Merge branch 'rt/bkl' into rt/base

Conflicts:
	lib/kernel_lock.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 39 insertions, 81 deletions

diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index 67b7217d14a0..f7874462effd 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -11,121 +11,79 @@
 #include <linux/semaphore.h>
 
 /*
- * The 'big kernel lock'
+ * The 'big kernel semaphore'
  *
- * This spinlock is taken and released recursively by lock_kernel()
+ * This mutex 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  __cacheline_aligned_in_smp DEFINE_ATOMIC_SPINLOCK(kernel_flag);
-
+static DEFINE_SEMAPHORE(kernel_sem);
 
 /*
- * Acquire/release the underlying lock from the scheduler.
+ * Re-acquire the kernel semaphore.
  *
- * 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.
- *
- * (This works on UP too - _raw_spin_trylock will never
- * return false in that case)
+ * 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.
  */
 int __lockfunc __reacquire_kernel_lock(void)
 {
-	while (!_raw_spin_trylock(&kernel_flag)) {
-		if (need_resched())
-			return -EAGAIN;
-		cpu_relax();
-	}
+	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);
+
 	preempt_disable();
+	task->lock_depth = saved_lock_depth;
+
 	return 0;
 }
 
 void __lockfunc __release_kernel_lock(void)
 {
-	_raw_spin_unlock(&kernel_flag);
-	preempt_enable_no_resched();
+	up(&kernel_sem);
 }
 
 /*
- * 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.
+ * Getting the big kernel semaphore.
  */
-#ifdef CONFIG_PREEMPT
-static inline void __lock_kernel(void)
+void __lockfunc 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;
-		}
+	struct task_struct *task = current;
+	int depth = task->lock_depth + 1;
 
+	if (likely(!depth))
 		/*
-		 * Otherwise, let's wait for the kernel lock
-		 * with preemption enabled..
+		 * No recursion worries - we set up lock_depth _after_
 		 */
-		do {
-			preempt_enable();
-			while (atomic_spin_is_locked(&kernel_flag))
-				cpu_relax();
-			preempt_disable();
-		} while (!_raw_spin_trylock(&kernel_flag));
-	}
-}
-
-#else
+		down(&kernel_sem);
 
-/*
- * Non-preemption case - just get the spinlock
- */
-static inline void __lock_kernel(void)
-{
-	_raw_spin_lock(&kernel_flag);
+	task->lock_depth = depth;
 }
-#endif
 
-static inline void __unlock_kernel(void)
+void __lockfunc 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();
-}
+	struct task_struct *task = current;
 
-/*
- * 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;
-}
+	BUG_ON(task->lock_depth < 0);
 
-void __lockfunc unlock_kernel(void)
-{
-	BUG_ON(current->lock_depth < 0);
-	if (likely(--current->lock_depth < 0))
-		__unlock_kernel();
+	if (likely(--task->lock_depth < 0))
+		up(&kernel_sem);
 }
 
 EXPORT_SYMBOL(lock_kernel);