mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Srivatsa S. Bhat](/assets/img/avatar_default.png)
Commit a144c6a
(PM: Print a warning if firmware is requested when tasks
are frozen) introduced usermodehelper_is_disabled() to warn and exit
immediately if firmware is requested when usermodehelpers are disabled.
However, it is racy. Consider the following scenario, currently used in
drivers/base/firmware_class.c:
...
if (usermodehelper_is_disabled())
goto out;
/* Do actual work */
...
out:
return err;
Nothing prevents someone from disabling usermodehelpers just after the check
in the 'if' condition, which means that it is quite possible to try doing the
"actual work" with usermodehelpers disabled, leading to undesirable
consequences.
In particular, this race condition in _request_firmware() causes task freezing
failures whenever suspend/hibernation is in progress because, it wrongly waits
to get the firmware/microcode image from userspace when actually the
usermodehelpers are disabled or userspace has been frozen.
Some of the example scenarios that cause freezing failures due to this race
are those that depend on userspace via request_firmware(), such as x86
microcode module initialization and microcode image reload.
Previous discussions about this issue can be found at:
http://thread.gmane.org/gmane.linux.kernel/1198291/focus=1200591
This patch adds proper synchronization to fix this issue.
It is to be noted that this patchset fixes the freezing failures but doesn't
remove the warnings. IOW, it does not attempt to add explicit synchronization
to x86 microcode driver to avoid requesting microcode image at inopportune
moments. Because, the warnings were introduced to highlight such cases, in the
first place. And we need not silence the warnings, since we take care of the
*real* problem (freezing failure) and hence, after that, the warnings are
pretty harmless anyway.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
552 lines
15 KiB
C
552 lines
15 KiB
C
/*
|
|
kmod, the new module loader (replaces kerneld)
|
|
Kirk Petersen
|
|
|
|
Reorganized not to be a daemon by Adam Richter, with guidance
|
|
from Greg Zornetzer.
|
|
|
|
Modified to avoid chroot and file sharing problems.
|
|
Mikael Pettersson
|
|
|
|
Limit the concurrent number of kmod modprobes to catch loops from
|
|
"modprobe needs a service that is in a module".
|
|
Keith Owens <kaos@ocs.com.au> December 1999
|
|
|
|
Unblock all signals when we exec a usermode process.
|
|
Shuu Yamaguchi <shuu@wondernetworkresources.com> December 2000
|
|
|
|
call_usermodehelper wait flag, and remove exec_usermodehelper.
|
|
Rusty Russell <rusty@rustcorp.com.au> Jan 2003
|
|
*/
|
|
#include <linux/module.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/kmod.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/cred.h>
|
|
#include <linux/file.h>
|
|
#include <linux/fdtable.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/security.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/init.h>
|
|
#include <linux/resource.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/rwsem.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <trace/events/module.h>
|
|
|
|
extern int max_threads;
|
|
|
|
static struct workqueue_struct *khelper_wq;
|
|
|
|
#define CAP_BSET (void *)1
|
|
#define CAP_PI (void *)2
|
|
|
|
static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
|
|
static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
|
|
static DEFINE_SPINLOCK(umh_sysctl_lock);
|
|
static DECLARE_RWSEM(umhelper_sem);
|
|
|
|
#ifdef CONFIG_MODULES
|
|
|
|
/*
|
|
modprobe_path is set via /proc/sys.
|
|
*/
|
|
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
|
|
|
|
/**
|
|
* __request_module - try to load a kernel module
|
|
* @wait: wait (or not) for the operation to complete
|
|
* @fmt: printf style format string for the name of the module
|
|
* @...: arguments as specified in the format string
|
|
*
|
|
* Load a module using the user mode module loader. The function returns
|
|
* zero on success or a negative errno code on failure. Note that a
|
|
* successful module load does not mean the module did not then unload
|
|
* and exit on an error of its own. Callers must check that the service
|
|
* they requested is now available not blindly invoke it.
|
|
*
|
|
* If module auto-loading support is disabled then this function
|
|
* becomes a no-operation.
|
|
*/
|
|
int __request_module(bool wait, const char *fmt, ...)
