linux/lib/test_kmod.c

1240 lines
30 KiB
C
Raw Normal View History

kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
/*
* kmod stress test driver
*
* Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or at your option any
* later version; or, when distributed separately from the Linux kernel or
* when incorporated into other software packages, subject to the following
* license:
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of copyleft-next (version 0.3.1 or later) as published
* at http://copyleft-next.org/.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
/*
* This driver provides an interface to trigger and test the kernel's
* module loader through a series of configurations and a few triggers.
* To test this driver use the following script as root:
*
* tools/testing/selftests/kmod/kmod.sh --help
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/kmod.h>
#include <linux/printk.h>
#include <linux/kthread.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/device.h>
#define TEST_START_NUM_THREADS 50
#define TEST_START_DRIVER "test_module"
#define TEST_START_TEST_FS "xfs"
#define TEST_START_TEST_CASE TEST_KMOD_DRIVER
static bool force_init_test = false;
module_param(force_init_test, bool_enable_only, 0644);
MODULE_PARM_DESC(force_init_test,
"Force kicking a test immediately after driver loads");
/*
* For device allocation / registration
*/
static DEFINE_MUTEX(reg_dev_mutex);
static LIST_HEAD(reg_test_devs);
/*
* num_test_devs actually represents the *next* ID of the next
* device we will allow to create.
*/
static int num_test_devs;
/**
* enum kmod_test_case - linker table test case
*
* If you add a test case, please be sure to review if you need to se
* @need_mod_put for your tests case.
*
* @TEST_KMOD_DRIVER: stress tests request_module()
* @TEST_KMOD_FS_TYPE: stress tests get_fs_type()
*/
enum kmod_test_case {
__TEST_KMOD_INVALID = 0,
TEST_KMOD_DRIVER,
TEST_KMOD_FS_TYPE,
__TEST_KMOD_MAX,
};
struct test_config {
char *test_driver;
char *test_fs;
unsigned int num_threads;
enum kmod_test_case test_case;
int test_result;
};
struct kmod_test_device;
/**
* kmod_test_device_info - thread info
*
* @ret_sync: return value if request_module() is used, sync request for
* @TEST_KMOD_DRIVER
* @fs_sync: return value of get_fs_type() for @TEST_KMOD_FS_TYPE
* @thread_idx: thread ID
* @test_dev: test device test is being performed under
* @need_mod_put: Some tests (get_fs_type() is one) requires putting the module
* (module_put(fs_sync->owner)) when done, otherwise you will not be able
* to unload the respective modules and re-test. We use this to keep
* accounting of when we need this and to help out in case we need to
* error out and deal with module_put() on error.
*/
struct kmod_test_device_info {
int ret_sync;
struct file_system_type *fs_sync;
struct task_struct *task_sync;
unsigned int thread_idx;
struct kmod_test_device *test_dev;
bool need_mod_put;
};
/**
* kmod_test_device - test device to help test kmod
*
* @dev_idx: unique ID for test device
* @config: configuration for the test
* @misc_dev: we use a misc device under the hood
* @dev: pointer to misc_dev's own struct device
* @config_mutex: protects configuration of test
* @trigger_mutex: the test trigger can only be fired once at a time
* @thread_lock: protects @done count, and the @info per each thread
* @done: number of threads which have completed or failed
* @test_is_oom: when we run out of memory, use this to halt moving forward
* @kthreads_done: completion used to signal when all work is done
* @list: needed to be part of the reg_test_devs
* @info: array of info for each thread
*/
struct kmod_test_device {
int dev_idx;
struct test_config config;
struct miscdevice misc_dev;
struct device *dev;
struct mutex config_mutex;
struct mutex trigger_mutex;
struct mutex thread_mutex;
unsigned int done;
bool test_is_oom;
struct completion kthreads_done;
struct list_head list;
struct kmod_test_device_info *info;
};
static const char *test_case_str(enum kmod_test_case test_case)
{
switch (test_case) {
case TEST_KMOD_DRIVER:
return "TEST_KMOD_DRIVER";
case TEST_KMOD_FS_TYPE:
return "TEST_KMOD_FS_TYPE";
default:
return "invalid";
}
}
static struct miscdevice *dev_to_misc_dev(struct device *dev)
{
return dev_get_drvdata(dev);
}
static struct kmod_test_device *misc_dev_to_test_dev(struct miscdevice *misc_dev)
{
return container_of(misc_dev, struct kmod_test_device, misc_dev);
}
static struct kmod_test_device *dev_to_test_dev(struct device *dev)
{
struct miscdevice *misc_dev;
misc_dev = dev_to_misc_dev(dev);
return misc_dev_to_test_dev(misc_dev);
}
/* Must run with thread_mutex held */
static void kmod_test_done_check(struct kmod_test_device *test_dev,
unsigned int idx)
{
struct test_config *config = &test_dev->config;
test_dev->done++;
