* relegated to obsolescence, but used by various less
* important (or lazy) subsystems.
*/
-#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
+#include <linux/semaphore.h>
+#include <linux/smp_lock.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/bkl.h>
/*
- * The 'big kernel semaphore'
+ * The 'big kernel lock'
*
- * This mutex is taken and released recursively by lock_kernel()
+ * 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.
*
- * Note: code locked by this semaphore will only be serialized against
- * other code using the same locking facility. The code guarantees that
- * the task remains on the same CPU.
- *
* Don't use in new code.
*/
-static DECLARE_MUTEX(kernel_sem);
+static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(kernel_flag);
+
/*
- * Re-acquire the kernel semaphore.
+ * 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.
*
- * This function is called with preemption off.
+ * If it successfully gets the lock, it should increment
+ * the preemption count like any spinlock does.
*
- * We are executing in schedule() so the code must be extremely careful
- * about recursion, both due to the down() and due to the enabling of
- * preemption. schedule() will re-check the preemption flag after
- * reacquiring the semaphore.
+ * (This works on UP too - do_raw_spin_trylock will never
+ * return false in that case)
*/
int __lockfunc __reacquire_kernel_lock(void)
{
- struct task_struct *task = current;
- int saved_lock_depth = task->lock_depth;
-
- BUG_ON(saved_lock_depth < 0);
-
- task->lock_depth = -1;
- preempt_enable_no_resched();
-
- down(&kernel_sem);
-
+ while (!do_raw_spin_trylock(&kernel_flag)) {
+ if (need_resched())
+ return -EAGAIN;
+ cpu_relax();
+ }
preempt_disable();
- task->lock_depth = saved_lock_depth;
-
return 0;
}
void __lockfunc __release_kernel_lock(void)
{
- up(&kernel_sem);
+ do_raw_spin_unlock(&kernel_flag);
+ preempt_enable_no_resched();
}
/*
- * Getting the big kernel semaphore.
+ * 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
+ * do_raw_spin_trylock() will always succeed.
*/
-void __lockfunc lock_kernel(void)
+#ifdef CONFIG_PREEMPT
+static inline void __lock_kernel(void)
{
- struct task_struct *task = current;
- int depth = task->lock_depth + 1;
+ preempt_disable();
+ if (unlikely(!do_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) {
+ do_raw_spin_lock(&kernel_flag);
+ return;
+ }
- if (likely(!depth))
/*
- * No recursion worries - we set up lock_depth _after_
+ * Otherwise, let's wait for the kernel lock
+ * with preemption enabled..
*/
- down(&kernel_sem);
+ do {
+ preempt_enable();
+ while (raw_spin_is_locked(&kernel_flag))
+ cpu_relax();
+ preempt_disable();
+ } while (!do_raw_spin_trylock(&kernel_flag));
+ }
+}
+
+#else
- task->lock_depth = depth;
+/*
+ * Non-preemption case - just get the spinlock
+ */
+static inline void __lock_kernel(void)
+{
+ do_raw_spin_lock(&kernel_flag);
}
+#endif
-void __lockfunc unlock_kernel(void)
+static inline void __unlock_kernel(void)
{
- struct task_struct *task = current;
+ /*
+ * the BKL is not covered by lockdep, so we open-code the
+ * unlocking sequence (and thus avoid the dep-chain ops):
+ */
+ do_raw_spin_unlock(&kernel_flag);
+ preempt_enable();
+}
- BUG_ON(task->lock_depth < 0);
+/*
+ * Getting the big kernel lock.
+ *
+ * This cannot happen asynchronously, so we only need to
+ * worry about other CPU's.
+ */
+void __lockfunc _lock_kernel(const char *func, const char *file, int line)
+{
+ int depth = current->lock_depth + 1;
+
+ trace_lock_kernel(func, file, line);
+
+ if (likely(!depth)) {
+ might_sleep();
+ __lock_kernel();
+ }
+ current->lock_depth = depth;
+}
+
+void __lockfunc _unlock_kernel(const char *func, const char *file, int line)
+{
+ BUG_ON(current->lock_depth < 0);
+ if (likely(--current->lock_depth < 0))
+ __unlock_kernel();
- if (likely(--task->lock_depth < 0))
- up(&kernel_sem);
+ trace_unlock_kernel(func, file, line);
}
-EXPORT_SYMBOL(lock_kernel);
-EXPORT_SYMBOL(unlock_kernel);
+EXPORT_SYMBOL(_lock_kernel);
+EXPORT_SYMBOL(_unlock_kernel);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff