Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull NOHZ updates from Ingo Molnar:
 "NOHZ enhancements, by Frederic Weisbecker, which reorganizes/refactors
  the NOHZ 'can the tick be stopped?' infrastructure and related code to
  be data driven, and harmonizes the naming and handling of all the
  various properties"

[ This makes the ugly "fetch_or()" macro that the scheduler used
  internally a new generic helper, and does a bad job at it.

  I'm pulling it, but I've asked Ingo and Frederic to get this
  fixed up ]

* 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched-clock: Migrate to use new tick dependency mask model
  posix-cpu-timers: Migrate to use new tick dependency mask model
  sched: Migrate sched to use new tick dependency mask model
  sched: Account rr tasks
  perf: Migrate perf to use new tick dependency mask model
  nohz: Use enum code for tick stop failure tracing message
  nohz: New tick dependency mask
  nohz: Implement wide kick on top of irq work
  atomic: Export fetch_or()

include/linux/atomic.h

@@ -548,6 +548,27 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 }
 #endif
 
+/**
+ * fetch_or - perform *ptr |= mask and return old value of *ptr
+ * @ptr: pointer to value
+ * @mask: mask to OR on the value
+ *
+ * cmpxchg based fetch_or, macro so it works for different integer types
+ */
+#ifndef fetch_or
+#define fetch_or(ptr, mask)						\
+({	typeof(*(ptr)) __old, __val = *(ptr);				\
+	for (;;) {							\
+		__old = cmpxchg((ptr), __val, __val | (mask));		\
+		if (__old == __val)					\
+			break;						\
+		__val = __old;						\
+	}								\
+	__old;								\
+})
+#endif
+
+
 #ifdef CONFIG_GENERIC_ATOMIC64
 #include <asm-generic/atomic64.h>
 #endif

include/linux/perf_event.h

@@ -1110,12 +1110,6 @@ static inline void perf_event_task_tick(void)				{ }
 static inline int perf_event_release_kernel(struct perf_event *event)	{ return 0; }
 #endif
 
-#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL)
-extern bool perf_event_can_stop_tick(void);
-#else
-static inline bool perf_event_can_stop_tick(void)			{ return true; }
-#endif
-
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 extern void perf_restore_debug_store(void);
 #else

include/linux/posix-timers.h

@@ -128,9 +128,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer);
 void run_posix_cpu_timers(struct task_struct *task);
 void posix_cpu_timers_exit(struct task_struct *task);
 void posix_cpu_timers_exit_group(struct task_struct *task);
-
-bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk);
-
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval);
 

include/linux/sched.h

@@ -717,6 +717,10 @@ struct signal_struct {
 	/* Earliest-expiration cache. */
 	struct task_cputime cputime_expires;
 
+#ifdef CONFIG_NO_HZ_FULL
+	unsigned long tick_dep_mask;
+#endif
+
 	struct list_head cpu_timers[3];
 
 	struct pid *tty_old_pgrp;
@@ -1542,6 +1546,10 @@ struct task_struct {
 		VTIME_SYS,
 	} vtime_snap_whence;
 #endif
+
+#ifdef CONFIG_NO_HZ_FULL
+	unsigned long tick_dep_mask;
+#endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	u64 start_time;		/* monotonic time in nsec */
 	u64 real_start_time;	/* boot based time in nsec */
@@ -2356,10 +2364,7 @@ static inline void wake_up_nohz_cpu(int cpu) { }
 #endif
 
 #ifdef CONFIG_NO_HZ_FULL
-extern bool sched_can_stop_tick(void);
 extern u64 scheduler_tick_max_deferment(void);
-#else
-static inline bool sched_can_stop_tick(void) { return false; }
 #endif
 
 #ifdef CONFIG_SCHED_AUTOGROUP

include/linux/tick.h

@@ -97,6 +97,19 @@ static inline void tick_broadcast_exit(void)
 	tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT);
 }
 