dev_dbg(test_dev->dev, "Done thread count: %u\n", test_dev->done);
if (test_dev->done == config->num_threads) {
dev_info(test_dev->dev, "Done: %u threads have all run now\n",
test_dev->done);
dev_info(test_dev->dev, "Last thread to run: %u\n", idx);
complete(&test_dev->kthreads_done);
}
}
static void test_kmod_put_module(struct kmod_test_device_info *info)
{
struct kmod_test_device *test_dev = info->test_dev;
struct test_config *config = &test_dev->config;
if (!info->need_mod_put)
return;
switch (config->test_case) {
case TEST_KMOD_DRIVER:
break;
case TEST_KMOD_FS_TYPE:
if (info && info->fs_sync && info->fs_sync->owner)
module_put(info->fs_sync->owner);
break;
default:
BUG();
}
info->need_mod_put = true;
}
static int run_request(void *data)
{
struct kmod_test_device_info *info = data;
struct kmod_test_device *test_dev = info->test_dev;
struct test_config *config = &test_dev->config;
switch (config->test_case) {
case TEST_KMOD_DRIVER:
info->ret_sync = request_module("%s", config->test_driver);
break;
case TEST_KMOD_FS_TYPE:
info->fs_sync = get_fs_type(config->test_fs);
info->need_mod_put = true;
break;
default:
/* __trigger_config_run() already checked for test sanity */
BUG();
return -EINVAL;
}
dev_dbg(test_dev->dev, "Ran thread %u\n", info->thread_idx);
test_kmod_put_module(info);
mutex_lock(&test_dev->thread_mutex);
info->task_sync = NULL;
kmod_test_done_check(test_dev, info->thread_idx);
mutex_unlock(&test_dev->thread_mutex);
return 0;
}
static int tally_work_test(struct kmod_test_device_info *info)
{
struct kmod_test_device *test_dev = info->test_dev;
struct test_config *config = &test_dev->config;
int err_ret = 0;
switch (config->test_case) {
case TEST_KMOD_DRIVER:
/*
* Only capture errors, if one is found that's
* enough, for now.
*/
if (info->ret_sync != 0)
err_ret = info->ret_sync;
dev_info(test_dev->dev,
"Sync thread %d return status: %d\n",
info->thread_idx, info->ret_sync);
break;
case TEST_KMOD_FS_TYPE:
/* For now we make this simple */
if (!info->fs_sync)
err_ret = -EINVAL;
dev_info(test_dev->dev, "Sync thread %u fs: %s\n",
info->thread_idx, info->fs_sync ? config->test_fs :
"NULL");
break;
default:
BUG();
}
return err_ret;
}
/*
* XXX: add result option to display if all errors did not match.
* For now we just keep any error code if one was found.
*
* If this ran it means *all* tasks were created fine and we
* are now just collecting results.
*
* Only propagate errors, do not override with a subsequent sucess case.
*/
static void tally_up_work(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
struct kmod_test_device_info *info;
unsigned int idx;
int err_ret = 0;
int ret = 0;
mutex_lock(&test_dev->thread_mutex);
dev_info(test_dev->dev, "Results:\n");
for (idx=0; idx < config->num_threads; idx++) {
info = &test_dev->info[idx];
ret = tally_work_test(info);
if (ret)
err_ret = ret;
}
/*
* Note: request_module() returns 256 for a module not found even
* though modprobe itself returns 1.
*/
config->test_result = err_ret;
mutex_unlock(&test_dev->thread_mutex);
}
static int try_one_request(struct kmod_test_device *test_dev, unsigned int idx)
{
struct kmod_test_device_info *info = &test_dev->info[idx];
int fail_ret = -ENOMEM;
mutex_lock(&test_dev->thread_mutex);
info->thread_idx = idx;
info->test_dev = test_dev;
info->task_sync = kthread_run(run_request, info, "%s-%u",
KBUILD_MODNAME, idx);
if (!info->task_sync || IS_ERR(info->task_sync)) {
test_dev->test_is_oom = true;
dev_err(test_dev->dev, "Setting up thread %u failed\n", idx);
info->task_sync = NULL;
goto err_out;
} else
dev_dbg(test_dev->dev, "Kicked off thread %u\n", idx);
mutex_unlock(&test_dev->thread_mutex);
return 0;
err_out:
info->ret_sync = fail_ret;
mutex_unlock(&test_dev->thread_mutex);
return fail_ret;
}
static void test_dev_kmod_stop_tests(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
struct kmod_test_device_info *info;
unsigned int i;
dev_info(test_dev->dev, "Ending request_module() tests\n");
mutex_lock(&test_dev->thread_mutex);
for (i=0; i < config->num_threads; i++) {
info = &test_dev->info[i];
if (info->task_sync && !IS_ERR(info->task_sync)) {
dev_info(test_dev->dev,
"Stopping still-running thread %i\n", i);
kthread_stop(info->task_sync);
}
/*
* info->task_sync is well protected, it can only be
* NULL or a pointer to a struct. If its NULL we either
* never ran, or we did and we completed the work. Completed
* tasks *always* put the module for us. This is a sanity
* check -- just in case.
*/
if (info->task_sync && info->need_mod_put)
test_kmod_put_module(info);
}
mutex_unlock(&test_dev->thread_mutex);
}
/*
* Only wait *iff* we did not run into any errors during all of our thread
* set up. If run into any issues we stop threads and just bail out with
* an error to the trigger. This also means we don't need any tally work
* for any threads which fail.
