From: Ingo Molnar <mingo@elte.hu>

This is another generic fallout from the voluntary-preempt patchset: a
cleanup of the cond_resched() infrastructure, in preparation of the latency
reduction patches.  The changes:

 - uninline cond_resched() - this makes the footprint smaller,
   especially once the number of cond_resched() points increase.

 - add a 'was rescheduled' return value to cond_resched. This makes it
   symmetric to cond_resched_lock() and later latency reduction patches
   rely on the ability to tell whether there was any preemption.

 - make cond_resched() more robust by using the same mechanism as
   preempt_kernel(): by using PREEMPT_ACTIVE. This preserves the task's
   state - e.g. if the task is in TASK_ZOMBIE but gets preempted via
   cond_resched() just prior scheduling off then this approach preserves
   TASK_ZOMBIE.

 - the patch also adds need_lockbreak() which critical sections can use 
   to detect lock-break requests.

I've tested the patch on x86 SMP and UP.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---

 25-akpm/include/linux/sched.h |   23 ++++++++++++++++-------
 25-akpm/kernel/sched.c        |   23 +++++++++++++++++------
 2 files changed, 33 insertions(+), 13 deletions(-)

diff -puN include/linux/sched.h~preempt-cleanup include/linux/sched.h
--- 25/include/linux/sched.h~preempt-cleanup	2004-12-03 20:56:34.156567600 -0800
+++ 25-akpm/include/linux/sched.h	2004-12-03 20:56:34.163566536 -0800
@@ -1066,15 +1066,24 @@ static inline int need_resched(void)
 	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
 }
 
-extern void __cond_resched(void);
-static inline void cond_resched(void)
-{
-	if (need_resched())
-		__cond_resched();
-}
-
+/*
+ * cond_resched() and cond_resched_lock(): latency reduction via
+ * explicit rescheduling in places that are safe. The return
+ * value indicates whether a reschedule was done in fact.
+ */
+extern int cond_resched(void);
 extern int cond_resched_lock(spinlock_t * lock);
 
+/*
+ * Does a critical section need to be broken due to another
+ * task waiting?:
+ */
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP)
+# define need_lockbreak(lock) ((lock)->break_lock)
+#else
+# define need_lockbreak(lock) 0
+#endif
+
 /* Reevaluate whether the task has signals pending delivery.
    This is required every time the blocked sigset_t changes.
    callers must hold sighand->siglock.  */
diff -puN kernel/sched.c~preempt-cleanup kernel/sched.c
--- 25/kernel/sched.c~preempt-cleanup	2004-12-03 20:56:34.158567296 -0800
+++ 25-akpm/kernel/sched.c	2004-12-03 20:56:34.167565928 -0800
@@ -3451,13 +3451,25 @@ asmlinkage long sys_sched_yield(void)
 	return 0;
 }
 
-void __sched __cond_resched(void)
+static inline void __cond_resched(void)
 {
-	set_current_state(TASK_RUNNING);
-	schedule();
+	do {
+		preempt_count() += PREEMPT_ACTIVE;
+		schedule();
+		preempt_count() -= PREEMPT_ACTIVE;
+	} while (need_resched());
 }
 
-EXPORT_SYMBOL(__cond_resched);
+int __sched cond_resched(void)
+{
+	if (need_resched()) {
+		__cond_resched();
+		return 1;
+	}
+	return 0;
+}
+
+EXPORT_SYMBOL(cond_resched);
 
 /*
  * cond_resched_lock() - if a reschedule is pending, drop the given lock,
@@ -3480,8 +3492,7 @@ int cond_resched_lock(spinlock_t * lock)
 	if (need_resched()) {
 		_raw_spin_unlock(lock);
 		preempt_enable_no_resched();
-		set_current_state(TASK_RUNNING);
-		schedule();
+		__cond_resched();
 		spin_lock(lock);
 		return 1;
 	}
_