|
|
{
|
|
va_list args;
|
|
char module_name[MODULE_NAME_LEN];
|
|
unsigned int max_modprobes;
|
|
int ret;
|
|
char *argv[] = { modprobe_path, "-q", "--", module_name, NULL };
|
|
static char *envp[] = { "HOME=/",
|
|
"TERM=linux",
|
|
"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
|
|
NULL };
|
|
static atomic_t kmod_concurrent = ATOMIC_INIT(0);
|
|
#define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */
|
|
static int kmod_loop_msg;
|
|
|
|
va_start(args, fmt);
|
|
ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
|
|
va_end(args);
|
|
if (ret >= MODULE_NAME_LEN)
|
|
return -ENAMETOOLONG;
|
|
|
|
ret = security_kernel_module_request(module_name);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/* If modprobe needs a service that is in a module, we get a recursive
|
|
* loop. Limit the number of running kmod threads to max_threads/2 or
|
|
* MAX_KMOD_CONCURRENT, whichever is the smaller. A cleaner method
|
|
* would be to run the parents of this process, counting how many times
|
|
* kmod was invoked. That would mean accessing the internals of the
|
|
* process tables to get the command line, proc_pid_cmdline is static
|
|
* and it is not worth changing the proc code just to handle this case.
|
|
* KAO.
|
|
*
|
|
* "trace the ppid" is simple, but will fail if someone's
|
|
* parent exits. I think this is as good as it gets. --RR
|
|
*/
|
|
max_modprobes = min(max_threads/2, MAX_KMOD_CONCURRENT);
|
|
atomic_inc(&kmod_concurrent);
|
|
if (atomic_read(&kmod_concurrent) > max_modprobes) {
|
|
/* We may be blaming an innocent here, but unlikely */
|
|
if (kmod_loop_msg < 5) {
|
|
printk(KERN_ERR
|
|
"request_module: runaway loop modprobe %s\n",
|
|
module_name);
|
|
kmod_loop_msg++;
|
|
}
|
|
atomic_dec(&kmod_concurrent);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
trace_module_request(module_name, wait, _RET_IP_);
|
|
|
|
ret = call_usermodehelper_fns(modprobe_path, argv, envp,
|
|
wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC,
|
|
NULL, NULL, NULL);
|
|
|
|
atomic_dec(&kmod_concurrent);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__request_module);
|
|
#endif /* CONFIG_MODULES */
|
|
|
|
/*
|
|
* This is the task which runs the usermode application
|
|
*/
|
|
static int ____call_usermodehelper(void *data)
|
|
{
|
|
struct subprocess_info *sub_info = data;
|
|
struct cred *new;
|
|
int retval;
|
|
|
|
spin_lock_irq(¤t->sighand->siglock);
|
|
flush_signal_handlers(current, 1);
|
|
spin_unlock_irq(¤t->sighand->siglock);
|
|
|
|
/* We can run anywhere, unlike our parent keventd(). */
|
|
set_cpus_allowed_ptr(current, cpu_all_mask);
|
|
|
|
/*
|
|
* Our parent is keventd, which runs with elevated scheduling priority.
|
|
* Avoid propagating that into the userspace child.
|
|
*/
|
|
set_user_nice(current, 0);
|
|
|
|
retval = -ENOMEM;
|
|
new = prepare_kernel_cred(current);
|
|
if (!new)
|
|
goto fail;
|
|
|
|
spin_lock(&umh_sysctl_lock);
|
|
new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset);
|
|
new->cap_inheritable = cap_intersect(usermodehelper_inheritable,
|
|
new->cap_inheritable);
|
|
spin_unlock(&umh_sysctl_lock);
|
|
|
|
if (sub_info->init) {
|
|
retval = sub_info->init(sub_info, new);
|
|
if (retval) {
|
|
abort_creds(new);
|
|
goto fail;
|
|
}
|
|
}
|
|
|
|
commit_creds(new);
|
|
|
|
retval = kernel_execve(sub_info->path,
|
|
(const char *const *)sub_info->argv,
|
|
(const char *const *)sub_info->envp);
|
|
|
|
/* Exec failed? */
|
|
fail:
|
|
sub_info->retval = retval;
|
|
do_exit(0);
|
|
}
|
|
|
|
void call_usermodehelper_freeinfo(struct subprocess_info *info)
|
|
{
|
|
if (info->cleanup)
|
|
(*info->cleanup)(info);
|
|
kfree(info);
|
|
}
|
|
EXPORT_SYMBOL(call_usermodehelper_freeinfo);
|
|
|
|
/* Keventd can't block, but this (a child) can. */
|
|
static int wait_for_helper(void *data)
|
|
{
|
|
struct subprocess_info *sub_info = data;
|
|
pid_t pid;
|
|
|
|
/* If SIGCLD is ignored sys_wait4 won't populate the status. */
|
|
spin_lock_irq(¤t->sighand->siglock);
|
|
current->sighand->action[SIGCHLD-1].sa.sa_handler = SIG_DFL;
|
|
spin_unlock_irq(¤t->sighand->siglock);
|
|
|
|
pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
|
|
if (pid < 0) {
|
|
sub_info->retval = pid;
|
|
} else {
|
|
int ret = -ECHILD;
|
|
/*
|
|
* Normally it is bogus to call wait4() from in-kernel because
|
|
* wait4() wants to write the exit code to a userspace address.