*/
static int try_requests(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
unsigned int idx;
int ret;
bool any_error = false;
for (idx=0; idx < config->num_threads; idx++) {
if (test_dev->test_is_oom) {
any_error = true;
break;
}
ret = try_one_request(test_dev, idx);
if (ret) {
any_error = true;
break;
}
}
if (!any_error) {
test_dev->test_is_oom = false;
dev_info(test_dev->dev,
"No errors were found while initializing threads\n");
wait_for_completion(&test_dev->kthreads_done);
tally_up_work(test_dev);
} else {
test_dev->test_is_oom = true;
dev_info(test_dev->dev,
"At least one thread failed to start, stop all work\n");
test_dev_kmod_stop_tests(test_dev);
return -ENOMEM;
}
return 0;
}
static int run_test_driver(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
dev_info(test_dev->dev, "Test case: %s (%u)\n",
test_case_str(config->test_case),
config->test_case);
dev_info(test_dev->dev, "Test driver to load: %s\n",
config->test_driver);
dev_info(test_dev->dev, "Number of threads to run: %u\n",
config->num_threads);
dev_info(test_dev->dev, "Thread IDs will range from 0 - %u\n",
config->num_threads - 1);
return try_requests(test_dev);
}
static int run_test_fs_type(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
dev_info(test_dev->dev, "Test case: %s (%u)\n",
test_case_str(config->test_case),
config->test_case);
dev_info(test_dev->dev, "Test filesystem to load: %s\n",
config->test_fs);
dev_info(test_dev->dev, "Number of threads to run: %u\n",
config->num_threads);
dev_info(test_dev->dev, "Thread IDs will range from 0 - %u\n",
config->num_threads - 1);
return try_requests(test_dev);
}
static ssize_t config_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
int len = 0;
mutex_lock(&test_dev->config_mutex);
len += snprintf(buf, PAGE_SIZE,
"Custom trigger configuration for: %s\n",
dev_name(dev));
len += snprintf(buf+len, PAGE_SIZE - len,
"Number of threads:\t%u\n",
config->num_threads);
len += snprintf(buf+len, PAGE_SIZE - len,
"Test_case:\t%s (%u)\n",
test_case_str(config->test_case),
config->test_case);
if (config->test_driver)
len += snprintf(buf+len, PAGE_SIZE - len,
"driver:\t%s\n",
config->test_driver);
else
len += snprintf(buf+len, PAGE_SIZE - len,
"driver:\tEMPTY\n");
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
if (config->test_fs)
len += snprintf(buf+len, PAGE_SIZE - len,
"fs:\t%s\n",
config->test_fs);
else
len += snprintf(buf+len, PAGE_SIZE - len,
"fs:\tEMPTY\n");
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
mutex_unlock(&test_dev->config_mutex);
return len;
}
static DEVICE_ATTR_RO(config);
/*
* This ensures we don't allow kicking threads through if our configuration
* is faulty.
*/
static int __trigger_config_run(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
test_dev->done = 0;
switch (config->test_case) {
case TEST_KMOD_DRIVER:
return run_test_driver(test_dev);
case TEST_KMOD_FS_TYPE:
return run_test_fs_type(test_dev);
default:
dev_warn(test_dev->dev,
"Invalid test case requested: %u\n",
config->test_case);
return -EINVAL;
}
}
static int trigger_config_run(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
int ret;
mutex_lock(&test_dev->trigger_mutex);
mutex_lock(&test_dev->config_mutex);
ret = __trigger_config_run(test_dev);
if (ret < 0)
goto out;
dev_info(test_dev->dev, "General test result: %d\n",
config->test_result);
/*
* We must return 0 after a trigger even unless something went
* wrong with the setup of the test. If the test setup went fine
* then userspace must just check the result of config->test_result.
* One issue with relying on the return from a call in the kernel
* is if the kernel returns a possitive value using this trigger
* will not return the value to userspace, it would be lost.
*
* By not relying on capturing the return value of tests we are using
* through the trigger it also us to run tests with set -e and only
* fail when something went wrong with the driver upon trigger
* requests.
*/
ret = 0;
out:
mutex_unlock(&test_dev->config_mutex);
mutex_unlock(&test_dev->trigger_mutex);
return ret;
}
static ssize_t
trigger_config_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
int ret;
if (test_dev->test_is_oom)
return -ENOMEM;
/* For all intents and purposes we don't care what userspace
* sent this trigger, we care only that we were triggered.
* We treat the return value only for caputuring issues with
* the test setup. At this point all the test variables should
* have been allocated so typically this should never fail.
*/
ret = trigger_config_run(test_dev);
if (unlikely(ret < 0))
goto out;
/*
* Note: any return > 0 will be treated as success
* and the error value will not be available to userspace.
* Do not rely on trying to send to userspace a test value
* return value as possitive return errors will be lost.
*/
if (WARN_ON(ret > 0))
return -EINVAL;
ret = count;
out:
return ret;
}
static DEVICE_ATTR_WO(trigger_config);
/*
* XXX: move to kstrncpy() once merged.
*
* Users should use kfree_const() when freeing these.
