summaryrefslogtreecommitdiff
path: root/kernel/module.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/module.c')
-rw-r--r--kernel/module.c300
1 files changed, 182 insertions, 118 deletions
diff --git a/kernel/module.c b/kernel/module.c
index 88cec1ddb1e3..ec53f594e9c9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -42,7 +42,6 @@
#include <linux/vermagic.h>
#include <linux/notifier.h>
#include <linux/sched.h>
-#include <linux/stop_machine.h>
#include <linux/device.h>
#include <linux/string.h>
#include <linux/mutex.h>
@@ -98,7 +97,7 @@
* 1) List of modules (also safely readable with preempt_disable),
* 2) module_use links,
* 3) module_addr_min/module_addr_max.
- * (delete uses stop_machine/add uses RCU list operations). */
+ * (delete and add uses RCU list operations). */
DEFINE_MUTEX(module_mutex);
EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
@@ -158,13 +157,13 @@ static BLOCKING_NOTIFIER_HEAD(module_notify_list);
* Protected by module_mutex. */
static unsigned long module_addr_min = -1UL, module_addr_max = 0;
-int register_module_notifier(struct notifier_block * nb)
+int register_module_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&module_notify_list, nb);
}
EXPORT_SYMBOL(register_module_notifier);
-int unregister_module_notifier(struct notifier_block * nb)
+int unregister_module_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&module_notify_list, nb);
}
@@ -628,18 +627,23 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
EXPORT_TRACEPOINT_SYMBOL(module_get);
+/* MODULE_REF_BASE is the base reference count by kmodule loader. */
+#define MODULE_REF_BASE 1
+
/* Init the unload section of the module. */
static int module_unload_init(struct module *mod)
{
- mod->refptr = alloc_percpu(struct module_ref);
- if (!mod->refptr)
- return -ENOMEM;
+ /*
+ * Initialize reference counter to MODULE_REF_BASE.
+ * refcnt == 0 means module is going.
+ */
+ atomic_set(&mod->refcnt, MODULE_REF_BASE);
INIT_LIST_HEAD(&mod->source_list);
INIT_LIST_HEAD(&mod->target_list);
/* Hold reference count during initialization. */
- raw_cpu_write(mod->refptr->incs, 1);
+ atomic_inc(&mod->refcnt);
return 0;
}
@@ -721,8 +725,6 @@ static void module_unload_free(struct module *mod)
kfree(use);
}
mutex_unlock(&module_mutex);
-
- free_percpu(mod->refptr);
}
#ifdef CONFIG_MODULE_FORCE_UNLOAD
@@ -740,60 +742,48 @@ static inline int try_force_unload(unsigned int flags)
}
#endif /* CONFIG_MODULE_FORCE_UNLOAD */
-struct stopref
+/* Try to release refcount of module, 0 means success. */
+static int try_release_module_ref(struct module *mod)
{
- struct module *mod;
- int flags;
- int *forced;
-};
+ int ret;
-/* Whole machine is stopped with interrupts off when this runs. */
-static int __try_stop_module(void *_sref)
-{
- struct stopref *sref = _sref;
+ /* Try to decrement refcnt which we set at loading */
+ ret = atomic_sub_return(MODULE_REF_BASE, &mod->refcnt);
+ BUG_ON(ret < 0);
+ if (ret)
+ /* Someone can put this right now, recover with checking */
+ ret = atomic_add_unless(&mod->refcnt, MODULE_REF_BASE, 0);
+
+ return ret;
+}
+static int try_stop_module(struct module *mod, int flags, int *forced)
+{
/* If it's not unused, quit unless we're forcing. */
- if (module_refcount(sref->mod) != 0) {
- if (!(*sref->forced = try_force_unload(sref->flags)))
+ if (try_release_module_ref(mod) != 0) {
+ *forced = try_force_unload(flags);
+ if (!(*forced))
return -EWOULDBLOCK;
}
/* Mark it as dying. */
- sref->mod->state = MODULE_STATE_GOING;
- return 0;
-}
+ mod->state = MODULE_STATE_GOING;
-static int try_stop_module(struct module *mod, int flags, int *forced)
-{
- struct stopref sref = { mod, flags, forced };
-
- return stop_machine(__try_stop_module, &sref, NULL);
+ return 0;
}
-unsigned long module_refcount(struct module *mod)
+/**
+ * module_refcount - return the refcount or -1 if unloading
+ *
+ * @mod: the module we're checking
+ *
+ * Returns:
+ * -1 if the module is in the process of unloading
+ * otherwise the number of references in the kernel to the module
+ */
+int module_refcount(struct module *mod)
{
- unsigned long incs = 0, decs = 0;
- int cpu;
-
- for_each_possible_cpu(cpu)
- 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;
+ return atomic_read(&mod->refcnt) - MODULE_REF_BASE;
}
EXPORT_SYMBOL(module_refcount);
@@ -875,10 +865,12 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod)
struct module_use *use;
int printed_something = 0;
- seq_printf(m, " %lu ", module_refcount(mod));
+ seq_printf(m, " %i ", module_refcount(mod));
- /* Always include a trailing , so userspace can differentiate
- between this and the old multi-field proc format. */
+ /*
+ * Always include a trailing , so userspace can differentiate
+ * between this and the old multi-field proc format.