+enum tick_dep_bits {
+	TICK_DEP_BIT_POSIX_TIMER	= 0,
+	TICK_DEP_BIT_PERF_EVENTS	= 1,
+	TICK_DEP_BIT_SCHED		= 2,
+	TICK_DEP_BIT_CLOCK_UNSTABLE	= 3
+};
+
+#define TICK_DEP_MASK_NONE		0
+#define TICK_DEP_MASK_POSIX_TIMER	(1 << TICK_DEP_BIT_POSIX_TIMER)
+#define TICK_DEP_MASK_PERF_EVENTS	(1 << TICK_DEP_BIT_PERF_EVENTS)
+#define TICK_DEP_MASK_SCHED		(1 << TICK_DEP_BIT_SCHED)
+#define TICK_DEP_MASK_CLOCK_UNSTABLE	(1 << TICK_DEP_BIT_CLOCK_UNSTABLE)
+
 #ifdef CONFIG_NO_HZ_COMMON
 extern int tick_nohz_enabled;
 extern int tick_nohz_tick_stopped(void);
@@ -154,9 +167,73 @@ static inline int housekeeping_any_cpu(void)
 	return cpumask_any_and(housekeeping_mask, cpu_online_mask);
 }
 
-extern void tick_nohz_full_kick(void);
+extern void tick_nohz_dep_set(enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear(enum tick_dep_bits bit);
+extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit);
+extern void tick_nohz_dep_set_task(struct task_struct *tsk,
+				   enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear_task(struct task_struct *tsk,
+				     enum tick_dep_bits bit);
+extern void tick_nohz_dep_set_signal(struct signal_struct *signal,
+				     enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,
+				       enum tick_dep_bits bit);
+
+/*
+ * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases
+ * on top of static keys.
+ */
+static inline void tick_dep_set(enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_set(bit);
+}
+
+static inline void tick_dep_clear(enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_clear(bit);
+}
+
+static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_cpu(cpu))
+		tick_nohz_dep_set_cpu(cpu, bit);
+}
+
+static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_cpu(cpu))
+		tick_nohz_dep_clear_cpu(cpu, bit);
+}
+
+static inline void tick_dep_set_task(struct task_struct *tsk,
+				     enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_set_task(tsk, bit);
+}
+static inline void tick_dep_clear_task(struct task_struct *tsk,
+				       enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_clear_task(tsk, bit);
+}
+static inline void tick_dep_set_signal(struct signal_struct *signal,
+				       enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_set_signal(signal, bit);
+}
+static inline void tick_dep_clear_signal(struct signal_struct *signal,
+					 enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_clear_signal(signal, bit);
+}
+
 extern void tick_nohz_full_kick_cpu(int cpu);
-extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(void);
 #else
 static inline int housekeeping_any_cpu(void)
@@ -166,9 +243,21 @@ static inline int housekeeping_any_cpu(void)
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
+
+static inline void tick_dep_set(enum tick_dep_bits bit) { }
+static inline void tick_dep_clear(enum tick_dep_bits bit) { }
+static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
+static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { }
+static inline void tick_dep_set_task(struct task_struct *tsk,
+				     enum tick_dep_bits bit) { }
+static inline void tick_dep_clear_task(struct task_struct *tsk,
+				       enum tick_dep_bits bit) { }
+static inline void tick_dep_set_signal(struct signal_struct *signal,
+				       enum tick_dep_bits bit) { }
+static inline void tick_dep_clear_signal(struct signal_struct *signal,
+					 enum tick_dep_bits bit) { }
+
 static inline void tick_nohz_full_kick_cpu(int cpu) { }
-static inline void tick_nohz_full_kick(void) { }
-static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(void) { }
 #endif
 

include/trace/events/timer.h

@@ -328,23 +328,49 @@ TRACE_EVENT(itimer_expire,
 );
 
 #ifdef CONFIG_NO_HZ_COMMON
+
+#define TICK_DEP_NAMES					\
+		tick_dep_name(NONE)			\
+		tick_dep_name(POSIX_TIMER)		\
+		tick_dep_name(PERF_EVENTS)		\
+		tick_dep_name(SCHED)			\
+		tick_dep_name_end(CLOCK_UNSTABLE)
+
+#undef tick_dep_name
+#undef tick_dep_name_end
+
+#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+#define tick_dep_name_end(sdep)  TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+
+TICK_DEP_NAMES
+
+#undef tick_dep_name
+#undef tick_dep_name_end
+
+#define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep },
+#define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep }
+
+#define show_tick_dep_name(val)				\
+	__print_symbolic(val, TICK_DEP_NAMES)
+
 TRACE_EVENT(tick_stop,
 
-	TP_PROTO(int success, char *error_msg),
+	TP_PROTO(int success, int dependency),
 