*/
static int __kstrncpy(char **dst, const char *name, size_t count, gfp_t gfp)
{
*dst = kstrndup(name, count, gfp);
if (!*dst)
return -ENOSPC;
return count;
}
static int config_copy_test_driver_name(struct test_config *config,
const char *name,
size_t count)
{
return __kstrncpy(&config->test_driver, name, count, GFP_KERNEL);
}
static int config_copy_test_fs(struct test_config *config, const char *name,
size_t count)
{
return __kstrncpy(&config->test_fs, name, count, GFP_KERNEL);
}
static void __kmod_config_free(struct test_config *config)
{
if (!config)
return;
kfree_const(config->test_driver);
config->test_driver = NULL;
kfree_const(config->test_fs);
config->test_driver = NULL;
}
static void kmod_config_free(struct kmod_test_device *test_dev)
{
struct test_config *config;
if (!test_dev)
return;
config = &test_dev->config;
mutex_lock(&test_dev->config_mutex);
__kmod_config_free(config);
mutex_unlock(&test_dev->config_mutex);
}
static ssize_t config_test_driver_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
int copied;
mutex_lock(&test_dev->config_mutex);
kfree_const(config->test_driver);
config->test_driver = NULL;
copied = config_copy_test_driver_name(config, buf, count);
mutex_unlock(&test_dev->config_mutex);
return copied;
}
/*
* As per sysfs_kf_seq_show() the buf is max PAGE_SIZE.
*/
static ssize_t config_test_show_str(struct mutex *config_mutex,
char *dst,
char *src)
{
int len;
mutex_lock(config_mutex);
len = snprintf(dst, PAGE_SIZE, "%s\n", src);
mutex_unlock(config_mutex);
return len;
}
static ssize_t config_test_driver_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return config_test_show_str(&test_dev->config_mutex, buf,
config->test_driver);
}
static DEVICE_ATTR_RW(config_test_driver);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
static ssize_t config_test_fs_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
int copied;
mutex_lock(&test_dev->config_mutex);
kfree_const(config->test_fs);
config->test_fs = NULL;
copied = config_copy_test_fs(config, buf, count);
mutex_unlock(&test_dev->config_mutex);
return copied;
}
static ssize_t config_test_fs_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return config_test_show_str(&test_dev->config_mutex, buf,
config->test_fs);
}
static DEVICE_ATTR_RW(config_test_fs);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
static int trigger_config_run_type(struct kmod_test_device *test_dev,
enum kmod_test_case test_case,
const char *test_str)
{
int copied = 0;
struct test_config *config = &test_dev->config;
mutex_lock(&test_dev->config_mutex);
switch (test_case) {
case TEST_KMOD_DRIVER:
kfree_const(config->test_driver);
config->test_driver = NULL;
copied = config_copy_test_driver_name(config, test_str,
strlen(test_str));
break;
case TEST_KMOD_FS_TYPE:
kfree_const(config->test_fs);
config->test_driver = NULL;
copied = config_copy_test_fs(config, test_str,
strlen(test_str));
break;
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
default:
mutex_unlock(&test_dev->config_mutex);
return -EINVAL;
}
config->test_case = test_case;
mutex_unlock(&test_dev->config_mutex);
if (copied <= 0 || copied != strlen(test_str)) {
test_dev->test_is_oom = true;
return -ENOMEM;
}
test_dev->test_is_oom = false;
return trigger_config_run(test_dev);
}
static void free_test_dev_info(struct kmod_test_device *test_dev)
{
vfree(test_dev->info);
test_dev->info = NULL;
}
static int kmod_config_sync_info(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
free_test_dev_info(test_dev);
treewide: Use array_size() in vzalloc() The vzalloc() function has no 2-factor argument form, so multiplication factors need to be wrapped in array_size(). This patch replaces cases of: vzalloc(a * b) with: vzalloc(array_size(a, b)) as well as handling cases of: vzalloc(a * b * c) with: vzalloc(array3_size(a, b, c)) This does, however, attempt to ignore constant size factors like: vzalloc(4 * 1024) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( vzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | vzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( vzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(u8) * COUNT + COUNT , ...) | vzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | vzalloc( - sizeof(char) * COUNT + COUNT , ...) | vzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( vzalloc( - sizeof(TYPE) * (COUNT_ID) + array_size(COUNT_ID, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT_ID + array_size(COUNT_ID, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT_CONST + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | vzalloc( - sizeof(THING) * (COUNT_ID) + array_size(COUNT_ID, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT_ID + array_size(COUNT_ID, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT_CONST + array_size(COUNT_CONST, sizeof(THING)) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ vzalloc( - SIZE * COUNT + array_size(COUNT, SIZE) , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( vzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( vzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | vzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | vzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( vzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( vzalloc(C1 * C2 * C3, ...) | vzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants. @@ expression E1, E2; constant C1, C2; @@ ( vzalloc(C1 * C2, ...) | vzalloc( - E1 * E2 + array_size(E1, E2) , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 23:27:37 +02:00
test_dev->info =
vzalloc(array_size(sizeof(struct kmod_test_device_info),
config->num_threads));
if (!test_dev->info)
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
return -ENOMEM;
return 0;
}
/*
* Old kernels may not have this, if you want to port this code to
* test it on older kernels.