+ */
list_for_each_entry(use, &mod->source_list, source_list) {
printed_something = 1;
seq_printf(m, "%s,", use->source->name);
@@ -886,11 +878,11 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod)
if (mod->init != NULL && mod->exit == NULL) {
printed_something = 1;
- seq_printf(m, "[permanent],");
+ seq_puts(m, "[permanent],");
}
if (!printed_something)
- seq_printf(m, "-");
+ seq_puts(m, "-");
}
void __symbol_put(const char *symbol)
@@ -925,7 +917,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr);
static ssize_t show_refcnt(struct module_attribute *mattr,
struct module_kobject *mk, char *buffer)
{
- return sprintf(buffer, "%lu\n", module_refcount(mk->mod));
+ return sprintf(buffer, "%i\n", module_refcount(mk->mod));
}
static struct module_attribute modinfo_refcnt =
@@ -935,7 +927,7 @@ void __module_get(struct module *module)
{
if (module) {
preempt_disable();
- __this_cpu_inc(module->refptr->incs);
+ atomic_inc(&module->refcnt);
trace_module_get(module, _RET_IP_);
preempt_enable();
}
@@ -948,11 +940,11 @@ bool try_module_get(struct module *module)
if (module) {
preempt_disable();
-
- if (likely(module_is_live(module))) {
- __this_cpu_inc(module->refptr->incs);
+ /* Note: here, we can fail to get a reference */
+ if (likely(module_is_live(module) &&
+ atomic_inc_not_zero(&module->refcnt) != 0))
trace_module_get(module, _RET_IP_);
- } else
+ else
ret = false;
preempt_enable();
@@ -963,11 +955,12 @@ EXPORT_SYMBOL(try_module_get);
void module_put(struct module *module)
{
+ int ret;
+
if (module) {
preempt_disable();
- smp_wmb(); /* see comment in module_refcount */
- __this_cpu_inc(module->refptr->decs);
-
+ ret = atomic_dec_if_positive(&module->refcnt);
+ WARN_ON(ret < 0); /* Failed to put refcount */
trace_module_put(module, _RET_IP_);
preempt_enable();
}
@@ -978,7 +971,7 @@ EXPORT_SYMBOL(module_put);
static inline void print_unload_info(struct seq_file *m, struct module *mod)
{
/* We don't know the usage count, or what modules are using. */
- seq_printf(m, " - -");
+ seq_puts(m, " - -");
}
static inline void module_unload_free(struct module *mod)
@@ -1131,7 +1124,7 @@ static unsigned long maybe_relocated(unsigned long crc,
static int check_version(Elf_Shdr *sechdrs,
unsigned int versindex,
const char *symname,
- struct module *mod,
+ struct module *mod,
const unsigned long *crc,
const struct module *crc_owner)
{
@@ -1165,7 +1158,7 @@ static int check_version(Elf_Shdr *sechdrs,
return 0;
bad_version:
- printk("%s: disagrees about version of symbol %s\n",
+ pr_warn("%s: disagrees about version of symbol %s\n",
mod->name, symname);
return 0;
}
@@ -1200,7 +1193,7 @@ static inline int same_magic(const char *amagic, const char *bmagic,
static inline int check_version(Elf_Shdr *sechdrs,
unsigned int versindex,
const char *symname,
- struct module *mod,
+ struct module *mod,
const unsigned long *crc,
const struct module *crc_owner)
{
@@ -1232,6 +1225,12 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
const unsigned long *crc;
int err;
+ /*
+ * The module_mutex should not be a heavily contended lock;
+ * if we get the occasional sleep here, we'll go an extra iteration
+ * in the wait_event_interruptible(), which is harmless.
