android_kernel_xiaomi_sm8350/kernel/kmod.c
David Howells d84f4f992c CRED: Inaugurate COW credentials
Inaugurate copy-on-write credentials management.  This uses RCU to manage the
credentials pointer in the task_struct with respect to accesses by other tasks.
A process may only modify its own credentials, and so does not need locking to
access or modify its own credentials.

A mutex (cred_replace_mutex) is added to the task_struct to control the effect
of PTRACE_ATTACHED on credential calculations, particularly with respect to
execve().

With this patch, the contents of an active credentials struct may not be
changed directly; rather a new set of credentials must be prepared, modified
and committed using something like the following sequence of events:

	struct cred *new = prepare_creds();
	int ret = blah(new);
	if (ret < 0) {
		abort_creds(new);
		return ret;
	}
	return commit_creds(new);

There are some exceptions to this rule: the keyrings pointed to by the active
credentials may be instantiated - keyrings violate the COW rule as managing
COW keyrings is tricky, given that it is possible for a task to directly alter
the keys in a keyring in use by another task.

To help enforce this, various pointers to sets of credentials, such as those in
the task_struct, are declared const.  The purpose of this is compile-time
discouragement of altering credentials through those pointers.  Once a set of
credentials has been made public through one of these pointers, it may not be
modified, except under special circumstances:

  (1) Its reference count may incremented and decremented.

  (2) The keyrings to which it points may be modified, but not replaced.

The only safe way to modify anything else is to create a replacement and commit
using the functions described in Documentation/credentials.txt (which will be
added by a later patch).

This patch and the preceding patches have been tested with the LTP SELinux
testsuite.

This patch makes several logical sets of alteration:

 (1) execve().

     This now prepares and commits credentials in various places in the
     security code rather than altering the current creds directly.

 (2) Temporary credential overrides.

     do_coredump() and sys_faccessat() now prepare their own credentials and
     temporarily override the ones currently on the acting thread, whilst
     preventing interference from other threads by holding cred_replace_mutex
     on the thread being dumped.

     This will be replaced in a future patch by something that hands down the
     credentials directly to the functions being called, rather than altering
     the task's objective credentials.

 (3) LSM interface.

     A number of functions have been changed, added or removed:

     (*) security_capset_check(), ->capset_check()
     (*) security_capset_set(), ->capset_set()

     	 Removed in favour of security_capset().

     (*) security_capset(), ->capset()

     	 New.  This is passed a pointer to the new creds, a pointer to the old
     	 creds and the proposed capability sets.  It should fill in the new
     	 creds or return an error.  All pointers, barring the pointer to the
     	 new creds, are now const.

     (*) security_bprm_apply_creds(), ->bprm_apply_creds()

     	 Changed; now returns a value, which will cause the process to be
     	 killed if it's an error.

     (*) security_task_alloc(), ->task_alloc_security()

     	 Removed in favour of security_prepare_creds().

     (*) security_cred_free(), ->cred_free()

     	 New.  Free security data attached to cred->security.

     (*) security_prepare_creds(), ->cred_prepare()

     	 New. Duplicate any security data attached to cred->security.

     (*) security_commit_creds(), ->cred_commit()

     	 New. Apply any security effects for the upcoming installation of new
     	 security by commit_creds().

     (*) security_task_post_setuid(), ->task_post_setuid()

     	 Removed in favour of security_task_fix_setuid().

     (*) security_task_fix_setuid(), ->task_fix_setuid()

     	 Fix up the proposed new credentials for setuid().  This is used by
     	 cap_set_fix_setuid() to implicitly adjust capabilities in line with
     	 setuid() changes.  Changes are made to the new credentials, rather
     	 than the task itself as in security_task_post_setuid().

     (*) security_task_reparent_to_init(), ->task_reparent_to_init()

     	 Removed.  Instead the task being reparented to init is referred
     	 directly to init's credentials.

	 NOTE!  This results in the loss of some state: SELinux's osid no
	 longer records the sid of the thread that forked it.

     (*) security_key_alloc(), ->key_alloc()
     (*) security_key_permission(), ->key_permission()

     	 Changed.  These now take cred pointers rather than task pointers to
     	 refer to the security context.

 (4) sys_capset().

     This has been simplified and uses less locking.  The LSM functions it
     calls have been merged.

 (5) reparent_to_kthreadd().

     This gives the current thread the same credentials as init by simply using
     commit_thread() to point that way.

 (6) __sigqueue_alloc() and switch_uid()

     __sigqueue_alloc() can't stop the target task from changing its creds
     beneath it, so this function gets a reference to the currently applicable
     user_struct which it then passes into the sigqueue struct it returns if
     successful.

     switch_uid() is now called from commit_creds(), and possibly should be
     folded into that.  commit_creds() should take care of protecting
     __sigqueue_alloc().

 (7) [sg]et[ug]id() and co and [sg]et_current_groups.

