mutex);
- if (t) {
+ t = find_table_lock(entries->name);
+ if (t || !IS_ERR(t)) {
duprintf("t->private->number = %u\n",
t->private->number);
if (entries->size == t->private->size)
entries->size);
ret = -EINVAL;
}
+ module_put(t->me);
up(&arpt_mutex);
} else
- duprintf("get_entries: Can't find %s!\n",
- entries->name);
+ ret = t ? PTR_ERR(t) : -ENOENT;
return ret;
}
+static void free_table_info(struct arpt_table_info *info)
+{
+ int cpu;
+ for_each_cpu(cpu) {
+ if (info->size <= PAGE_SIZE)
+ kfree(info->entries[cpu]);
+ else
+ vfree(info->entries[cpu]);
+ }
+ kfree(info);
+}
+
+static struct arpt_table_info *alloc_table_info(unsigned int size)
+{
+ struct arpt_table_info *newinfo;
+ int cpu;
+
+ newinfo = kzalloc(sizeof(struct arpt_table_info), GFP_KERNEL);
+ if (!newinfo)
+ return NULL;
+
+ newinfo->size = size;
+
+ for_each_cpu(cpu) {
+ if (size <= PAGE_SIZE)
+ newinfo->entries[cpu] = kmalloc_node(size,
+ GFP_KERNEL,
+ cpu_to_node(cpu));
+ else
+ newinfo->entries[cpu] = vmalloc_node(size,
+ cpu_to_node(cpu));
+
+ if (newinfo->entries[cpu] == NULL) {
+ free_table_info(newinfo);
+ return NULL;
+ }
+ }
+
+ return newinfo;
+}
+
static int do_replace(void __user *user, unsigned int len)
{
int ret;
struct arpt_table *t;
struct arpt_table_info *newinfo, *oldinfo;
struct arpt_counters *counters;
+ void *loc_cpu_entry, *loc_cpu_old_entry;
if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
return -EFAULT;
if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages)
return -ENOMEM;
- newinfo = vmalloc(sizeof(struct arpt_table_info)
- + SMP_ALIGN(tmp.size) *
- (highest_possible_processor_id()+1));
+ newinfo = alloc_table_info(tmp.size);
if (!newinfo)
return -ENOMEM;
- if (copy_from_user(newinfo->entries, user + sizeof(tmp),
+ /* choose the copy that is on our node/cpu */
+ loc_cpu_entry = newinfo->entries[raw_smp_processor_id()];
+ if (copy_from_user(loc_cpu_entry, user + sizeof(tmp),
tmp.size) != 0) {
ret = -EFAULT;
goto free_newinfo;
ret = -ENOMEM;
goto free_newinfo;
}
- memset(counters, 0, tmp.num_counters * sizeof(struct arpt_counters));
ret = translate_table(tmp.name, tmp.valid_hooks,
- newinfo, tmp.size, tmp.num_entries,
+ newinfo, loc_cpu_entry, tmp.size, tmp.num_entries,
tmp.hook_entry, tmp.underflow);
if (ret != 0)
goto free_newinfo_counters;
duprintf("arp_tables: Translated table\n");
- t = arpt_find_table_lock(tmp.name, &ret, &arpt_mutex);
- if (!t)
+ t = try_then_request_module(find_table_lock(tmp.name),
+ "arptable_%s", tmp.name);
+ if (!t || IS_ERR(t)) {
+ ret = t ? PTR_ERR(t) : -ENOENT;
goto free_newinfo_counters_untrans;
+ }
/* You lied! */
if (tmp.valid_hooks != t->valid_hooks) {
duprintf("Valid hook crap: %08X vs %08X\n",
tmp.valid_hooks, t->valid_hooks);
ret = -EINVAL;
- goto free_newinfo_counters_untrans_unlock;
- }
-
- /* Get a reference in advance, we're not allowed fail later */
- if (!try_module_get(t->me)) {
- ret = -EBUSY;
- goto free_newinfo_counters_untrans_unlock;
+ goto put_module;
}
oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret);
/* Get the old counters. */
get_counters(oldinfo, counters);
/* Decrease module usage counts and free resource */
- ARPT_ENTRY_ITERATE(oldinfo->entries, oldinfo->size, cleanup_entry,NULL);
- vfree(oldinfo);
+ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()];
+ ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL);
+
+ free_table_info(oldinfo);
if (copy_to_user(tmp.counters, counters,
sizeof(struct arpt_counters) * tmp.num_counters) != 0)
ret = -EFAULT;
put_module:
module_put(t->me);
- free_newinfo_counters_untrans_unlock:
up(&arpt_mutex);
free_newinfo_counters_untrans:
- ARPT_ENTRY_ITERATE(newinfo->entries, newinfo->size, cleanup_entry, NULL);
+ ARPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL);
free_newinfo_counters:
vfree(counters);
free_newinfo:
- vfree(newinfo);
+ free_table_info(newinfo);
return ret;
}
unsigned int i;
struct arpt_counters_info tmp, *paddc;
struct arpt_table *t;
- int ret;
+ int ret = 0;
+ void *loc_cpu_entry;
if (copy_from_user(&tmp, user, sizeof(tmp)) != 0)
return -EFAULT;
goto free;
}
- t = arpt_find_table_lock(tmp.name, &ret, &arpt_mutex);
- if (!t)
+ t = find_table_lock(tmp.name);
+ if (!t || IS_ERR(t)) {
+ ret = t ? PTR_ERR(t) : -ENOENT;
goto free;
+ }
write_lock_bh(&t->lock);
if (t->private->number != paddc->num_counters) {
}
i = 0;
- ARPT_ENTRY_ITERATE(t->private->entries,
+ /* Choose the copy that is on our node */
+ loc_cpu_entry = t->private->entries[smp_processor_id()];
+ ARPT_ENTRY_ITERATE(loc_cpu_entry,
t->private->size,
add_counter_to_entry,
paddc->counters,
unlock_up_free:
write_unlock_bh(&t->lock);
up(&arpt_mutex);
+ module_put(t->me);
free:
vfree(paddc);
break;
}
name[ARPT_TABLE_MAXNAMELEN-1] = '\0';
- t = arpt_find_table_lock(name, &ret, &arpt_mutex);
- if (t) {
+
+ t = try_then_request_module(find_table_lock(name),
+ "arptable_%s", name);
+ if (t && !IS_ERR(t)) {
struct arpt_getinfo info;
info.valid_hooks = t->valid_hooks;
ret = -EFAULT;
else
ret = 0;
-
up(&arpt_mutex);
- }
+ module_put(t->me);
+ } else
+ ret = t ? PTR_ERR(t) : -ENOENT;
}
break;
break;
}
+ case ARPT_SO_GET_REVISION_TARGET: {
+ struct arpt_get_revision rev;
+
+ if (*len != sizeof(rev)) {
+ ret = -EINVAL;
+ break;
+ }
+ if (copy_from_user(&rev, user, sizeof(rev)) != 0) {
+ ret = -EFAULT;
+ break;
+ }
+
+ try_then_request_module(find_revision(rev.name, rev.revision,
+ target_revfn, &ret),
+ "arpt_%s", rev.name);
+ break;
+ }
+
default:
duprintf("do_arpt_get_ctl: unknown request %i\n", cmd);
ret = -EINVAL;
if (ret != 0)
return ret;
- if (!list_named_insert(&arpt_target, target)) {
- duprintf("arpt_register_target: `%s' already in list!\n",
- target->name);
- ret = -EINVAL;
- }
+ list_add(&target->list, &arpt_target);
up(&arpt_mutex);
+
return ret;
}
struct arpt_table_info *newinfo;
static struct arpt_table_info bootstrap
= { 0, 0, 0, { 0 }, { 0 }, { } };
+ void *loc_cpu_entry;
- newinfo = vmalloc(sizeof(struct arpt_table_info)
- + SMP_ALIGN(repl->size) *
- (highest_possible_processor_id()+1));
+ newinfo = alloc_table_info(repl->size);
if (!newinfo) {
ret = -ENOMEM;
return ret;
}
- memcpy(newinfo->entries, repl->entries, repl->size);
+
+ /* choose the copy on our node/cpu */
+ 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,
- newinfo, repl->size,
+ newinfo, loc_cpu_entry, repl->size,
repl->num_entries,
repl->hook_entry,
repl->underflow);
duprintf("arpt_register_table: translate table gives %d\n", ret);
if (ret != 0) {
- vfree(newinfo);
+ free_table_info(newinfo);
return ret;
}
ret = down_interruptible(&arpt_mutex);
if (ret != 0) {
- vfree(newinfo);
+ free_table_info(newinfo);
return ret;
}
return ret;
free_unlock:
- vfree(newinfo);
+ free_table_info(newinfo);
goto unlock;
}
void arpt_unregister_table(struct arpt_table *table)
{
+ void *loc_cpu_entry;
+
down(&arpt_mutex);
LIST_DELETE(&arpt_tables, table);
up(&arpt_mutex);
/* Decrease module usage counts and free resources */
- ARPT_ENTRY_ITERATE(table->private->entries, table->private->size,
+ loc_cpu_entry = table->private->entries[raw_smp_processor_id()];
+ ARPT_ENTRY_ITERATE(loc_cpu_entry, table->private->size,
cleanup_entry, NULL);
- vfree(table->private);
+ free_table_info(table->private);
}
/* The built-in targets: standard (NULL) and error. */
projects / linux-2.6 / blobdiff