+ */
+ sched_annotate_sleep();
mutex_lock(&module_mutex);
sym = find_symbol(name, &owner, &crc,
!(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
@@ -1288,15 +1287,13 @@ static inline bool sect_empty(const Elf_Shdr *sect)
return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
}
-struct module_sect_attr
-{
+struct module_sect_attr {
struct module_attribute mattr;
char *name;
unsigned long address;
};
-struct module_sect_attrs
-{
+struct module_sect_attrs {
struct attribute_group grp;
unsigned int nsections;
struct module_sect_attr attrs[0];
@@ -1550,7 +1547,8 @@ static int module_add_modinfo_attrs(struct module *mod)
(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);
+ error = sysfs_create_file(&mod->mkobj.kobj,
+ &temp_attr->attr);
++temp_attr;
}
}
@@ -1566,7 +1564,7 @@ static void module_remove_modinfo_attrs(struct module *mod)
/* pick a field to test for end of list */
if (!attr->attr.name)
break;
- sysfs_remove_file(&mod->mkobj.kobj,&attr->attr);
+ sysfs_remove_file(&mod->mkobj.kobj, &attr->attr);
if (attr->free)
attr->free(mod);
}
@@ -1697,18 +1695,6 @@ static void mod_sysfs_teardown(struct module *mod)
mod_sysfs_fini(mod);
}
-/*
- * unlink the module with the whole machine is stopped with interrupts off
- * - this defends against kallsyms not taking locks
- */
-static int __unlink_module(void *_mod)
-{
- struct module *mod = _mod;
- list_del(&mod->list);
- module_bug_cleanup(mod);
- return 0;
-}
-
#ifdef CONFIG_DEBUG_SET_MODULE_RONX
/*
* LKM RO/NX protection: protect module's text/ro-data
@@ -1824,7 +1810,7 @@ static void unset_module_core_ro_nx(struct module *mod) { }
static void unset_module_init_ro_nx(struct module *mod) { }
#endif
-void __weak module_free(struct module *mod, void *module_region)
+void __weak module_memfree(void *module_region)
{
vfree(module_region);
}
@@ -1833,6 +1819,10 @@ void __weak module_arch_cleanup(struct module *mod)
{
}
+void __weak module_arch_freeing_init(struct module *mod)
+{
+}
+
/* Free a module, remove from lists, etc. */
static void free_module(struct module *mod)
{
@@ -1860,21 +1850,27 @@ static void free_module(struct module *mod)
/* Now we can delete it from the lists */
mutex_lock(&module_mutex);
- stop_machine(__unlink_module, mod, NULL);
+ /* Unlink carefully: kallsyms could be walking list. */
+ list_del_rcu(&mod->list);
+ /* Remove this module from bug list, this uses list_del_rcu */
+ module_bug_cleanup(mod);
+ /* Wait for RCU synchronizing before releasing mod->list and buglist. */
+ synchronize_rcu();
mutex_unlock(&module_mutex);
/* This may be NULL, but that's OK */
unset_module_init_ro_nx(mod);
- module_free(mod, mod->module_init);
+ module_arch_freeing_init(mod);
+ module_memfree(mod->module_init);
kfree(mod->args);
percpu_modfree(mod);
- /* Free lock-classes: */
+ /* Free lock-classes; relies on the preceding sync_rcu(). */
lockdep_free_key_range(mod->module_core, mod->core_size);
/* Finally, free the core (containing the module structure) */
unset_module_core_ro_nx(mod);
- module_free(mod, mod->module_core);
+ module_memfree(mod->module_core);
#ifdef CONFIG_MPU
update_protections(current->mm);
@@ -1955,7 +1951,7 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
/* We compiled with -fno-common. These are not
supposed to happen. */
pr_debug("Common symbol: %s\n", name);
- printk("%s: please compile with -fno-common\n",
+ pr_warn("%s: please compile with -fno-common\n",
mod->name);
ret = -ENOEXEC;
break;
@@ -2259,7 +2255,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info)
