[RFC][PATCH 02/11] sched: Create preempt_count invariant

[Peter Zijlstra <peterz@infradead.org>]

[-- Attachment #1: peterz-kill-preempt_active-2.patch --]
[-- Type: text/plain, Size: 1936 bytes --]

Ensure that upon scheduling preempt_count == 2; although currently an
additional PREEMPT_ACTIVE is still possible.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/asm/preempt.h |    3 ++-
 include/asm-generic/preempt.h  |    2 +-
 kernel/sched/core.c            |   14 ++++++++++----
 3 files changed, 13 insertions(+), 6 deletions(-)

--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -31,7 +31,8 @@ static __always_inline void preempt_coun
  * must be macros to avoid header recursion hell
  */
 #define init_task_preempt_count(p) do { \
-	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
+	task_thread_info(p)->saved_preempt_count = \
+		2*PREEMPT_DISABLE_OFFSET + PREEMPT_NEED_RESCHED; \
 } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -24,7 +24,7 @@ static __always_inline void preempt_coun
  * must be macros to avoid header recursion hell
  */
 #define init_task_preempt_count(p) do { \
-	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+	task_thread_info(p)->preempt_count = 2*PREEMPT_DISABLED; \
 } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2588,11 +2588,17 @@ asmlinkage __visible void schedule_tail(
 {
 	struct rq *rq;
 
-	/* finish_task_switch() drops rq->lock and enables preemtion */
-	preempt_disable();
-	rq = finish_task_switch(prev);
+	/*
+	 * Still have preempt_count() == 2, from:
+	 *
+	 *	schedule()
+	 *	  preempt_disable();			// 1
+	 *	  __schedule()
+	 *	    raw_spin_lock_irq(&rq->lock)	// 2
+	 */
+	rq = finish_task_switch(prev); /* drops rq->lock, preempt_count() == 1 */
 	balance_callback(rq);
-	preempt_enable();
+	preempt_enable(); /* preempt_count() == 0 */
 
 	if (current->set_child_tid)
 		put_user(task_pid_vnr(current), current->set_child_tid);