-	TP_ARGS(success, error_msg),
+	TP_ARGS(success, dependency),
 
 	TP_STRUCT__entry(
 		__field( int ,		success	)
-		__string( msg, 		error_msg )
+		__field( int ,		dependency )
 	),
 
 	TP_fast_assign(
 		__entry->success	= success;
-		__assign_str(msg, error_msg);
+		__entry->dependency	= dependency;
 	),
 
-	TP_printk("success=%s msg=%s",  __entry->success ? "yes" : "no", __get_str(msg))
+	TP_printk("success=%d dependency=%s",  __entry->success, \
+			show_tick_dep_name(__entry->dependency))
 );
 #endif
 

kernel/events/core.c

@@ -3112,17 +3112,6 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 	return rotate;
 }
 
-#ifdef CONFIG_NO_HZ_FULL
-bool perf_event_can_stop_tick(void)
-{
-	if (atomic_read(&nr_freq_events) ||
-	    __this_cpu_read(perf_throttled_count))
-		return false;
-	else
-		return true;
-}
-#endif
-
 void perf_event_task_tick(void)
 {
 	struct list_head *head = this_cpu_ptr(&active_ctx_list);
@@ -3133,6 +3122,7 @@ void perf_event_task_tick(void)
 
 	__this_cpu_inc(perf_throttled_seq);
 	throttled = __this_cpu_xchg(perf_throttled_count, 0);
+	tick_dep_clear_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
 
 	list_for_each_entry_safe(ctx, tmp, head, active_ctx_list)
 		perf_adjust_freq_unthr_context(ctx, throttled);
@@ -3564,6 +3554,28 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
 		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+static DEFINE_SPINLOCK(nr_freq_lock);
+#endif
+
+static void unaccount_freq_event_nohz(void)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	spin_lock(&nr_freq_lock);
+	if (atomic_dec_and_test(&nr_freq_events))
+		tick_nohz_dep_clear(TICK_DEP_BIT_PERF_EVENTS);
+	spin_unlock(&nr_freq_lock);
+#endif
+}
+
+static void unaccount_freq_event(void)
+{
+	if (tick_nohz_full_enabled())
+		unaccount_freq_event_nohz();
+	else
+		atomic_dec(&nr_freq_events);
+}
+
 static void unaccount_event(struct perf_event *event)
 {
 	bool dec = false;
@@ -3580,7 +3592,7 @@ static void unaccount_event(struct perf_event *event)
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
-		atomic_dec(&nr_freq_events);
+		unaccount_freq_event();
 	if (event->attr.context_switch) {
 		dec = true;
 		atomic_dec(&nr_switch_events);
@@ -6424,9 +6436,9 @@ static int __perf_event_overflow(struct perf_event *event,
 		if (unlikely(throttle
 			     && hwc->interrupts >= max_samples_per_tick)) {
 			__this_cpu_inc(perf_throttled_count);
+			tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
 			hwc->interrupts = MAX_INTERRUPTS;
 			perf_log_throttle(event, 0);
-			tick_nohz_full_kick();
 			ret = 1;
 		}
 	}
@@ -7815,6 +7827,27 @@ static void account_event_cpu(struct perf_event *event, int cpu)
 		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
 }
 
+/* Freq events need the tick to stay alive (see perf_event_task_tick). */
+static void account_freq_event_nohz(void)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	/* Lock so we don't race with concurrent unaccount */
+	spin_lock(&nr_freq_lock);
+	if (atomic_inc_return(&nr_freq_events) == 1)
+		tick_nohz_dep_set(TICK_DEP_BIT_PERF_EVENTS);
+	spin_unlock(&nr_freq_lock);
+#endif
+}
+
+static void account_freq_event(void)
+{
+	if (tick_nohz_full_enabled())
+		account_freq_event_nohz();
+	else
+		atomic_inc(&nr_freq_events);
+}
+
+
 static void account_event(struct perf_event *event)
 {
 	bool inc = false;
@@ -7830,10 +7863,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_comm_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
-	if (event->attr.freq) {
-		if (atomic_inc_return(&nr_freq_events) == 1)
-			tick_nohz_full_kick_all();
-	}
+	if (event->attr.freq)
+		account_freq_event();
 	if (event->attr.context_switch) {
 		atomic_inc(&nr_switch_events);
 		inc = true;