|
|
* But wait_for_helper() always runs as keventd, and put_user()
|
|
* to a kernel address works OK for kernel threads, due to their
|
|
* having an mm_segment_t which spans the entire address space.
|
|
*
|
|
* Thus the __user pointer cast is valid here.
|
|
*/
|
|
sys_wait4(pid, (int __user *)&ret, 0, NULL);
|
|
|
|
/*
|
|
* If ret is 0, either ____call_usermodehelper failed and the
|
|
* real error code is already in sub_info->retval or
|
|
* sub_info->retval is 0 anyway, so don't mess with it then.
|
|
*/
|
|
if (ret)
|
|
sub_info->retval = ret;
|
|
}
|
|
|
|
complete(sub_info->complete);
|
|
return 0;
|
|
}
|
|
|
|
/* This is run by khelper thread */
|
|
static void __call_usermodehelper(struct work_struct *work)
|
|
{
|
|
struct subprocess_info *sub_info =
|
|
container_of(work, struct subprocess_info, work);
|
|
enum umh_wait wait = sub_info->wait;
|
|
pid_t pid;
|
|
|
|
/* CLONE_VFORK: wait until the usermode helper has execve'd
|
|
* successfully We need the data structures to stay around
|
|
* until that is done. */
|
|
if (wait == UMH_WAIT_PROC)
|
|
pid = kernel_thread(wait_for_helper, sub_info,
|
|
CLONE_FS | CLONE_FILES | SIGCHLD);
|
|
else
|
|
pid = kernel_thread(____call_usermodehelper, sub_info,
|
|
CLONE_VFORK | SIGCHLD);
|
|
|
|
switch (wait) {
|
|
case UMH_NO_WAIT:
|
|
call_usermodehelper_freeinfo(sub_info);
|
|
break;
|
|
|
|
case UMH_WAIT_PROC:
|
|
if (pid > 0)
|
|
break;
|
|
/* FALLTHROUGH */
|
|
case UMH_WAIT_EXEC:
|
|
if (pid < 0)
|
|
sub_info->retval = pid;
|
|
complete(sub_info->complete);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If set, call_usermodehelper_exec() will exit immediately returning -EBUSY
|
|
* (used for preventing user land processes from being created after the user
|
|
* land has been frozen during a system-wide hibernation or suspend operation).
|
|
* Should always be manipulated under umhelper_sem acquired for write.
|
|
*/
|
|
static int usermodehelper_disabled = 1;
|
|
|
|
/* Number of helpers running */
|
|
static atomic_t running_helpers = ATOMIC_INIT(0);
|
|
|
|
/*
|
|
* Wait queue head used by usermodehelper_pm_callback() to wait for all running
|
|
* helpers to finish.
