lkml.org 
[lkml]   [2012]   [Feb]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectModule/kthread/printk question/problem
I'm writing a kernel module which creates a substantial amount of
kernel threads. After dropping some real stuff, the module is:

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/slab.h>

MODULE_LICENSE("GPL");

static int nrthreads = 128;
module_param(nrthreads, int, 0644);

static int loopcount = 1024;
module_param(loopcount, int, 0644);

static int usehrtime = 0;
module_param(usehrtime, int, 0644);

static int slack = 50000;
module_param(slack, int, 0644);
static int msecs = 1;
module_param(msecs, int, 0644);

static DECLARE_COMPLETION(done);
static struct task_struct **threads;
static atomic_t nrunning;

static int test(void *unused)
{
int i;
ktime_t expires = ktime_set(0, msecs * NSEC_PER_MSEC);
for (i = 0; !kthread_should_stop() && i < loopcount; i++) {
if (usehrtime) {
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_hrtimeout_range(&expires, slack, HRTIMER_MODE_REL);
}
else
schedule_timeout_uninterruptible(msecs_to_jiffies(msecs));
}
if (atomic_dec_and_test(&nrunning)) {
printk("last thread done\n");
complete(&done);
}
return 0;
}
static int __init testmod_init(void)
{
int i;
printk("test begin\n");

atomic_set(&nrunning, nrthreads);

threads = kmalloc(nrthreads * sizeof(struct task_struct *), GFP_KERNEL);
if (!threads)
return -ENOMEM;
for (i = 0; i < nrthreads; i++) {
threads[i] = kthread_run(test, NULL, "test/%d", i);
if (IS_ERR(threads[i])) {
int j, err = PTR_ERR(threads[i]);
for (j = 0; j < i; j++)
kthread_stop(threads[j]);
kfree(threads);
return err;
}
}
return 0;
}
static void __exit testmod_exit(void)
{
wait_for_completion(&done);
kfree(threads);
}
module_init(testmod_init);
module_exit(testmod_exit);

Usually it works as expected, at least from 8 to 128 threads.
But when I'm trying to run it a loop like:

while true; do insmod testmod.ko && rmmod testmod.ko; sleep 1; done

it's also possible to catch a very rare crash (ARM example):

Unable to handle kernel paging request at virtual address 7f1200c4
pgd = 80004000
[7f1200c4] *pgd=bdc28811, *pte=00000000, *ppte=00000000
Internal error: Oops: 80000007 [#1] PREEMPT SMP
Modules linked in: [last unloaded: testmod]
CPU: 1 Tainted: G O (3.3.0-rc2 #3)
PC is at 0x7f1200c4
LR is at __schedule+0x684/0x6e4
pc : [<7f1200c4>] lr : [<802c053c>] psr: 600f0113
sp : bf115f88 ip : 00000000 fp : 00000000
r10: 00000000 r9 : 00000000 r8 : 7f120394
r7 : 00000002 r6 : 00000400 r5 : 7f120204 r4 : bf114000
r3 : 00000000 r2 : bf115ec0 r1 : bf9220c0 r0 : 00000001
Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel
Control: 10c5387d Table: bfbcc04a DAC: 00000015
Process test/126 (pid: 10918, stack limit = 0xbf1142f8)
Stack: (0xbf115f88 to 0xbf116000)
5f80: 000f4240 00000000 bf213e4c 00000000 7f120000 00000013
5fa0: 00000000 80049228 00000000 00000000 00000000 00000000 00000000 00000000
5fc0: dead4ead ffffffff ffffffff 8048b2b8 00000000 00000000 8036a3f9 bf115fdc
5fe0: bf115fdc 271aee1c bf213e4c 8004919c 8000eabc 8000eabc bfefc811 bfefcc11
Code: bad PC value
Note the bad PC, and stack is just a nonsense. I suspect that the kernel calls
testmod_exit() and frees module memory _before_ all test/X threads are really
dead - i.e. the module memory is freed when at least one of the test/X threads
is somewhere in do_exit() or nearby. Is that possible? If yes, what's the better
way to ensure that all test/X threads are really gone at some point of
testmod_exit()?

An interesting thing is that I can't reproduce this fault with both printk()s
commented out. No ideas why.

Dmitry


\
 
 \ /
  Last update: 2012-02-01 17:11    [from the cache]
©2003-2011 Jasper Spaans