[PATCH 09/11] Maintain preemptability count even for !CONFIG_PREEMPT kernels

[Gleb Natapov <gleb@redhat.com>]

Do not preempt kernel. Just maintain counter to know if task can sleep.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 include/linux/hardirq.h |    6 ++----
 include/linux/preempt.h |   22 ++++++++++++++++------
 kernel/sched.c          |    6 ------
 lib/kernel_lock.c       |    1 +
 4 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 6d527ee..a6b6040 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -92,12 +92,11 @@
  */
 #define in_nmi()	(preempt_count() & NMI_MASK)
 
+#define PREEMPT_CHECK_OFFSET 1
 #if defined(CONFIG_PREEMPT)
 # define PREEMPT_INATOMIC_BASE kernel_locked()
-# define PREEMPT_CHECK_OFFSET 1
 #else
 # define PREEMPT_INATOMIC_BASE 0
-# define PREEMPT_CHECK_OFFSET 0
 #endif
 
 /*
@@ -116,12 +115,11 @@
 #define in_atomic_preempt_off() \
 		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET)
 
+#define IRQ_EXIT_OFFSET (HARDIRQ_OFFSET-1)
 #ifdef CONFIG_PREEMPT
 # define preemptible()	(preempt_count() == 0 && !irqs_disabled())
-# define IRQ_EXIT_OFFSET (HARDIRQ_OFFSET-1)
 #else
 # define preemptible()	0
-# define IRQ_EXIT_OFFSET HARDIRQ_OFFSET
 #endif
 
 #if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS)
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 72b1a10..7d039ca 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -82,14 +82,24 @@ do { \
 
 #else
 
-#define preempt_disable()		do { } while (0)
-#define preempt_enable_no_resched()	do { } while (0)
-#define preempt_enable()		do { } while (0)
+#define preempt_disable() \
+do { \
+	inc_preempt_count(); \
+	barrier(); \
+} while (0)
+
+#define preempt_enable() \
+do { \
+	barrier(); \
+	dec_preempt_count(); \
+} while (0)
+
+#define preempt_enable_no_resched()	preempt_enable()
 #define preempt_check_resched()		do { } while (0)
 
-#define preempt_disable_notrace()		do { } while (0)
-#define preempt_enable_no_resched_notrace()	do { } while (0)
-#define preempt_enable_notrace()		do { } while (0)
+#define preempt_disable_notrace()		preempt_disable()
+#define preempt_enable_no_resched_notrace()	preempt_enable()
+#define preempt_enable_notrace()		preempt_enable()
 
 #endif
 
diff --git a/kernel/sched.c b/kernel/sched.c
index e886895..adb0415 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2561,10 +2561,8 @@ void sched_fork(struct task_struct *p, int clone_flags)
 #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
 	p->oncpu = 0;
 #endif
-#ifdef CONFIG_PREEMPT
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
-#endif
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 
 	put_cpu();
@@ -6944,11 +6942,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	spin_unlock_irqrestore(&rq->lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
-#if defined(CONFIG_PREEMPT)
 	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
-#else
-	task_thread_info(idle)->preempt_count = 0;
-#endif
 	/*
 	 * The idle tasks have their own, simple scheduling class:
 	 */
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index 39f1029..6e2659d 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -93,6 +93,7 @@ static inline void __lock_kernel(void)
  */
 static inline void __lock_kernel(void)
 {
+	preempt_disable();
 	_raw_spin_lock(&kernel_flag);
 }
 #endif
-- 
1.6.3.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>