     The set functions now all use prepare_creds(), commit_creds() and
     abort_creds() to build and check a new set of credentials before applying
     it.

     security_task_set[ug]id() is called inside the prepared section.  This
     guarantees that nothing else will affect the creds until we've finished.

     The calling of set_dumpable() has been moved into commit_creds().

     Much of the functionality of set_user() has been moved into
     commit_creds().

     The get functions all simply access the data directly.

 (8) security_task_prctl() and cap_task_prctl().

     security_task_prctl() has been modified to return -ENOSYS if it doesn't
     want to handle a function, or otherwise return the return value directly
     rather than through an argument.

     Additionally, cap_task_prctl() now prepares a new set of credentials, even
     if it doesn't end up using it.

 (9) Keyrings.

     A number of changes have been made to the keyrings code:

     (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have
     	 all been dropped and built in to the credentials functions directly.
     	 They may want separating out again later.

     (b) key_alloc() and search_process_keyrings() now take a cred pointer
     	 rather than a task pointer to specify the security context.

     (c) copy_creds() gives a new thread within the same thread group a new
     	 thread keyring if its parent had one, otherwise it discards the thread
     	 keyring.

     (d) The authorisation key now points directly to the credentials to extend
     	 the search into rather pointing to the task that carries them.

     (e) Installing thread, process or session keyrings causes a new set of
     	 credentials to be created, even though it's not strictly necessary for
     	 process or session keyrings (they're shared).

(10) Usermode helper.

     The usermode helper code now carries a cred struct pointer in its
     subprocess_info struct instead of a new session keyring pointer.  This set
     of credentials is derived from init_cred and installed on the new process
     after it has been cloned.

     call_usermodehelper_setup() allocates the new credentials and
     call_usermodehelper_freeinfo() discards them if they haven't been used.  A
     special cred function (prepare_usermodeinfo_creds()) is provided
     specifically for call_usermodehelper_setup() to call.

     call_usermodehelper_setkeys() adjusts the credentials to sport the
     supplied keyring as the new session keyring.

(11) SELinux.

     SELinux has a number of changes, in addition to those to support the LSM
     interface changes mentioned above:

     (a) selinux_setprocattr() no longer does its check for whether the
     	 current ptracer can access processes with the new SID inside the lock
     	 that covers getting the ptracer's SID.  Whilst this lock ensures that
     	 the check is done with the ptracer pinned, the result is only valid
     	 until the lock is released, so there's no point doing it inside the
     	 lock.

(12) is_single_threaded().

     This function has been extracted from selinux_setprocattr() and put into
     a file of its own in the lib/ directory as join_session_keyring() now
     wants to use it too.

     The code in SELinux just checked to see whether a task shared mm_structs
     with other tasks (CLONE_VM), but that isn't good enough.  We really want
     to know if they're part of the same thread group (CLONE_THREAD).

(13) nfsd.

     The NFS server daemon now has to use the COW credentials to set the
     credentials it is going to use.  It really needs to pass the credentials
     down to the functions it calls, but it can't do that until other patches
     in this series have been applied.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:23 +11:00