}
static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
- unsigned int shnum)
+ unsigned int shnum)
{
const Elf_Shdr *sec;
@@ -2315,11 +2311,13 @@ static void layout_symtab(struct module *mod, struct load_info *info)
info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym);
mod->core_size += strtab_size;
+ mod->core_size = debug_align(mod->core_size);
/* Put string table section at end of init part of module. */
strsect->sh_flags |= SHF_ALLOC;
strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect,
info->index.str) | INIT_OFFSET_MASK;
+ mod->init_size = debug_align(mod->init_size);
pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
}
@@ -2481,6 +2479,23 @@ static int elf_header_check(struct load_info *info)
return 0;
}
+#define COPY_CHUNK_SIZE (16*PAGE_SIZE)
+
+static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned long len)
+{
+ do {
+ unsigned long n = min(len, COPY_CHUNK_SIZE);
+
+ if (copy_from_user(dst, usrc, n) != 0)
+ return -EFAULT;
+ cond_resched();
+ dst += n;
+ usrc += n;
+ len -= n;
+ } while (len);
+ return 0;
+}
+
/* Sets info->hdr and info->len. */
static int copy_module_from_user(const void __user *umod, unsigned long len,
struct load_info *info)
@@ -2500,7 +2515,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
if (!info->hdr)
return -ENOMEM;
- if (copy_from_user(info->hdr, umod, info->len) != 0) {
+ if (copy_chunked_from_user(info->hdr, umod, info->len) != 0) {
vfree(info->hdr);
return -EFAULT;
}
@@ -2735,7 +2750,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
* This shouldn't happen with same compiler and binutils
* building all parts of the module.
*/
- printk(KERN_WARNING "%s: has both .ctors and .init_array.\n",
+ pr_warn("%s: has both .ctors and .init_array.\n",
mod->name);
return -EINVAL;
}
@@ -2809,7 +2824,7 @@ static int move_module(struct module *mod, struct load_info *info)
*/
kmemleak_ignore(ptr);
if (!ptr) {
- module_free(mod, mod->module_core);
+ module_memfree(mod->module_core);
return -ENOMEM;
}
memset(ptr, 0, mod->init_size);
@@ -2954,8 +2969,9 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
static void module_deallocate(struct module *mod, struct load_info *info)
{
percpu_modfree(mod);
- module_free(mod, mod->module_init);
- module_free(mod, mod->module_core);
+ module_arch_freeing_init(mod);
+ module_memfree(mod->module_init);
+ module_memfree(mod->module_core);
}
int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -2987,6 +3003,12 @@ static bool finished_loading(const char *name)
struct module *mod;
bool ret;
+ /*
+ * The module_mutex should not be a heavily contended lock;
+ * if we get the occasional sleep here, we'll go an extra iteration
+ * in the wait_event_interruptible(), which is harmless.
+ */
+ sched_annotate_sleep();
mutex_lock(&module_mutex);
mod = find_module_all(name, strlen(name), true);
ret = !mod || mod->state == MODULE_STATE_LIVE
@@ -3007,10 +3029,36 @@ static void do_mod_ctors(struct module *mod)
#endif
}
-/* This is where the real work happens */
-static int do_init_module(struct module *mod)
+/* For freeing module_init on success, in case kallsyms traversing */
+struct mod_initfree {
+ struct rcu_head rcu;
+ void *module_init;
+};
+
+static void do_free_init(struct rcu_head *head)
+{
+ struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
+ module_memfree(m->module_init);
+ kfree(m);
+}
+
+/*
+ * This is where the real work happens.
+ *
+ * Keep it uninlined to provide a reliable breakpoint target, e.g. for the gdb
+ * helper command 'lx-symbols'.
