linux_dsm_epyc7002/kernel/kmod.c
Eric Biggers d7d27cfc5c kmod: make request_module() return an error when autoloading is disabled
Patch series "module autoloading fixes and cleanups", v5.

This series fixes a bug where request_module() was reporting success to
kernel code when module autoloading had been completely disabled via
'echo > /proc/sys/kernel/modprobe'.

It also addresses the issues raised on the original thread
(https://lkml.kernel.org/lkml/20200310223731.126894-1-ebiggers@kernel.org/T/#u)
bydocumenting the modprobe sysctl, adding a self-test for the empty path
case, and downgrading a user-reachable WARN_ONCE().

This patch (of 4):

It's long been possible to disable kernel module autoloading completely
(while still allowing manual module insertion) by setting
/proc/sys/kernel/modprobe to the empty string.

This can be preferable to setting it to a nonexistent file since it
avoids the overhead of an attempted execve(), avoids potential
deadlocks, and avoids the call to security_kernel_module_request() and
thus on SELinux-based systems eliminates the need to write SELinux rules
to dontaudit module_request.

However, when module autoloading is disabled in this way,
request_module() returns 0.  This is broken because callers expect 0 to
mean that the module was successfully loaded.

Apparently this was never noticed because this method of disabling
module autoloading isn't used much, and also most callers don't use the
return value of request_module() since it's always necessary to check
whether the module registered its functionality or not anyway.

But improperly returning 0 can indeed confuse a few callers, for example
get_fs_type() in fs/filesystems.c where it causes a WARNING to be hit:

	if (!fs && (request_module("fs-%.*s", len, name) == 0)) {
		fs = __get_fs_type(name, len);
		WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name);
	}

This is easily reproduced with:

	echo > /proc/sys/kernel/modprobe
	mount -t NONEXISTENT none /

It causes:

	request_module fs-NONEXISTENT succeeded, but still no fs?
	WARNING: CPU: 1 PID: 1106 at fs/filesystems.c:275 get_fs_type+0xd6/0xf0
	[...]

This should actually use pr_warn_once() rather than WARN_ONCE(), since
it's also user-reachable if userspace immediately unloads the module.
Regardless, request_module() should correctly return an error when it
fails.  So let's make it return -ENOENT, which matches the error when
the modprobe binary doesn't exist.

I've also sent patches to document and test this case.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Jessica Yu <jeyu@kernel.org>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Ben Hutchings <benh@debian.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200310223731.126894-1-ebiggers@kernel.org
Link: http://lkml.kernel.org/r/20200312202552.241885-1-ebiggers@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-10 15:36:22 -07:00

179 lines
5.0 KiB
C

/*
* kmod - the kernel module loader
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/binfmts.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 <linux/ptrace.h>
#include <linux/async.h>
#include <linux/uaccess.h>
#include <trace/events/module.h>
/*
* Assuming:
*
* threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
* (u64) THREAD_SIZE * 8UL);
*
* If you need less than 50 threads would mean we're dealing with systems
* smaller than 3200 pages. This assumes you are capable of having ~13M memory,
* and this would only be an be an upper limit, after which the OOM killer
* would take effect. Systems like these are very unlikely if modules are
* enabled.
*/
#define MAX_KMOD_CONCURRENT 50
static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);
static DECLARE_WAIT_QUEUE_HEAD(kmod_wq);
/*
* This is a restriction on having *all* MAX_KMOD_CONCURRENT threads
* running at the same time without returning. When this happens we
* believe you've somehow ended up with a recursive module dependency
* creating a loop.
*
* We have no option but to fail.
*
* Userspace should proactively try to detect and prevent these.
*/
#define MAX_KMOD_ALL_BUSY_TIMEOUT 5
/*
modprobe_path is set via /proc/sys.
*/
char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
static void free_modprobe_argv(struct subprocess_info *info)
{
kfree(info->argv[3]); /* check call_modprobe() */
kfree(info->argv);
}
static int call_modprobe(char *module_name, int wait)
{
struct subprocess_info *info;
static char *envp[] = {
"HOME=/",
"TERM=linux",
"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
NULL
};
char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL);
if (!argv)
goto out;
module_name = kstrdup(module_name, GFP_KERNEL);
if (!module_name)
goto free_argv;
argv[0] = modprobe_path;
argv[1] = "-q";
argv[2] = "--";
argv[3] = module_name; /* check free_modprobe_argv() */
argv[4] = NULL;
info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL,
NULL, free_modprobe_argv, NULL);
if (!info)
goto free_module_name;
return call_usermodehelper_exec(info, wait | UMH_KILLABLE);
free_module_name:
kfree(module_name);
free_argv:
kfree(argv);
out:
return -ENOMEM;
}
/**
* __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 or positive exit code from
* "modprobe" 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
* simply returns -ENOENT.
*/
int __request_module(bool wait, const char *fmt, ...)
{
va_list args;
char module_name[MODULE_NAME_LEN];
int ret;
/*
* We don't allow synchronous module loading from async. Module
* init may invoke async_synchronize_full() which will end up
* waiting for this task which already is waiting for the module
* loading to complete, leading to a deadlock.
*/
WARN_ON_ONCE(wait && current_is_async());
if (!modprobe_path[0])
return -ENOENT;
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 (atomic_dec_if_positive(&kmod_concurrent_max) < 0) {
pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...",
atomic_read(&kmod_concurrent_max),
MAX_KMOD_CONCURRENT, module_name);
ret = wait_event_killable_timeout(kmod_wq,
atomic_dec_if_positive(&kmod_concurrent_max) >= 0,
MAX_KMOD_ALL_BUSY_TIMEOUT * HZ);
if (!ret) {
pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now",
module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT);
return -ETIME;
} else if (ret == -ERESTARTSYS) {
pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name);
return ret;
}
}
trace_module_request(module_name, wait, _RET_IP_);
ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
atomic_inc(&kmod_concurrent_max);
wake_up(&kmod_wq);
return ret;
}
EXPORT_SYMBOL(__request_module);