*/
#ifdef get_kmod_umh_limit
static unsigned int kmod_init_test_thread_limit(void)
{
return get_kmod_umh_limit();
}
#else
static unsigned int kmod_init_test_thread_limit(void)
{
return TEST_START_NUM_THREADS;
}
#endif
static int __kmod_config_init(struct kmod_test_device *test_dev)
{
struct test_config *config = &test_dev->config;
int ret = -ENOMEM, copied;
__kmod_config_free(config);
copied = config_copy_test_driver_name(config, TEST_START_DRIVER,
strlen(TEST_START_DRIVER));
if (copied != strlen(TEST_START_DRIVER))
goto err_out;
copied = config_copy_test_fs(config, TEST_START_TEST_FS,
strlen(TEST_START_TEST_FS));
if (copied != strlen(TEST_START_TEST_FS))
goto err_out;
config->num_threads = kmod_init_test_thread_limit();
config->test_result = 0;
config->test_case = TEST_START_TEST_CASE;
ret = kmod_config_sync_info(test_dev);
if (ret)
goto err_out;
test_dev->test_is_oom = false;
return 0;
err_out:
test_dev->test_is_oom = true;
WARN_ON(test_dev->test_is_oom);
__kmod_config_free(config);
return ret;
}
static ssize_t reset_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
int ret;
mutex_lock(&test_dev->trigger_mutex);
mutex_lock(&test_dev->config_mutex);
ret = __kmod_config_init(test_dev);
if (ret < 0) {
ret = -ENOMEM;
dev_err(dev, "could not alloc settings for config trigger: %d\n",
ret);
goto out;
}
dev_info(dev, "reset\n");
ret = count;
out:
mutex_unlock(&test_dev->config_mutex);
mutex_unlock(&test_dev->trigger_mutex);
return ret;
}
static DEVICE_ATTR_WO(reset);
static int test_dev_config_update_uint_sync(struct kmod_test_device *test_dev,
const char *buf, size_t size,
unsigned int *config,
int (*test_sync)(struct kmod_test_device *test_dev))
{
int ret;
test_kmod: fix bug which allows negative values on two config options Parsing with kstrtol() enables values to be negative, and we failed to check for negative values when parsing with test_dev_config_update_uint_sync() or test_dev_config_update_uint_range(). test_dev_config_update_uint_range() has a minimum check though so an issue is not present there. test_dev_config_update_uint_sync() is only used for the number of threads to use (config_num_threads_store()), and indeed this would fail with an attempt for a large allocation. Although the issue is only present in practice with the first fix both by using kstrtoul() instead of kstrtol(). Link: http://lkml.kernel.org/r/20170802211450.27928-4-mcgrof@kernel.org Fixes: 39258f448d71 ("kmod: add test driver to stress test the module loader") Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: David Binderman <dcb314@hotmail.com> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jessica Yu <jeyu@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Michal Marek <mmarek@suse.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Petr Mladek <pmladek@suse.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-11 00:23:44 +02:00
unsigned long new;
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
unsigned int old_val;
test_kmod: fix bug which allows negative values on two config options Parsing with kstrtol() enables values to be negative, and we failed to check for negative values when parsing with test_dev_config_update_uint_sync() or test_dev_config_update_uint_range(). test_dev_config_update_uint_range() has a minimum check though so an issue is not present there. test_dev_config_update_uint_sync() is only used for the number of threads to use (config_num_threads_store()), and indeed this would fail with an attempt for a large allocation. Although the issue is only present in practice with the first fix both by using kstrtoul() instead of kstrtol(). Link: http://lkml.kernel.org/r/20170802211450.27928-4-mcgrof@kernel.org Fixes: 39258f448d71 ("kmod: add test driver to stress test the module loader") Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: David Binderman <dcb314@hotmail.com> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jessica Yu <jeyu@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Michal Marek <mmarek@suse.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Petr Mladek <pmladek@suse.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-11 00:23:44 +02:00
ret = kstrtoul(buf, 10, &new);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
if (ret)
return ret;
if (new > UINT_MAX)
return -EINVAL;
mutex_lock(&test_dev->config_mutex);
old_val = *config;
*(unsigned int *)config = new;
ret = test_sync(test_dev);
if (ret) {
*(unsigned int *)config = old_val;
ret = test_sync(test_dev);
WARN_ON(ret);
mutex_unlock(&test_dev->config_mutex);
return -EINVAL;
}
mutex_unlock(&test_dev->config_mutex);
/* Always return full write size even if we didn't consume all */
return size;
}
static int test_dev_config_update_uint_range(struct kmod_test_device *test_dev,
const char *buf, size_t size,
unsigned int *config,
unsigned int min,
unsigned int max)
{
int ret;