+ */
+static noinline int do_init_module(struct module *mod)
{
int ret = 0;
+ struct mod_initfree *freeinit;
+
+ freeinit = kmalloc(sizeof(*freeinit), GFP_KERNEL);
+ if (!freeinit) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ freeinit->module_init = mod->module_init;
/*
* We want to find out whether @mod uses async during init. Clear
@@ -3023,16 +3071,7 @@ static int do_init_module(struct module *mod)
if (mod->init != NULL)
ret = do_one_initcall(mod->init);
if (ret < 0) {
- /* Init routine failed: abort. Try to protect us from
- buggy refcounters. */
- mod->state = MODULE_STATE_GOING;
- synchronize_sched();
- module_put(mod);
- blocking_notifier_call_chain(&module_notify_list,
- MODULE_STATE_GOING, mod);
- free_module(mod);
- wake_up_all(&module_wq);
- return ret;
+ goto fail_free_freeinit;
}
if (ret > 0) {
pr_warn("%s: '%s'->init suspiciously returned %d, it should "
@@ -3077,15 +3116,35 @@ static int do_init_module(struct module *mod)
mod->strtab = mod->core_strtab;
#endif
unset_module_init_ro_nx(mod);
- module_free(mod, mod->module_init);
+ module_arch_freeing_init(mod);
mod->module_init = NULL;
mod->init_size = 0;
mod->init_ro_size = 0;
mod->init_text_size = 0;
+ /*
+ * We want to free module_init, but be aware that kallsyms may be
+ * walking this with preempt disabled. In all the failure paths,
+ * we call synchronize_rcu/synchronize_sched, but we don't want
+ * to slow down the success path, so use actual RCU here.
+ */
+ call_rcu(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
wake_up_all(&module_wq);
return 0;
+
+fail_free_freeinit:
+ kfree(freeinit);
+fail:
+ /* Try to protect us from buggy refcounters. */
+ mod->state = MODULE_STATE_GOING;
+ synchronize_sched();
+ module_put(mod);
+ blocking_notifier_call_chain(&module_notify_list,
+ MODULE_STATE_GOING, mod);
+ free_module(mod);
+ wake_up_all(&module_wq);
+ return ret;
}
static int may_init_module(void)
@@ -3176,7 +3235,7 @@ out:
static int unknown_module_param_cb(char *param, char *val, const char *modname)
{
- /* Check for magic 'dyndbg' arg */
+ /* Check for magic 'dyndbg' arg */
int ret = ddebug_dyndbg_module_param_cb(param, val, modname);
if (ret != 0)
pr_warn("%s: unknown parameter '%s' ignored\n", modname, param);
@@ -3216,7 +3275,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
mod->sig_ok = info->sig_ok;
if (!mod->sig_ok) {
pr_notice_once("%s: module verification failed: signature "
- "and/or required key missing - tainting "
+ "and/or required key missing - tainting "
"kernel\n", mod->name);
add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK);
}
@@ -3326,8 +3385,13 @@ static int load_module(struct load_info *info, const char __user *uargs,
/* Unlink carefully: kallsyms could be walking list. */
list_del_rcu(&mod->list);
wake_up_all(&module_wq);
+ /* Wait for RCU synchronizing before releasing mod->list. */
+ synchronize_rcu();
mutex_unlock(&module_mutex);
free_module:
+ /* Free lock-classes; relies on the preceding sync_rcu() */
+ lockdep_free_key_range(mod->module_core, mod->core_size);
+
module_deallocate(mod, info);
free_copy:
free_copy(info);
@@ -3659,8 +3723,8 @@ static int m_show(struct seq_file *m, void *p)
/* Informative for users. */
seq_printf(m, " %s",
- mod->state == MODULE_STATE_GOING ? "Unloading":
- mod->state == MODULE_STATE_COMING ? "Loading":
+ mod->state == MODULE_STATE_GOING ? "Unloading" :
+ mod->state == MODULE_STATE_COMING ? "Loading" :
"Live");
/* Used by oprofile and other similar tools. */
seq_printf(m, " 0x%pK", mod->module_core);
@@ -3669,7 +3733,7 @@ static int m_show(struct seq_file *m, void *p)
if (mod->taints)
seq_printf(m, " %s", module_flags(mod, buf));
- seq_printf(m, "\n");
+ seq_puts(m, "\n");
return 0;
}