|
|
*/
|
|
static DECLARE_WAIT_QUEUE_HEAD(running_helpers_waitq);
|
|
|
|
/*
|
|
* Time to wait for running_helpers to become zero before the setting of
|
|
* usermodehelper_disabled in usermodehelper_pm_callback() fails
|
|
*/
|
|
#define RUNNING_HELPERS_TIMEOUT (5 * HZ)
|
|
|
|
void read_lock_usermodehelper(void)
|
|
{
|
|
down_read(&umhelper_sem);
|
|
}
|
|
EXPORT_SYMBOL_GPL(read_lock_usermodehelper);
|
|
|
|
void read_unlock_usermodehelper(void)
|
|
{
|
|
up_read(&umhelper_sem);
|
|
}
|
|
EXPORT_SYMBOL_GPL(read_unlock_usermodehelper);
|
|
|
|
/**
|
|
* usermodehelper_disable - prevent new helpers from being started
|
|
*/
|
|
int usermodehelper_disable(void)
|
|
{
|
|
long retval;
|
|
|
|
down_write(&umhelper_sem);
|
|
usermodehelper_disabled = 1;
|
|
up_write(&umhelper_sem);
|
|
|
|
/*
|
|
* From now on call_usermodehelper_exec() won't start any new
|
|
* helpers, so it is sufficient if running_helpers turns out to
|
|
* be zero at one point (it may be increased later, but that
|
|
* doesn't matter).
|
|
*/
|
|
retval = wait_event_timeout(running_helpers_waitq,
|
|
atomic_read(&running_helpers) == 0,
|
|
RUNNING_HELPERS_TIMEOUT);
|
|
if (retval)
|
|
return 0;
|
|
|
|
down_write(&umhelper_sem);
|
|
usermodehelper_disabled = 0;
|
|
up_write(&umhelper_sem);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
/**
|
|
* usermodehelper_enable - allow new helpers to be started again
|
|
*/
|
|
void usermodehelper_enable(void)
|
|
{
|
|
down_write(&umhelper_sem);
|
|
usermodehelper_disabled = 0;
|
|
up_write(&umhelper_sem);
|
|
}
|
|
|
|
/**
|
|
* usermodehelper_is_disabled - check if new helpers are allowed to be started
|
|
*/
|
|
bool usermodehelper_is_disabled(void)
|
|
{
|
|
return usermodehelper_disabled;
|
|
}
|
|
EXPORT_SYMBOL_GPL(usermodehelper_is_disabled);
|
|
|
|
static void helper_lock(void)
|
|
{
|
|
atomic_inc(&running_helpers);
|
|
smp_mb__after_atomic_inc();
|
|
}
|
|
|
|
static void helper_unlock(void)
|
|
{
|
|
if (atomic_dec_and_test(&running_helpers))
|
|
wake_up(&running_helpers_waitq);
|
|
}
|
|
|
|
/**
|
|
* call_usermodehelper_setup - prepare to call a usermode helper
|
|
* @path: path to usermode executable
|
|
* @argv: arg vector for process
|
|
* @envp: environment for process
|
|
* @gfp_mask: gfp mask for memory allocation
|
|
*
|
|
* Returns either %NULL on allocation failure, or a subprocess_info
|
|
* structure. This should be passed to call_usermodehelper_exec to
|
|
* exec the process and free the structure.
|
|
*/
|
|
struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
|
|
char **envp, gfp_t gfp_mask)
|
|
{
|
|
struct subprocess_info *sub_info;
|
|
sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask);
|
|
if (!sub_info)
|
|
goto out;
|
|
|
|
INIT_WORK(&sub_info->work, __call_usermodehelper);
|
|
sub_info->path = path;
|
|
sub_info->argv = argv;
|
|
sub_info->envp = envp;
|
|
out:
|
|
return sub_info;
|
|
}
|
|
EXPORT_SYMBOL(call_usermodehelper_setup);
|
|
|
|
/**
|
|
* call_usermodehelper_setfns - set a cleanup/init function
|
|
* @info: a subprocess_info returned by call_usermodehelper_setup
|
|
* @cleanup: a cleanup function
|
|
* @init: an init function
|
|
* @data: arbitrary context sensitive data
|
|
*
|
|
* The init function is used to customize the helper process prior to
|
|
* exec. A non-zero return code causes the process to error out, exit,
|
|
* and return the failure to the calling process
|
|
*
|
|
* The cleanup function is just before ethe subprocess_info is about to
|
|
* be freed. This can be used for freeing the argv and envp. The
|
|
* Function must be runnable in either a process context or the
|
|
* context in which call_usermodehelper_exec is called.
|
|
*/
|
|
void call_usermodehelper_setfns(struct subprocess_info *info,
|
|
int (*init)(struct subprocess_info *info, struct cred *new),
|
|
void (*cleanup)(struct subprocess_info *info),
|
|
void *data)
|
|
{
|
|
info->cleanup = cleanup;
|
|
info->init = init;
|
|
info->data = data;
|
|
}
|
|
EXPORT_SYMBOL(call_usermodehelper_setfns);
|
|
|
|
/**
|
|
* call_usermodehelper_exec - start a usermode application
|
|
* @sub_info: information about the subprocessa
|
|
* @wait: wait for the application to finish and return status.