test_kmod: fix bug which allows negative values on two config options Parsing with kstrtol() enables values to be negative, and we failed to check for negative values when parsing with test_dev_config_update_uint_sync() or test_dev_config_update_uint_range(). test_dev_config_update_uint_range() has a minimum check though so an issue is not present there. test_dev_config_update_uint_sync() is only used for the number of threads to use (config_num_threads_store()), and indeed this would fail with an attempt for a large allocation. Although the issue is only present in practice with the first fix both by using kstrtoul() instead of kstrtol(). Link: http://lkml.kernel.org/r/20170802211450.27928-4-mcgrof@kernel.org Fixes: 39258f448d71 ("kmod: add test driver to stress test the module loader") Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: David Binderman <dcb314@hotmail.com> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jessica Yu <jeyu@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Michal Marek <mmarek@suse.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Petr Mladek <pmladek@suse.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-11 00:23:44 +02:00
unsigned long new;
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
test_kmod: fix bug which allows negative values on two config options Parsing with kstrtol() enables values to be negative, and we failed to check for negative values when parsing with test_dev_config_update_uint_sync() or test_dev_config_update_uint_range(). test_dev_config_update_uint_range() has a minimum check though so an issue is not present there. test_dev_config_update_uint_sync() is only used for the number of threads to use (config_num_threads_store()), and indeed this would fail with an attempt for a large allocation. Although the issue is only present in practice with the first fix both by using kstrtoul() instead of kstrtol(). Link: http://lkml.kernel.org/r/20170802211450.27928-4-mcgrof@kernel.org Fixes: 39258f448d71 ("kmod: add test driver to stress test the module loader") Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: David Binderman <dcb314@hotmail.com> Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Jessica Yu <jeyu@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Michal Marek <mmarek@suse.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Petr Mladek <pmladek@suse.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-08-11 00:23:44 +02:00
ret = kstrtoul(buf, 10, &new);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
if (ret)
return ret;
if (new < min || new > max)
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
return -EINVAL;
mutex_lock(&test_dev->config_mutex);
*config = new;
mutex_unlock(&test_dev->config_mutex);
/* Always return full write size even if we didn't consume all */
return size;
}
static int test_dev_config_update_int(struct kmod_test_device *test_dev,
const char *buf, size_t size,
int *config)
{
int ret;
long new;
ret = kstrtol(buf, 10, &new);
if (ret)
return ret;
if (new < INT_MIN || new > INT_MAX)
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
return -EINVAL;
mutex_lock(&test_dev->config_mutex);
*config = new;
mutex_unlock(&test_dev->config_mutex);
/* Always return full write size even if we didn't consume all */
return size;
}
static ssize_t test_dev_config_show_int(struct kmod_test_device *test_dev,
char *buf,
int config)
{
int val;
mutex_lock(&test_dev->config_mutex);
val = config;
mutex_unlock(&test_dev->config_mutex);
return snprintf(buf, PAGE_SIZE, "%d\n", val);
}
static ssize_t test_dev_config_show_uint(struct kmod_test_device *test_dev,
char *buf,
unsigned int config)
{
unsigned int val;
mutex_lock(&test_dev->config_mutex);
val = config;
mutex_unlock(&test_dev->config_mutex);
return snprintf(buf, PAGE_SIZE, "%u\n", val);
}
static ssize_t test_result_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return test_dev_config_update_int(test_dev, buf, count,
&config->test_result);
}
static ssize_t config_num_threads_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return test_dev_config_update_uint_sync(test_dev, buf, count,
&config->num_threads,
kmod_config_sync_info);
}
static ssize_t config_num_threads_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return test_dev_config_show_int(test_dev, buf, config->num_threads);
}
static DEVICE_ATTR_RW(config_num_threads);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
static ssize_t config_test_case_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return test_dev_config_update_uint_range(test_dev, buf, count,
&config->test_case,
__TEST_KMOD_INVALID + 1,
__TEST_KMOD_MAX - 1);
}
static ssize_t config_test_case_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return test_dev_config_show_uint(test_dev, buf, config->test_case);
}
static DEVICE_ATTR_RW(config_test_case);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
static ssize_t test_result_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct kmod_test_device *test_dev = dev_to_test_dev(dev);
struct test_config *config = &test_dev->config;
return test_dev_config_show_int(test_dev, buf, config->test_result);
}
static DEVICE_ATTR_RW(test_result);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
#define TEST_KMOD_DEV_ATTR(name) &dev_attr_##name.attr
static struct attribute *test_dev_attrs[] = {
TEST_KMOD_DEV_ATTR(trigger_config),
TEST_KMOD_DEV_ATTR(config),
TEST_KMOD_DEV_ATTR(reset),
TEST_KMOD_DEV_ATTR(config_test_driver),
TEST_KMOD_DEV_ATTR(config_test_fs),
TEST_KMOD_DEV_ATTR(config_num_threads),
TEST_KMOD_DEV_ATTR(config_test_case),
TEST_KMOD_DEV_ATTR(test_result),
NULL,
};
ATTRIBUTE_GROUPS(test_dev);
static int kmod_config_init(struct kmod_test_device *test_dev)
{
int ret;
mutex_lock(&test_dev->config_mutex);
ret = __kmod_config_init(test_dev);
