Commit-ID: eb797bf5bba817f2178e6126fb01efee27192a2d
Gitweb: http://git.kernel.org/tip/eb797bf5bba817f2178e6126fb01efee27192a2d
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Wed, 20 Nov 2013 12:22:37 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Sun, 12 Jan 2014 10:48:23 +0100
sched/preempt: Fix up missed PREEMPT_NEED_RESCHED folding
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.
Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/n/tip-x9jgh45oeayzajz2mjt0y7d6@xxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
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(-)
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 19b71c4..1da25a5 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -53,7 +53,7 @@ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
if (!need_resched())
__mwait(eax, ecx);
}
- __current_clr_polling();
+ current_clr_polling();
}
#endif /* _ASM_X86_MWAIT_H */
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index a3d9dc8..ef4e80c 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.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;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 53f97eb..6340654 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2627,6 +2627,21 @@ static inline bool __must_check current_clr_polling_and_test(void)
}
#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());
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 988573a..277f494 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -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();
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a88f4a4..98a7a1c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -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())
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|