linux_dsm_epyc7002/drivers/oprofile/oprof.c
Robert Richter 87121ca504 oprofile: Fix crash when unloading module (hr timer mode)
Oprofile may crash in a KVM guest while unlaoding modules. This
happens if oprofile_arch_init() fails and oprofile switches to the hr
timer mode as a fallback. In this case oprofile_arch_exit() is called,
but it never was initialized properly which causes the crash. This
patch fixes this.

oprofile: using timer interrupt.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
IP: [<ffffffff8123c226>] unregister_syscore_ops+0x41/0x58
PGD 41da3f067 PUD 41d80e067 PMD 0
Oops: 0002 [#1] PREEMPT SMP
CPU 5
Modules linked in: oprofile(-)

Pid: 2382, comm: modprobe Not tainted 3.1.0-rc7-00018-g709a39d #18 Advanced Micro Device Anaheim/Anaheim
RIP: 0010:[<ffffffff8123c226>]  [<ffffffff8123c226>] unregister_syscore_ops+0x41/0x58
RSP: 0018:ffff88041de1de98  EFLAGS: 00010296
RAX: 0000000000000000 RBX: ffffffffa00060e0 RCX: dead000000200200
RDX: 0000000000000000 RSI: dead000000100100 RDI: ffffffff8178c620
RBP: ffff88041de1dea8 R08: 0000000000000001 R09: 0000000000000082
R10: 0000000000000000 R11: ffff88041de1dde8 R12: 0000000000000080
R13: fffffffffffffff5 R14: 0000000000000001 R15: 0000000000610210
FS:  00007f9ae5bef700(0000) GS:ffff88042fd40000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000008 CR3: 000000041ca44000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process modprobe (pid: 2382, threadinfo ffff88041de1c000, task ffff88042db6d040)
Stack:
 ffff88041de1deb8 ffffffffa0006770 ffff88041de1deb8 ffffffffa000251e
 ffff88041de1dec8 ffffffffa00022c2 ffff88041de1ded8 ffffffffa0004993
 ffff88041de1df78 ffffffff81073115 656c69666f72706f 0000000000610200
Call Trace:
 [<ffffffffa000251e>] op_nmi_exit+0x15/0x17 [oprofile]
 [<ffffffffa00022c2>] oprofile_arch_exit+0xe/0x10 [oprofile]
 [<ffffffffa0004993>] oprofile_exit+0x13/0x15 [oprofile]
 [<ffffffff81073115>] sys_delete_module+0x1c3/0x22f
 [<ffffffff811bf09e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [<ffffffff8148070b>] system_call_fastpath+0x16/0x1b
Code: 20 c6 78 81 e8 c5 cc 23 00 48 8b 13 48 8b 43 08 48 be 00 01 10 00 00 00 ad de 48 b9 00 02 20 00 00 00 ad de 48 c7 c7 20 c6 78 81
 89 42 08 48 89 10 48 89 33 48 89 4b 08 e8 a6 c0 23 00 5a 5b
RIP  [<ffffffff8123c226>] unregister_syscore_ops+0x41/0x58
 RSP <ffff88041de1de98>
CR2: 0000000000000008
---[ end trace 06d4e95b6aa3b437 ]---

CC: stable@kernel.org # 2.6.37+
Signed-off-by: Robert Richter <robert.richter@amd.com>
2011-11-04 15:04:33 +01:00

