#define CREATE_TRACE_POINTS
#include <trace/events/module.h>
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
#if 0
#define DEBUGP printk
#else
DEFINE_MUTEX(module_mutex);
EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
+#ifdef CONFIG_KGDB_KDB
+struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
+#endif /* CONFIG_KGDB_KDB */
+
/* Block module loading/unloading? */
int modules_disabled = 0;
#ifdef CONFIG_SMP
-static void *percpu_modalloc(unsigned long size, unsigned long align,
- const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
{
- void *ptr;
+ return mod->percpu;
+}
+static int percpu_modalloc(struct module *mod,
+ unsigned long size, unsigned long align)
+{
if (align > PAGE_SIZE) {
printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
- name, align, PAGE_SIZE);
+ mod->name, align, PAGE_SIZE);
align = PAGE_SIZE;
}
- ptr = __alloc_reserved_percpu(size, align);
- if (!ptr)
+ mod->percpu = __alloc_reserved_percpu(size, align);
+ if (!mod->percpu) {
printk(KERN_WARNING
"Could not allocate %lu bytes percpu data\n", size);
- return ptr;
+ return -ENOMEM;
+ }
+ mod->percpu_size = size;
+ return 0;
}
-static void percpu_modfree(void *freeme)
+static void percpu_modfree(struct module *mod)
{
- free_percpu(freeme);
+ free_percpu(mod->percpu);
}
static unsigned int find_pcpusec(Elf_Ehdr *hdr,
return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
}
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+static void percpu_modcopy(struct module *mod,
+ const void *from, unsigned long size)
{
int cpu;
for_each_possible_cpu(cpu)
- memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+ memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
+}
+
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+ struct module *mod;
+ unsigned int cpu;
+
+ preempt_disable();
+
+ list_for_each_entry_rcu(mod, &modules, list) {
+ if (!mod->percpu_size)
+ continue;
+ for_each_possible_cpu(cpu) {
+ void *start = per_cpu_ptr(mod->percpu, cpu);
+
+ if ((void *)addr >= start &&
+ (void *)addr < start + mod->percpu_size) {
+ preempt_enable();
+ return true;
+ }
+ }
+ }
+
+ preempt_enable();
+ return false;
}
#else /* ... !CONFIG_SMP */
-static inline void *percpu_modalloc(unsigned long size, unsigned long align,
- const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
{
return NULL;
}
-static inline void percpu_modfree(void *pcpuptr)
+static inline int percpu_modalloc(struct module *mod,
+ unsigned long size, unsigned long align)
+{
+ return -ENOMEM;
+}
+static inline void percpu_modfree(struct module *mod)
{
- BUG();
}
static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
Elf_Shdr *sechdrs,
{
return 0;
}
-static inline void percpu_modcopy(void *pcpudst, const void *src,
- unsigned long size)
+static inline void percpu_modcopy(struct module *mod,
+ const void *from, unsigned long size)
{
/* pcpusec should be 0, and size of that section should be 0. */
BUG_ON(size != 0);
}
+bool is_module_percpu_address(unsigned long addr)
+{
+ return false;
+}
#endif /* CONFIG_SMP */
static char last_unloaded_module[MODULE_NAME_LEN+1];
#ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
/* Init the unload section of the module. */
static void module_unload_init(struct module *mod)
{
int cpu;
INIT_LIST_HEAD(&mod->modules_which_use_me);
- for_each_possible_cpu(cpu)
- local_set(__module_ref_addr(mod, cpu), 0);
+ for_each_possible_cpu(cpu) {
+ per_cpu_ptr(mod->refptr, cpu)->incs = 0;
+ per_cpu_ptr(mod->refptr, cpu)->decs = 0;
+ }
+
/* Hold reference count during initialization. */
- local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
+ __this_cpu_write(mod->refptr->incs, 1);
/* Backwards compatibility macros put refcount during init. */
mod->waiter = current;
}
struct module_use *use;
int no_warn, err;
- if (b == NULL || already_uses(a, b)) return 1;
-
- /* If we're interrupted or time out, we fail. */
- if (wait_event_interruptible_timeout(
- module_wq, (err = strong_try_module_get(b)) != -EBUSY,
- 30 * HZ) <= 0) {
- printk("%s: gave up waiting for init of module %s.\n",
- a->name, b->name);
+ if (b == NULL || already_uses(a, b))
return 0;
- }
- /* If strong_try_module_get() returned a different error, we fail. */
+ /* If we're interrupted or time out, we fail. */
+ err = strong_try_module_get(b);
if (err)
- return 0;
+ return err;
DEBUGP("Allocating new usage for %s.\n", a->name);
use = kmalloc(sizeof(*use), GFP_ATOMIC);
if (!use) {
printk("%s: out of memory loading\n", a->name);
module_put(b);
- return 0;
+ return -ENOMEM;
}
use->module_which_uses = a;
list_add(&use->list, &b->modules_which_use_me);
no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name);
- return 1;
+ return 0;
}
EXPORT_SYMBOL_GPL(use_module);
unsigned int module_refcount(struct module *mod)
{
- unsigned int total = 0;
+ unsigned int incs = 0, decs = 0;
int cpu;
for_each_possible_cpu(cpu)
- total += local_read(__module_ref_addr(mod, cpu));
- return total;
+ decs += per_cpu_ptr(mod->refptr, cpu)->decs;
+ /*
+ * ensure the incs are added up after the decs.
