sched: Prepare for per-cpu preempt_count

When using per-cpu preempt_count variables we need to save/restore the
preempt_count on context switch (into per task storage; for instance
the old thread_info::preempt_count variable) because of
PREEMPT_ACTIVE.

However, this means that on fork() the preempt_count value of the last
context switch gets copied and if we had a PREEMPT_ACTIVE switch right
before cloning a child task the child task will now too have
PREEMPT_ACTIVE set and start its life with an extra PREEMPT_ACTIVE
count.

Therefore we need to make init_task_preempt_count() unconditional;
this resets whatever preempt_count we inherited from our parent
process.

Doing so for !per-cpu implementations is harmless.

For !PREEMPT_COUNT kernels we need to be careful not to start life
with an increased preempt_count.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-4k0b7oy1rcdyzochwiixuwi9@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -428,6 +428,14 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+#define PREEMPT_ENABLED		(PREEMPT_NEED_RESCHED)
+
+#ifdef CONFIG_PREEMPT_COUNT
+#define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
+#else
+#define PREEMPT_DISABLED	PREEMPT_ENABLED
+#endif
+
 /*
  * Disable preemption until the scheduler is running.
  * Reset by start_kernel()->sched_init()->init_idle().
@@ -435,9 +443,7 @@ struct task_cputime {
  * We include PREEMPT_ACTIVE to avoid cond_resched() from working
  * before the scheduler is active -- see should_resched().
  */
-#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE + PREEMPT_NEED_RESCHED)
-#define PREEMPT_ENABLED		(PREEMPT_NEED_RESCHED)
-#define PREEMPT_DISABLED	(1 + PREEMPT_NEED_RESCHED)
+#define INIT_PREEMPT_COUNT	(PREEMPT_DISABLED + PREEMPT_ACTIVE)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts

kernel/sched/core.c

@@ -1722,9 +1722,7 @@ void sched_fork(struct task_struct *p)
 #if defined(CONFIG_SMP)
 	p->on_cpu = 0;
 #endif
-#ifdef CONFIG_PREEMPT_COUNT
 	init_task_preempt_count(p);
-#endif
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 #endif