mutex_unlock(&test_dev->config_mutex);
return ret;
}
static struct kmod_test_device *alloc_test_dev_kmod(int idx)
{
int ret;
struct kmod_test_device *test_dev;
struct miscdevice *misc_dev;
test_dev = vzalloc(sizeof(struct kmod_test_device));
if (!test_dev)
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
goto err_out;
mutex_init(&test_dev->config_mutex);
mutex_init(&test_dev->trigger_mutex);
mutex_init(&test_dev->thread_mutex);
init_completion(&test_dev->kthreads_done);
ret = kmod_config_init(test_dev);
if (ret < 0) {
pr_err("Cannot alloc kmod_config_init()\n");
goto err_out_free;
}
test_dev->dev_idx = idx;
misc_dev = &test_dev->misc_dev;
misc_dev->minor = MISC_DYNAMIC_MINOR;
misc_dev->name = kasprintf(GFP_KERNEL, "test_kmod%d", idx);
if (!misc_dev->name) {
pr_err("Cannot alloc misc_dev->name\n");
goto err_out_free_config;
}
misc_dev->groups = test_dev_groups;
return test_dev;
err_out_free_config:
free_test_dev_info(test_dev);
kmod_config_free(test_dev);
err_out_free:
vfree(test_dev);
test_dev = NULL;
err_out:
return NULL;
}
static void free_test_dev_kmod(struct kmod_test_device *test_dev)
{
if (test_dev) {
kfree_const(test_dev->misc_dev.name);
test_dev->misc_dev.name = NULL;
free_test_dev_info(test_dev);
kmod_config_free(test_dev);
vfree(test_dev);
test_dev = NULL;
}
}
static struct kmod_test_device *register_test_dev_kmod(void)
{
struct kmod_test_device *test_dev = NULL;
int ret;
mutex_lock(&reg_dev_mutex);
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
/* int should suffice for number of devices, test for wrap */
if (num_test_devs + 1 == INT_MAX) {
kmod: add test driver to stress test the module loader This adds a new stress test driver for kmod: the kernel module loader. The new stress test driver, test_kmod, is only enabled as a module right now. It should be possible to load this as built-in and load tests early (refer to the force_init_test module parameter), however since a lot of test can get a system out of memory fast we leave this disabled for now. Using a system with 1024 MiB of RAM can *easily* get your kernel OOM fast with this test driver. The test_kmod driver exposes API knobs for us to fine tune simple request_module() and get_fs_type() calls. Since these API calls only allow each one parameter a test driver for these is rather simple. Other factors that can help out test driver though are the number of calls we issue and knowing current limitations of each. This exposes configuration as much as possible through userspace to be able to build tests directly from userspace. Since it allows multiple misc devices its will eventually (once we add a knob to let us create new devices at will) also be possible to perform more tests in parallel, provided you have enough memory. We only enable tests we know work as of right now. Demo screenshots: # tools/testing/selftests/kmod/kmod.sh kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0002_driver: OK! - loading kmod test kmod_test_0002_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0002_fs: OK! - loading kmod test kmod_test_0002_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL kmod_test_0003: OK! - loading kmod test kmod_test_0003: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0004: OK! - loading kmod test kmod_test_0004: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0005: OK! - loading kmod test kmod_test_0005: OK! - Return value: 0 (SUCCESS), expected SUCCESS kmod_test_0006: OK! - loading kmod test kmod_test_0006: OK! - Return value: 0 (SUCCESS), expected SUCCESS XXX: add test restult for 0007 Test completed You can also request for specific tests: # tools/testing/selftests/kmod/kmod.sh -t 0001 kmod_test_0001_driver: OK! - loading kmod test kmod_test_0001_driver: OK! - Return value: 256 (MODULE_NOT_FOUND), expected MODULE_NOT_FOUND kmod_test_0001_fs: OK! - loading kmod test kmod_test_0001_fs: OK! - Return value: -22 (-EINVAL), expected -EINVAL Test completed Lastly, the current available number of tests: # tools/testing/selftests/kmod/kmod.sh --help Usage: tools/testing/selftests/kmod/kmod.sh [ -t <4-number-digit> ] Valid tests: 0001-0009 0001 - Simple test - 1 thread for empty string 0002 - Simple test - 1 thread for modules/filesystems that do not exist 0003 - Simple test - 1 thread for get_fs_type() only 0004 - Simple test - 2 threads for get_fs_type() only 0005 - multithreaded tests with default setup - request_module() only 0006 - multithreaded tests with default setup - get_fs_type() only 0007 - multithreaded tests with default setup test request_module() and get_fs_type() 0008 - multithreaded - push kmod_concurrent over max_modprobes for request_module() 0009 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type() The following test cases currently fail, as such they are not currently enabled by default: # tools/testing/selftests/kmod/kmod.sh -t 0008 # tools/testing/selftests/kmod/kmod.sh -t 0009 To be sure to run them as intended please unload both of the modules: o test_module o xfs And ensure they are not loaded on your system prior to testing them. If you use these paritions for your rootfs you can change the default test driver used for get_fs_type() by exporting it into your environment. For example of other test defaults you can override refer to kmod.sh allow_user_defaults(). Behind the