+ * module_put ensures incs are visible before decs with smp_wmb.
+ *
+ * This 2-count scheme avoids the situation where the refcount
+ * for CPU0 is read, then CPU0 increments the module refcount,
+ * then CPU1 drops that refcount, then the refcount for CPU1 is
+ * read. We would record a decrement but not its corresponding
+ * increment so we would see a low count (disaster).
+ *
+ * Rare situation? But module_refcount can be preempted, and we
+ * might be tallying up 4096+ CPUs. So it is not impossible.
+ */
+ smp_rmb();
+ for_each_possible_cpu(cpu)
+ incs += per_cpu_ptr(mod->refptr, cpu)->incs;
+ return incs - decs;
}
EXPORT_SYMBOL(module_refcount);
return -EFAULT;
name[MODULE_NAME_LEN-1] = '\0';
- /* Create stop_machine threads since free_module relies on
- * a non-failing stop_machine call. */
- ret = stop_machine_create();
- if (ret)
- return ret;
-
- if (mutex_lock_interruptible(&module_mutex) != 0) {
- ret = -EINTR;
- goto out_stop;
- }
+ if (mutex_lock_interruptible(&module_mutex) != 0)
+ return -EINTR;
mod = find_module(name);
if (!mod) {
out:
mutex_unlock(&module_mutex);
-out_stop:
- stop_machine_destroy();
return ret;
}
void module_put(struct module *module)
{
if (module) {
- unsigned int cpu = get_cpu();
- local_dec(__module_ref_addr(module, cpu));
- trace_module_put(module, _RET_IP_,
- local_read(__module_ref_addr(module, cpu)));
+ preempt_disable();
+ smp_wmb(); /* see comment in module_refcount */
+ __this_cpu_inc(module->refptr->decs);
+
+ trace_module_put(module, _RET_IP_);
/* Maybe they're waiting for us to drop reference? */
if (unlikely(!module_is_live(module)))
wake_up_process(module->waiter);
- put_cpu();
+ preempt_enable();
}
}
EXPORT_SYMBOL(module_put);
int use_module(struct module *a, struct module *b)
{
- return strong_try_module_get(b) == 0;
+ return strong_try_module_get(b);
}
EXPORT_SYMBOL_GPL(use_module);
struct module *owner;
const struct kernel_symbol *sym;
const unsigned long *crc;
+ DEFINE_WAIT(wait);
+ int err;
+ long timeleft = 30 * HZ;
+again:
sym = find_symbol(name, &owner, &crc,
!(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
- /* use_module can fail due to OOM,
- or module initialization or unloading */
- if (sym) {
- if (!check_version(sechdrs, versindex, name, mod, crc, owner)
- || !use_module(mod, owner))
- sym = NULL;
+ if (!sym)
+ return NULL;
+
+ if (!check_version(sechdrs, versindex, name, mod, crc, owner))
+ return NULL;
+
+ prepare_to_wait(&module_wq, &wait, TASK_INTERRUPTIBLE);
+ err = use_module(mod, owner);
+ if (likely(!err) || err != -EBUSY || signal_pending(current)) {
+ finish_wait(&module_wq, &wait);
+ return err ? NULL : sym;
}
- return sym;
+
+ /* Module is still loading. Drop lock and wait. */
+ mutex_unlock(&module_mutex);
+ timeleft = schedule_timeout(timeleft);
+ mutex_lock(&module_mutex);
+ finish_wait(&module_wq, &wait);
+
+ /* Module might be gone entirely, or replaced. Re-lookup. */
+ if (timeleft)
+ goto again;
+
+ printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n",
+ mod->name, owner->name);
+ return NULL;
}
/*
if (sattr->name == NULL)
goto out;
sect_attrs->nsections++;
+ sysfs_attr_init(&sattr->mattr.attr);
sattr->mattr.show = module_sect_show;
sattr->mattr.store = NULL;
sattr->mattr.attr.name = sattr->name;