293 lines
5.1 KiB
C

/**
* @file oprof.c
*
* @remark Copyright 2002 OProfile authors
* @remark Read the file COPYING
*
* @author John Levon <levon@movementarian.org>
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/oprofile.h>
#include <linux/moduleparam.h>
#include <linux/workqueue.h>
#include <linux/time.h>
#include <linux/mutex.h>
#include "oprof.h"
#include "event_buffer.h"
#include "cpu_buffer.h"
#include "buffer_sync.h"
#include "oprofile_stats.h"
struct oprofile_operations oprofile_ops;
unsigned long oprofile_started;
unsigned long oprofile_backtrace_depth;
static unsigned long is_setup;
static DEFINE_MUTEX(start_mutex);
/* timer
0 - use performance monitoring hardware if available
1 - use the timer int mechanism regardless
*/
static int timer = 0;
int oprofile_setup(void)
{
int err;
mutex_lock(&start_mutex);
if ((err = alloc_cpu_buffers()))
goto out;
if ((err = alloc_event_buffer()))
goto out1;
if (oprofile_ops.setup && (err = oprofile_ops.setup()))
goto out2;
/* Note even though this starts part of the
* profiling overhead, it's necessary to prevent
* us missing task deaths and eventually oopsing
* when trying to process the event buffer.
*/
if (oprofile_ops.sync_start) {
int sync_ret = oprofile_ops.sync_start();
switch (sync_ret) {
case 0:
goto post_sync;
case 1:
goto do_generic;
case -1:
goto out3;
default:
goto out3;
}
}
do_generic:
if ((err = sync_start()))
goto out3;
post_sync:
is_setup = 1;
mutex_unlock(&start_mutex);
return 0;
out3:
if (oprofile_ops.shutdown)
oprofile_ops.shutdown();
out2:
free_event_buffer();
out1:
free_cpu_buffers();
out:
mutex_unlock(&start_mutex);
return err;
}
#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
static void switch_worker(struct work_struct *work);
static DECLARE_DELAYED_WORK(switch_work, switch_worker);
static void start_switch_worker(void)
{
if (oprofile_ops.switch_events)
schedule_delayed_work(&switch_work, oprofile_time_slice);
}
static void stop_switch_worker(void)
{
cancel_delayed_work_sync(&switch_work);
}
static void switch_worker(struct work_struct *work)
{
if (oprofile_ops.switch_events())
return;
atomic_inc(&oprofile_stats.multiplex_counter);
start_switch_worker();
}
/* User inputs in ms, converts to jiffies */
int oprofile_set_timeout(unsigned long val_msec)
{
int err = 0;
unsigned long time_slice;
mutex_lock(&start_mutex);
if (oprofile_started) {
err = -EBUSY;
goto out;
}
if (!oprofile_ops.switch_events) {
err = -EINVAL;
goto out;
}
time_slice = msecs_to_jiffies(val_msec);
if (time_slice == MAX_JIFFY_OFFSET) {
err = -EINVAL;
goto out;
}
oprofile_time_slice = time_slice;
out:
mutex_unlock(&start_mutex);
return err;
}
#else
static inline void start_switch_worker(void) { }
static inline void stop_switch_worker(void) { }
#endif
/* Actually start profiling (echo 1>/dev/oprofile/enable) */
int oprofile_start(void)
{
int err = -EINVAL;
mutex_lock(&start_mutex);
if (!is_setup)
goto out;
err = 0;
if (oprofile_started)
goto out;
oprofile_reset_stats();
if ((err = oprofile_ops.start()))
goto out;
start_switch_worker();
oprofile_started = 1;
out:
mutex_unlock(&start_mutex);
return err;
}
/* echo 0>/dev/oprofile/enable */
void oprofile_stop(void)
{
mutex_lock(&start_mutex);
if (!oprofile_started)
goto out;
oprofile_ops.stop();
oprofile_started = 0;
stop_switch_worker();
/* wake up the daemon to read what remains */
wake_up_buffer_waiter();
out:
mutex_unlock(&start_mutex);
}
void oprofile_shutdown(void)
{
mutex_lock(&start_mutex);
if (oprofile_ops.sync_stop) {
int sync_ret = oprofile_ops.sync_stop();
switch (sync_ret) {
case 0:
goto post_sync;
case 1:
goto do_generic;
default:
goto post_sync;
}
}
do_generic:
sync_stop();
post_sync:
if (oprofile_ops.shutdown)
oprofile_ops.shutdown();
is_setup = 0;
free_event_buffer();
free_cpu_buffers();
mutex_unlock(&start_mutex);
}
int oprofile_set_ulong(unsigned long *addr, unsigned long val)
{
int err = -EBUSY;
mutex_lock(&start_mutex);
if (!oprofile_started) {
*addr = val;
err = 0;
}
mutex_unlock(&start_mutex);
return err;
}
static int timer_mode;
static int __init oprofile_init(void)
{
int err;
/* always init architecture to setup backtrace support */
err = oprofile_arch_init(&oprofile_ops);
timer_mode = err || timer; /* fall back to timer mode on errors */
if (timer_mode) {
if (!err)
oprofile_arch_exit();
err = oprofile_timer_init(&oprofile_ops);
if (err)
return err;
}
err = oprofilefs_register();
if (!err)
return 0;
/* failed */
if (timer_mode)
oprofile_timer_exit();
else
oprofile_arch_exit();
return err;
}
static void __exit oprofile_exit(void)
{
oprofilefs_unregister();
if (timer_mode)
oprofile_timer_exit();
else
oprofile_arch_exit();
}
module_init(oprofile_init);
module_exit(oprofile_exit);
module_param_named(timer, timer, int, 0644);
MODULE_PARM_DESC(timer, "force use of timer interrupt");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("John Levon <levon@movementarian.org>");
MODULE_DESCRIPTION("OProfile system profiler");