[GIT pull] scheduler fixes for 4.11

[Thomas Gleixner]

Linus,

please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

This update provides:

  - Make the scheduler clock switch to unstable mode smooth so the
    timestamps stay at microseconds granularity instead of switching to
    tick granularity.

  - Unbreak perf test tsc by taking the new offset into account which was
    added in order to proveide better sched clock continuity

  - Switching sched clock to unstable mode runs all clock related
    computations which affect the sched clock output itself from a work
    queue. In case of preemption sched clock uses half updated data and
    provides wrong timestamps. Keep the math in the protected context and
    delegate only the static key switch to workqueue context.

  - Remove a duplicate header include

Thanks,

	tglx

------------------>
Ingo Molnar (1):
      sched/headers: Remove duplicate #include <linux/sched/debug.h> line

Pavel Tatashin (1):
      sched/clock: Fix broken stable to unstable transfer

Peter Zijlstra (2):
      sched/clock: Fix clear_sched_clock_stable() preempt wobbly
      sched/clock, x86/perf: Fix "perf test tsc"


 arch/x86/events/core.c       |  9 ++++++---
 arch/x86/include/asm/timer.h |  2 ++
 arch/x86/kernel/tsc.c        |  4 ++--
 drivers/tty/vt/keyboard.c    |  1 -
 include/linux/sched/clock.h  | 13 +++++++------
 kernel/sched/clock.c         | 46 ++++++++++++++++++++++++++------------------
 6 files changed, 44 insertions(+), 31 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2aa1ad194db2..580b60f5ac83 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2256,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
 	struct cyc2ns_data *data;
+	u64 offset;
 
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
@@ -2263,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event,
 		!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!sched_clock_stable())
+	if (!using_native_sched_clock() || !sched_clock_stable())
 		return;
 
 	data = cyc2ns_read_begin();
 
+	offset = data->cyc2ns_offset + __sched_clock_offset;
+
 	/*
 	 * Internal timekeeping for enabled/running/stopped times
 	 * is always in the local_clock domain.
@@ -2275,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 1;
 	userpg->time_mult = data->cyc2ns_mul;
 	userpg->time_shift = data->cyc2ns_shift;
-	userpg->time_offset = data->cyc2ns_offset - now;
+	userpg->time_offset = offset - now;
 
 	/*
 	 * cap_user_time_zero doesn't make sense when we're using a different
@@ -2283,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 */
 	if (!event->attr.use_clockid) {
 		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = data->cyc2ns_offset;
+		userpg->time_zero = offset;
 	}
 
 	cyc2ns_read_end(data);
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index a04eabd43d06..27e9f9d769b8 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
+extern bool using_native_sched_clock(void);
+
 /*
  * We use the full linear equation: f(x) = a + b*x, in order to allow
  * a continuous function in the face of dynamic freq changes.
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c73a7f9e881a..714dfba6a1e7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -328,7 +328,7 @@ unsigned long long sched_clock(void)
 	return paravirt_sched_clock();
 }
 
-static inline bool using_native_sched_clock(void)
+bool using_native_sched_clock(void)
 {
 	return pv_time_ops.sched_clock == native_sched_clock;
 }
@@ -336,7 +336,7 @@ static inline bool using_native_sched_clock(void)
 unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
 
-static inline bool using_native_sched_clock(void) { return true; }
+bool using_native_sched_clock(void) { return true; }
 #endif
 
 int check_tsc_unstable(void)
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index c5f0fc906136..8af8d9542663 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
-#include <linux/sched/debug.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/mm.h>
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 4a68c6791207..34fe92ce1ebd 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -54,15 +54,16 @@ static inline u64 local_clock(void)
 }
 #else
 extern void sched_clock_init_late(void);
-/*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
- */
 extern int sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
+/*
+ * When sched_clock_stable(), __sched_clock_offset provides the offset
+ * between local_clock() and sched_clock().
+ */
+extern u64 __sched_clock_offset;
+
+
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index a08795e21628..00a45c45beca 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -96,10 +96,10 @@ static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
 static int __sched_clock_stable_early = 1;
 
 /*
- * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset
  */
-static __read_mostly u64 raw_offset;
-static __read_mostly u64 gtod_offset;
+__read_mostly u64 __sched_clock_offset;
+static __read_mostly u64 __gtod_offset;
 
 struct sched_clock_data {
 	u64			tick_raw;
@@ -131,17 +131,24 @@ static void __set_sched_clock_stable(void)
 	/*
 	 * Attempt to make the (initial) unstable->stable transition continuous.
 	 */
-	raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
+	__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
 
 	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
-			scd->tick_gtod, gtod_offset,
-			scd->tick_raw,  raw_offset);
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
 
 	static_branch_enable(&__sched_clock_stable);
 	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
-static void __clear_sched_clock_stable(struct work_struct *work)
+static void __sched_clock_work(struct work_struct *work)
+{
+	static_branch_disable(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __sched_clock_work);
+
+static void __clear_sched_clock_stable(void)
 {
 	struct sched_clock_data *scd = this_scd();
 
@@ -154,17 +161,17 @@ static void __clear_sched_clock_stable(struct work_struct *work)
 	 *
 	 * Still do what we can.
 	 */
-	gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod);
 
 	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
-			scd->tick_gtod, gtod_offset,
-			scd->tick_raw,  raw_offset);
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
 
-	static_branch_disable(&__sched_clock_stable);
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-}
 
-static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+	if (sched_clock_stable())
+		schedule_work(&sched_clock_work);
+}
 
 void clear_sched_clock_stable(void)
 {
@@ -173,7 +180,7 @@ void clear_sched_clock_stable(void)
 	smp_mb(); /* matches sched_clock_init_late() */
 
 	if (sched_clock_running == 2)
-		schedule_work(&sched_clock_work);
+		__clear_sched_clock_stable();
 }
 
 void sched_clock_init_late(void)
@@ -214,7 +221,7 @@ static inline u64 wrap_max(u64 x, u64 y)
  */
 static u64 sched_clock_local(struct sched_clock_data *scd)
 {
-	u64 now, clock, old_clock, min_clock, max_clock;
+	u64 now, clock, old_clock, min_clock, max_clock, gtod;
 	s64 delta;
 
 again:
@@ -231,9 +238,10 @@ static u64 sched_clock_local(struct sched_clock_data *scd)
 	 *		      scd->tick_gtod + TICK_NSEC);
 	 */
 
-	clock = scd->tick_gtod + gtod_offset + delta;
-	min_clock = wrap_max(scd->tick_gtod, old_clock);
-	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
+	gtod = scd->tick_gtod + __gtod_offset;
+	clock = gtod + delta;
+	min_clock = wrap_max(gtod, old_clock);
+	max_clock = wrap_max(old_clock, gtod + TICK_NSEC);
 
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
@@ -317,7 +325,7 @@ u64 sched_clock_cpu(int cpu)
 	u64 clock;
 
 	if (sched_clock_stable())
-		return sched_clock() + raw_offset;
+		return sched_clock() + __sched_clock_offset;
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;