struct bin_attribute attrs[0];
};
-static ssize_t module_notes_read(struct kobject *kobj,
+static ssize_t module_notes_read(struct file *filp, struct kobject *kobj,
struct bin_attribute *bin_attr,
char *buf, loff_t pos, size_t count)
{
if (sect_empty(&sechdrs[i]))
continue;
if (sechdrs[i].sh_type == SHT_NOTE) {
+ sysfs_bin_attr_init(nattr);
nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
nattr->attr.mode = S_IRUGO;
nattr->size = sechdrs[i].sh_size;
if (!attr->test ||
(attr->test && attr->test(mod))) {
memcpy(temp_attr, attr, sizeof(*temp_attr));
+ sysfs_attr_init(&temp_attr->attr);
error = sysfs_create_file(&mod->mkobj.kobj,&temp_attr->attr);
++temp_attr;
}
/* This may be NULL, but that's OK */
module_free(mod, mod->module_init);
kfree(mod->args);
- if (mod->percpu)
- percpu_modfree(mod->percpu);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+ percpu_modfree(mod);
+#if defined(CONFIG_MODULE_UNLOAD)
if (mod->refptr)
- percpu_modfree(mod->refptr);
+ free_percpu(mod->refptr);
#endif
/* Free lock-classes: */
lockdep_free_key_range(mod->module_core, mod->core_size);
default:
/* Divert to percpu allocation if a percpu var. */
if (sym[i].st_shndx == pcpuindex)
- secbase = (unsigned long)mod->percpu;
+ secbase = (unsigned long)mod_percpu(mod);
else
secbase = sechdrs[sym[i].st_shndx].sh_addr;
sym[i].st_value += secbase;
unsigned int modindex, versindex, infoindex, pcpuindex;
struct module *mod;
long err = 0;
- void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+ void *ptr = NULL; /* Stops spurious gcc warning */
unsigned long symoffs, stroffs, *strmap;
mm_segment_t old_fs;
if (pcpuindex) {
/* We have a special allocation for this section. */
- percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
- sechdrs[pcpuindex].sh_addralign,
- mod->name);
- if (!percpu) {
- err = -ENOMEM;
+ err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size,
+ sechdrs[pcpuindex].sh_addralign);
+ if (err)
goto free_mod;
- }
sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
- mod->percpu = percpu;
}
/* Determine total sizes, and put offsets in sh_entsize. For now
mod = (void *)sechdrs[modindex].sh_addr;
kmemleak_load_module(mod, hdr, sechdrs, secstrings);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
- mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
- mod->name);
+#if defined(CONFIG_MODULE_UNLOAD)
+ mod->refptr = alloc_percpu(struct module_ref);
if (!mod->refptr) {
err = -ENOMEM;
goto free_init;
sort_extable(mod->extable, mod->extable + mod->num_exentries);
/* Finally, copy percpu area over. */
- percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
+ percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr,
sechdrs[pcpuindex].sh_size);
add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
kobject_put(&mod->mkobj.kobj);
free_unload:
module_unload_free(mod);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
- percpu_modfree(mod->refptr);
+#if defined(CONFIG_MODULE_UNLOAD)
+ free_percpu(mod->refptr);
free_init:
#endif
module_free(mod, mod->module_init);
module_free(mod, mod->module_core);
/* mod will be freed with core. Don't access it beyond this line! */
free_percpu:
- if (percpu)
- percpu_modfree(percpu);
+ percpu_modfree(mod);
free_mod:
kfree(args);
kfree(strmap);