@@ -50,7 +50,7 @@ static inline void mwait_idle_with_hints
if (!need_resched())
__mwait(eax, ecx);
}
- __current_clr_polling();
+ current_clr_polling();
}
#endif /* _ASM_X86_MWAIT_H */
@@ -116,6 +116,21 @@ do { \
#endif /* CONFIG_PREEMPT_COUNT */
+#ifdef CONFIG_PREEMPT
+#define preempt_set_need_resched() \
+do { \
+ set_preempt_need_resched(); \
+} while (0)
+#define preempt_fold_need_resched() \
+do { \
+ if (tif_need_resched()) \
+ set_preempt_need_resched(); \
+} while (0)
+#else
+#define preempt_set_need_resched() do { } while (0)
+#define preempt_fold_need_resched() do { } while (0)
+#endif
+
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier;
@@ -2628,6 +2628,21 @@ static inline bool __must_check current_
}
#endif
+static inline void current_clr_polling(void)
+{
+ __current_clr_polling();
+
+ /*
+ * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
+ * Once the bit is cleared, we'll get IPIs with every new
+ * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
+ * fold.
+ */
+ smp_mb(); /* paired with resched_task() */
+
+ preempt_fold_need_resched();
+}
+
static __always_inline bool need_resched(void)
{
return unlikely(tif_need_resched());
@@ -105,14 +105,17 @@ static void cpu_idle_loop(void)
__current_set_polling();
}
arch_cpu_idle_exit();
- /*
- * We need to test and propagate the TIF_NEED_RESCHED
- * bit here because we might not have send the
- * reschedule IPI to idle tasks.
- */
- if (tif_need_resched())
- set_preempt_need_resched();
}
+
+ /*
+ * Since we fell out of the loop above, we know
+ * TIF_NEED_RESCHED must be set, propagate it into
+ * PREEMPT_NEED_RESCHED.
+ *
+ * This is required because for polling idle loops we will
+ * not have had an IPI to fold the state for us.
+ */
+ preempt_set_need_resched();
tick_nohz_idle_exit();
schedule_preempt_disabled();
}
@@ -1499,8 +1499,7 @@ void scheduler_ipi(void)
* TIF_NEED_RESCHED remotely (for the first time) will also send
* this IPI.
*/
- if (tif_need_resched())
- set_preempt_need_resched();
+ preempt_fold_need_resched();
if (llist_empty(&this_rq()->wake_list)
&& !tick_nohz_full_cpu(smp_processor_id())
With various drivers wanting to inject idle time; we get people calling idle routines outside of the idle loop proper. Therefore we need to be extra careful about not missing TIF_NEED_RESCHED -> PREEMPT_NEED_RESCHED propagations. While looking at this, I also realized there's a small window in the existing idle loop where we can miss TIF_NEED_RESCHED; when it hits right after the tif_need_resched() test at the end of the loop but right before the need_resched() test at the start of the loop. So move preempt_fold_need_resched() out of the loop where we're guaranteed to have TIF_NEED_RESCHED set. Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> --- arch/x86/include/asm/mwait.h | 2 +- include/linux/preempt.h | 15 +++++++++++++++ include/linux/sched.h | 15 +++++++++++++++ kernel/cpu/idle.c | 17 ++++++++++------- kernel/sched/core.c | 3 +-- 5 files changed, 42 insertions(+), 10 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-pm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html