[PATCH v2 3/3] sched/preempt: fix cond_resched_lock() and cond_resched_softirq()

[Konstantin Khlebnikov]

These functions check should_resched() before unlocking spinlock/bh-enable:
preempt_count always non-zero => should_resched() always returns false.
cond_resched_lock() worked iff spin_needbreak is set.

This patch adds argument "preempt_offset" to should_resched().

preempt_count offset constants for that:

PREEMPT_DISABLE_OFFSET  - offset after preempt_disable()
PREEMPT_LOCK_OFFSET     - offset after spin_lock()
SOFTIRQ_DISABLE_OFFSET  - offset after local_bh_distable()
SOFTIRQ_LOCK_OFFSET     - offset after spin_lock_bh()

Signed-off-by: Konstantin Khlebnikov <khlebnikov at yandex-team.ru>
---
 arch/x86/include/asm/preempt.h |    4 ++--
 include/asm-generic/preempt.h  |    5 +++--
 include/linux/preempt.h        |   19 ++++++++++++++-----
 include/linux/sched.h          |    6 ------
 kernel/sched/core.c            |    6 +++---
 5 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index dca71714f860..b12f81022a6b 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -90,9 +90,9 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!raw_cpu_read_4(__preempt_count));
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d0a7a4753db2..0bec580a4885 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -71,9 +71,10 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!preempt_count() && tif_need_resched());
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 84991f185173..bea8dd8ff5e0 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -84,13 +84,21 @@
  */
 #define in_nmi()	(preempt_count() & NMI_MASK)
 
+/*
+ * The preempt_count offset after preempt_disable();
+ */
 #if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_DISABLE_OFFSET 1
+# define PREEMPT_DISABLE_OFFSET	PREEMPT_OFFSET
 #else
-# define PREEMPT_DISABLE_OFFSET 0
+# define PREEMPT_DISABLE_OFFSET	0
 #endif
 
 /*
+ * The preempt_count offset after spin_lock()
+ */
+#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+
+/*
  * The preempt_count offset needed for things like:
  *
  *  spin_lock_bh()
@@ -103,7 +111,7 @@
  *
  * Work as expected.
  */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)
 
 /*
  * Are we running in atomic context?  WARNING: this macro cannot
@@ -124,7 +132,8 @@
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
-#define preempt_count_dec_and_test() ({ preempt_count_sub(1); should_resched(); })
+#define preempt_count_dec_and_test() \
+	({ preempt_count_sub(1); should_resched(0); })
 #else
 #define preempt_count_add(val)	__preempt_count_add(val)
 #define preempt_count_sub(val)	__preempt_count_sub(val)
@@ -184,7 +193,7 @@ do { \
 
 #define preempt_check_resched() \
 do { \
-	if (should_resched()) \
+	if (should_resched(0)) \
 		__preempt_schedule(); \
 } while (0)
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ae21f1591615..a8e9b17acdee 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2885,12 +2885,6 @@ extern int _cond_resched(void);
 
 extern int __cond_resched_lock(spinlock_t *lock);
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
-#else
-#define PREEMPT_LOCK_OFFSET	0
-#endif
-
 #define cond_resched_lock(lock) ({				\
 	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78b4bad10081..d9a4d93dc879 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4492,7 +4492,7 @@ SYSCALL_DEFINE0(sched_yield)
 
 int __sched _cond_resched(void)
 {
-	if (should_resched()) {
+	if (should_resched(0)) {
 		preempt_schedule_common();
 		return 1;
 	}
@@ -4510,7 +4510,7 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	int resched = should_resched();
+	int resched = should_resched(PREEMPT_LOCK_OFFSET);
 	int ret = 0;
 
 	lockdep_assert_held(lock);
@@ -4532,7 +4532,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (should_resched()) {
+	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
 		local_bh_enable();
 		preempt_schedule_common();
 		local_bh_disable();