527 lines
14 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/mnt_namespace.h>
#include <linux/completion.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 <asm/uaccess.h>
extern int max_threads;
static struct workqueue_struct *khelper_wq;
#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
* @fmt: printf style format string for the name of the module
* @varargs: arguements 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(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;
/* 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);
atomic_dec(&kmod_concurrent);
return -ENOMEM;
}
ret = call_usermodehelper(modprobe_path, argv, envp, 1);
atomic_dec(&kmod_concurrent);
return ret;
}
EXPORT_SYMBOL(request_module);
#endif /* CONFIG_MODULES */
struct subprocess_info {
struct work_struct work;
struct completion *complete;
struct cred *cred;
char *path;
char **argv;
char **envp;
enum umh_wait wait;
int retval;
struct file *stdin;
void (*cleanup)(char **argv, char **envp);
};
/*
* This is the task which runs the usermode application
*/
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
int retval;
BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
/* Unblock all signals */
spin_lock_irq(&current->sighand->siglock);
flush_signal_handlers(current, 1);
sigemptyset(&current->blocked);
recalc_sigpending();
spin_unlock_irq(&current->sighand->siglock);
/* Install the credentials */
commit_creds(sub_info->cred);
sub_info->cred = NULL;
/* Install input pipe when needed */
if (sub_info->stdin) {
struct files_struct *f = current->files;
struct fdtable *fdt;
/* no races because files should be private here */
sys_close(0);
fd_install(0, sub_info->stdin);
spin_lock(&f->file_lock);
fdt = files_fdtable(f);
FD_SET(0, fdt->open_fds);
FD_CLR(0, fdt->close_on_exec);
spin_unlock(&f->file_lock);
/* and disallow core files too */
current->signal->rlim[RLIMIT_CORE] = (struct rlimit){0, 0};
}
/* We can run anywhere, unlike our parent keventd(). */
set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
/*
* Our parent is keventd, which runs with elevated scheduling priority.
* Avoid propagating that into the userspace child.
*/
set_user_nice(current, 0);
retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp);
/* Exec failed? */
sub_info->retval = retval;
do_exit(0);
}
void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
if (info->cleanup)
(*info->cleanup)(info->argv, info->envp);
if (info->cred)
put_cred(info->cred);
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;
/* Install a handler: if SIGCLD isn't handled sys_wait4 won't
* populate the status, but will return -ECHILD. */
allow_signal(SIGCHLD);
pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
if (pid < 0) {
sub_info->retval = pid;
} else {
int ret;
/*
* 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;
}
if (sub_info->wait == UMH_NO_WAIT)
call_usermodehelper_freeinfo(sub_info);
else
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);
pid_t pid;
enum umh_wait wait = sub_info->wait;
BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
/* 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 || wait == UMH_NO_WAIT)
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:
break;
case UMH_WAIT_PROC:
if (pid > 0)
break;
sub_info->retval = pid;
/* FALLTHROUGH */
case UMH_WAIT_EXEC:
complete(sub_info->complete);
}
}
#ifdef CONFIG_PM_SLEEP
/*
* 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).
*/
static int usermodehelper_disabled;
/* 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)
/**
* usermodehelper_disable - prevent new helpers from being started
*/
int usermodehelper_disable(void)
{
long retval;
usermodehelper_disabled = 1;
smp_mb();
/*
* 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;
usermodehelper_disabled = 0;
return -EAGAIN;
}
/**
* usermodehelper_enable - allow new helpers to be started again
*/
void usermodehelper_enable(void)
{
usermodehelper_disabled = 0;
}
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);
}
#else /* CONFIG_PM_SLEEP */
#define usermodehelper_disabled 0
static inline void helper_lock(void) {}
static inline void helper_unlock(void) {}
#endif /* CONFIG_PM_SLEEP */
/**
* 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;
sub_info->cred = prepare_usermodehelper_creds();
if (!sub_info->cred)
return NULL;
out:
return sub_info;
}
EXPORT_SYMBOL(call_usermodehelper_setup);
/**
* call_usermodehelper_setkeys - set the session keys for usermode helper
* @info: a subprocess_info returned by call_usermodehelper_setup
* @session_keyring: the session keyring for the process
*/
void call_usermodehelper_setkeys(struct subprocess_info *info,
struct key *session_keyring)
{
#ifdef CONFIG_KEYS
struct thread_group_cred *tgcred = info->cred->tgcred;
key_put(tgcred->session_keyring);
tgcred->session_keyring = key_get(session_keyring);
#else
BUG();
#endif
}
EXPORT_SYMBOL(call_usermodehelper_setkeys);
/**
* call_usermodehelper_setcleanup - set a cleanup function
* @info: a subprocess_info returned by call_usermodehelper_setup
* @cleanup: a cleanup function
*
* The cleanup function is just befor 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_setcleanup(struct subprocess_info *info,
void (*cleanup)(char **argv, char **envp))
{
info->cleanup = cleanup;
}
EXPORT_SYMBOL(call_usermodehelper_setcleanup);
/**
* call_usermodehelper_stdinpipe - set up a pipe to be used for stdin
* @sub_info: a subprocess_info returned by call_usermodehelper_setup
* @filp: set to the write-end of a pipe
*
* This constructs a pipe, and sets the read end to be the stdin of the
* subprocess, and returns the write-end in *@filp.
*/
int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info,
struct file **filp)
{
struct file *f;
f = create_write_pipe(0);
if (IS_ERR(f))
return PTR_ERR(f);
*filp = f;
f = create_read_pipe(f, 0);
if (IS_ERR(f)) {
free_write_pipe(*filp);
return PTR_ERR(f);
}
sub_info->stdin = f;
return 0;
}
EXPORT_SYMBOL(call_usermodehelper_stdinpipe);
/**
* 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;
BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
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);
/**
* call_usermodehelper_pipe - call a usermode helper process with a pipe stdin
* @path: path to usermode executable
* @argv: arg vector for process
* @envp: environment for process
* @filp: set to the write-end of a pipe
*
* This is a simple wrapper which executes a usermode-helper function
* with a pipe as stdin. It is implemented entirely in terms of
* lower-level call_usermodehelper_* functions.
*/
int call_usermodehelper_pipe(char *path, char **argv, char **envp,
struct file **filp)
{
struct subprocess_info *sub_info;
int ret;
sub_info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL);
if (sub_info == NULL)
return -ENOMEM;
ret = call_usermodehelper_stdinpipe(sub_info, filp);
if (ret < 0)
goto out;
return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
out:
call_usermodehelper_freeinfo(sub_info);
return ret;
}
EXPORT_SYMBOL(call_usermodehelper_pipe);
void __init usermodehelper_init(void)
{
khelper_wq = create_singlethread_workqueue("khelper");
BUG_ON(!khelper_wq);
}