scenes this is how we fine tune at a test case prior to hitting a trigger to run it: cat /sys/devices/virtual/misc/test_kmod0/config echo -n "2" > /sys/devices/virtual/misc/test_kmod0/config_test_case echo -n "ext4" > /sys/devices/virtual/misc/test_kmod0/config_test_fs echo -n "80" > /sys/devices/virtual/misc/test_kmod0/config_num_threads cat /sys/devices/virtual/misc/test_kmod0/config echo -n "1" > /sys/devices/virtual/misc/test_kmod0/config_num_threads Finally to trigger: echo -n "1" > /sys/devices/virtual/misc/test_kmod0/trigger_config The kmod.sh script uses the above constructs to build different test cases. A bit of interpretation of the current failures follows, first two premises: a) When request_module() is used userspace figures out an optimized version of module order for us. Once it finds the modules it needs, as per depmod symbol dep map, it will finit_module() the respective modules which are needed for the original request_module() request. b) We have an optimization in place whereby if a kernel uses request_module() on a module already loaded we never bother userspace as the module already is loaded. This is all handled by kernel/kmod.c. A few things to consider to help identify root causes of issues: 0) kmod 19 has a broken heuristic for modules being assumed to be built-in to your kernel and will return 0 even though request_module() failed. Upgrade to a newer version of kmod. 1) A get_fs_type() call for "xfs" will request_module() for "fs-xfs", not for "xfs". The optimization in kernel described in b) fails to catch if we have a lot of consecutive get_fs_type() calls. The reason is the optimization in place does not look for aliases. This means two consecutive get_fs_type() calls will bump kmod_concurrent, whereas request_module() will not. This one explanation why test case 0009 fails at least once for get_fs_type(). 2) If a module fails to load --- for whatever reason (kmod_concurrent limit reached, file not yet present due to rootfs switch, out of memory) we have a period of time during which module request for the same name either with request_module() or get_fs_type() will *also* fail to load even if the file for the module is ready. This explains why *multiple* NULLs are possible on test 0009. 3) finit_module() consumes quite a bit of memory. 4) Filesystems typically also have more dependent modules than other modules, its important to note though that even though a get_fs_type() call does not incur additional kmod_concurrent bumps, since userspace loads dependencies it finds it needs via finit_module_fd(), it *will* take much more memory to load a module with a lot of dependencies. Because of 3) and 4) we will easily run into out of memory failures with certain tests. For instance test 0006 fails on qemu with 1024 MiB of RAM. It panics a box after reaping all userspace processes and still not having enough memory to reap. [arnd@arndb.de: add dependencies for test module] Link: http://lkml.kernel.org/r/20170630154834.3689272-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170628223155.26472-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Jessica Yu <jeyu@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Michal Marek <mmarek@suse.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-14 23:50:08 +02:00
pr_err("reached limit of number of test devices\n");
goto out;
}
test_dev = alloc_test_dev_kmod(num_test_devs);
if (!test_dev)
goto out;
ret = misc_register(&test_dev->misc_dev);
if (ret) {
pr_err("could not register misc device: %d\n", ret);
free_test_dev_kmod(test_dev);
goto out;
}
test_dev->dev = test_dev->misc_dev.this_device;
list_add_tail(&test_dev->list, &reg_test_devs);
dev_info(test_dev->dev, "interface ready\n");
num_test_devs++;
out:
mutex_unlock(&reg_dev_mutex);
return test_dev;
}
static int __init test_kmod_init(void)
{
struct kmod_test_device *test_dev;
int ret;
test_dev = register_test_dev_kmod();
if (!test_dev) {
pr_err("Cannot add first test kmod device\n");
return -ENODEV;
}
/*
* With some work we might be able to gracefully enable
* testing with this driver built-in, for now this seems
* rather risky. For those willing to try have at it,
* and enable the below. Good luck! If that works, try
* lowering the init level for more fun.
*/
if (force_init_test) {
ret = trigger_config_run_type(test_dev,
TEST_KMOD_DRIVER, "tun");
if (WARN_ON(ret))
return ret;
ret = trigger_config_run_type(test_dev,
TEST_KMOD_FS_TYPE, "btrfs");
if (WARN_ON(ret))
return ret;
}
return 0;
}
late_initcall(test_kmod_init);
static
void unregister_test_dev_kmod(struct kmod_test_device *test_dev)
{
mutex_lock(&test_dev->trigger_mutex);
mutex_lock(&test_dev->config_mutex);
test_dev_kmod_stop_tests(test_dev);
dev_info(test_dev->dev, "removing interface\n");
misc_deregister(&test_dev->misc_dev);
kfree(&test_dev->misc_dev.name);
mutex_unlock(&test_dev->config_mutex);
mutex_unlock(&test_dev->trigger_mutex);
free_test_dev_kmod(test_dev);
}
static void __exit test_kmod_exit(void)
{
struct kmod_test_device *test_dev, *tmp;
mutex_lock(&reg_dev_mutex);
list_for_each_entry_safe(test_dev, tmp, &reg_test_devs, list) {
list_del(&test_dev->list);
unregister_test_dev_kmod(test_dev);
}
mutex_unlock(&reg_dev_mutex);
}
module_exit(test_kmod_exit);
MODULE_AUTHOR("Luis R. Rodriguez <mcgrof@kernel.org>");
MODULE_LICENSE("GPL");