96a2c464de
Add two events lock_kernel and unlock_kernel() to trace the bkl uses.
This opens the door for userspace tools to perform statistics about
the callsites that use it, dependencies with other locks (by pairing
the trace with lock events), use with recursivity and so on...
The {__reacquire,release}_kernel_lock() events are not traced because
these are called from schedule, thus the sched events are sufficient
to trace them.
Example of a trace:
hald-addon-stor-4152 [000] 165.875501: unlock_kernel: depth: 0, fs/block_dev.c:1358 __blkdev_put()
hald-addon-stor-4152 [000] 167.832974: lock_kernel: depth: 0, fs/block_dev.c:1167 __blkdev_get()
How to get the callsites that acquire it recursively:
cd /debug/tracing/events/bkl
echo "lock_depth > 0" > filter
firefox-4951 [001] 206.276967: unlock_kernel: depth: 1, fs/reiserfs/super.c:575 reiserfs_dirty_inode()
You can also filter by file and/or line.
v2: Use of FILTER_PTR_STRING attribute for files and lines fields to
make them traceable.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
134 lines
3 KiB
C
134 lines
3 KiB
C
/*
|
|
* lib/kernel_lock.c
|
|
*
|
|
* This is the traditional BKL - big kernel lock. Largely
|
|
* relegated to obsolescence, but used by various less
|
|
* important (or lazy) subsystems.
|
|
*/
|
|
#include <linux/module.h>
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/semaphore.h>
|
|
#define CREATE_TRACE_POINTS
|
|
#include <linux/smp_lock.h>
|
|
|
|
/*
|
|
* The 'big kernel lock'
|
|
*
|
|
* This spinlock is taken and released recursively by lock_kernel()
|
|
* and unlock_kernel(). It is transparently dropped and reacquired
|
|
* over schedule(). It is used to protect legacy code that hasn't
|
|
* been migrated to a proper locking design yet.
|
|
*
|
|
* Don't use in new code.
|
|
*/
|
|
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);
|
|
|
|
|
|
/*
|
|
* Acquire/release the underlying lock from the scheduler.
|
|
*
|
|
* This is called with preemption disabled, and should
|
|
* return an error value if it cannot get the lock and
|
|
* TIF_NEED_RESCHED gets set.
|
|
*
|
|
* If it successfully gets the lock, it should increment
|
|
* the preemption count like any spinlock does.
|
|
*
|
|
* (This works on UP too - _raw_spin_trylock will never
|
|
* return false in that case)
|
|
*/
|
|
int __lockfunc __reacquire_kernel_lock(void)
|
|
{
|
|
while (!_raw_spin_trylock(&kernel_flag)) {
|
|
if (need_resched())
|
|
return -EAGAIN;
|
|
cpu_relax();
|
|
}
|
|
preempt_disable();
|
|
return 0;
|
|
}
|
|
|
|
void __lockfunc __release_kernel_lock(void)
|
|
{
|
|
_raw_spin_unlock(&kernel_flag);
|
|
preempt_enable_no_resched();
|
|
}
|
|
|
|
/*
|
|
* These are the BKL spinlocks - we try to be polite about preemption.
|
|
* If SMP is not on (ie UP preemption), this all goes away because the
|
|
* _raw_spin_trylock() will always succeed.
|
|
*/
|
|
#ifdef CONFIG_PREEMPT
|
|
static inline void __lock_kernel(void)
|
|
{
|
|
preempt_disable();
|
|
if (unlikely(!_raw_spin_trylock(&kernel_flag))) {
|
|
/*
|
|
* If preemption was disabled even before this
|
|
* was called, there's nothing we can be polite
|
|
* about - just spin.
|
|
*/
|
|
if (preempt_count() > 1) {
|
|
_raw_spin_lock(&kernel_flag);
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* Otherwise, let's wait for the kernel lock
|
|
* with preemption enabled..
|
|
*/
|
|
do {
|
|
preempt_enable();
|
|
while (spin_is_locked(&kernel_flag))
|
|
cpu_relax();
|
|
preempt_disable();
|
|
} while (!_raw_spin_trylock(&kernel_flag));
|
|
}
|
|
}
|
|
|
|
#else
|
|
|
|
/*
|
|
* Non-preemption case - just get the spinlock
|
|
*/
|
|
static inline void __lock_kernel(void)
|
|
{
|
|
_raw_spin_lock(&kernel_flag);
|
|
}
|
|
#endif
|
|
|
|
static inline void __unlock_kernel(void)
|
|
{
|
|
/*
|
|
* the BKL is not covered by lockdep, so we open-code the
|
|
* unlocking sequence (and thus avoid the dep-chain ops):
|
|
*/
|
|
_raw_spin_unlock(&kernel_flag);
|
|
preempt_enable();
|
|
}
|
|
|
|
/*
|
|
* Getting the big kernel lock.
|
|
*
|
|
* This cannot happen asynchronously, so we only need to
|
|
* worry about other CPU's.
|
|
*/
|
|
void __lockfunc _lock_kernel(void)
|
|
{
|
|
int depth = current->lock_depth+1;
|
|
if (likely(!depth))
|
|
__lock_kernel();
|
|
current->lock_depth = depth;
|
|
}
|
|
|
|
void __lockfunc _unlock_kernel(void)
|
|
{
|
|
BUG_ON(current->lock_depth < 0);
|
|
if (likely(--current->lock_depth < 0))
|
|
__unlock_kernel();
|
|
}
|
|
|
|
EXPORT_SYMBOL(_lock_kernel);
|
|
EXPORT_SYMBOL(_unlock_kernel);
|
|
|