|
|
* when -1 don't wait at all, but you get no useful error back when
|
|
* the program couldn't be exec'ed. This makes it safe to call
|
|
* from interrupt context.
|
|
*
|
|
* Runs a user-space application. The application is started
|
|
* asynchronously if wait is not set, and runs as a child of keventd.
|
|
* (ie. it runs with full root capabilities).
|
|
*/
|
|
int call_usermodehelper_exec(struct subprocess_info *sub_info,
|
|
enum umh_wait wait)
|
|
{
|
|
DECLARE_COMPLETION_ONSTACK(done);
|
|
int retval = 0;
|
|
|
|
helper_lock();
|
|
if (sub_info->path[0] == '\0')
|
|
goto out;
|
|
|
|
if (!khelper_wq || usermodehelper_disabled) {
|
|
retval = -EBUSY;
|
|
goto out;
|
|
}
|
|
|
|
sub_info->complete = &done;
|
|
sub_info->wait = wait;
|
|
|
|
queue_work(khelper_wq, &sub_info->work);
|
|
if (wait == UMH_NO_WAIT) /* task has freed sub_info */
|
|
goto unlock;
|
|
wait_for_completion(&done);
|
|
retval = sub_info->retval;
|
|
|
|
out:
|
|
call_usermodehelper_freeinfo(sub_info);
|
|
unlock:
|
|
helper_unlock();
|
|
return retval;
|
|
}
|
|
EXPORT_SYMBOL(call_usermodehelper_exec);
|
|
|
|
static int proc_cap_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp, loff_t *ppos)
|
|
{
|
|
struct ctl_table t;
|
|
unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
|
|
kernel_cap_t new_cap;
|
|
int err, i;
|
|
|
|
if (write && (!capable(CAP_SETPCAP) ||
|
|
!capable(CAP_SYS_MODULE)))
|
|
return -EPERM;
|
|
|
|
/*
|
|
* convert from the global kernel_cap_t to the ulong array to print to
|
|
* userspace if this is a read.
|
|
*/
|
|
spin_lock(&umh_sysctl_lock);
|
|
for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) {
|
|
if (table->data == CAP_BSET)
|
|
cap_array[i] = usermodehelper_bset.cap[i];
|
|
else if (table->data == CAP_PI)
|
|
cap_array[i] = usermodehelper_inheritable.cap[i];
|
|
else
|
|
BUG();
|
|
}
|
|
spin_unlock(&umh_sysctl_lock);
|
|
|
|
t = *table;
|
|
t.data = &cap_array;
|
|
|
|
/*
|
|
* actually read or write and array of ulongs from userspace. Remember
|
|
* these are least significant 32 bits first
|
|
*/
|
|
err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
/*
|
|
* convert from the sysctl array of ulongs to the kernel_cap_t
|
|
* internal representation
|
|
*/
|
|
for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++)
|
|
new_cap.cap[i] = cap_array[i];
|
|
|
|
/*
|
|
* Drop everything not in the new_cap (but don't add things)
|
|
*/
|
|
spin_lock(&umh_sysctl_lock);
|
|
if (write) {
|
|
if (table->data == CAP_BSET)
|
|
usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap);
|
|
if (table->data == CAP_PI)
|
|
usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap);
|
|
}
|
|
spin_unlock(&umh_sysctl_lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct ctl_table usermodehelper_table[] = {
|
|
{
|
|
.procname = "bset",
|
|
.data = CAP_BSET,
|
|
.maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
|
|
.mode = 0600,
|
|
.proc_handler = proc_cap_handler,
|
|
},
|
|
{
|
|
.procname = "inheritable",
|
|
.data = CAP_PI,
|
|
.maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long),
|
|
.mode = 0600,
|
|
.proc_handler = proc_cap_handler,
|
|
},
|
|
{ }
|
|
};
|
|
|
|
void __init usermodehelper_init(void)
|
|
{
|
|
khelper_wq = create_singlethread_workqueue("khelper");
|
|
BUG_ON(!khelper_wq);
|
|
}
|