Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The main changes are:

   - irqtime accounting cleanups and enhancements. (Frederic Weisbecker)

   - schedstat debugging enhancements, make it more broadly runtime
     available. (Josh Poimboeuf)

   - More work on asymmetric topology/capacity scheduling. (Morten
     Rasmussen)

   - sched/wait fixes and cleanups. (Oleg Nesterov)

   - PELT (per entity load tracking) improvements. (Peter Zijlstra)

   - Rewrite and enhance select_idle_siblings(). (Peter Zijlstra)

   - sched/numa enhancements/fixes (Rik van Riel)

   - sched/cputime scalability improvements (Stanislaw Gruszka)

   - Load calculation arithmetics fixes. (Dietmar Eggemann)

   - sched/deadline enhancements (Tommaso Cucinotta)

   - Fix utilization accounting when switching to the SCHED_NORMAL
     policy. (Vincent Guittot)

   - ... plus misc cleanups and enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/irqtime: Consolidate irqtime flushing code
  sched/irqtime: Consolidate accounting synchronization with u64_stats API
  u64_stats: Introduce IRQs disabled helpers
  sched/irqtime: Remove needless IRQs disablement on kcpustat update
  sched/irqtime: No need for preempt-safe accessors
  sched/fair: Fix min_vruntime tracking
  sched/debug: Add SCHED_WARN_ON()
  sched/core: Fix set_user_nice()
  sched/fair: Introduce set_curr_task() helper
  sched/core, ia64: Rename set_curr_task()
  sched/core: Fix incorrect utilization accounting when switching to fair class
  sched/core: Optimize SCHED_SMT
  sched/core: Rewrite and improve select_idle_siblings()
  sched/core: Replace sd_busy/nr_busy_cpus with sched_domain_shared
  sched/core: Introduce 'struct sched_domain_shared'
  sched/core: Restructure destroy_sched_domain()
  sched/core: Remove unused @cpu argument from destroy_sched_domain*()
  sched/wait: Introduce init_wait_entry()
  sched/wait: Avoid abort_exclusive_wait() in __wait_on_bit_lock()
  sched/wait: Avoid abort_exclusive_wait() in ___wait_event()
  ...

4 files changed, 59 insertions, 42 deletions

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d96a6118d26a..74fd6f05bc5b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -259,17 +259,14 @@ static inline void might_fault(void) { }
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(int state);
 __printf(1, 2)
-void panic(const char *fmt, ...)
-	__noreturn __cold;
+void panic(const char *fmt, ...) __noreturn __cold;
 void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
 extern int oops_may_print(void);
-void do_exit(long error_code)
-	__noreturn;
-void complete_and_exit(struct completion *, long)
-	__noreturn;
+void do_exit(long error_code) __noreturn;
+void complete_and_exit(struct completion *, long) __noreturn;
 
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 98fe95fea30c..f76d75fc9eaf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -448,6 +448,8 @@ static inline void io_schedule(void)
 	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 }
 
+void __noreturn do_task_dead(void);
+
 struct nsproxy;
 struct user_namespace;
 
@@ -1022,7 +1024,8 @@ extern void wake_up_q(struct wake_q_head *head);
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu power */
+#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
@@ -1064,6 +1067,12 @@ extern int sched_domain_level_max;
 
 struct sched_group;
 
+struct sched_domain_shared {
+	atomic_t	ref;
+	atomic_t	nr_busy_cpus;
+	int		has_idle_cores;
+};
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -1094,6 +1103,8 @@ struct sched_domain {
 	u64 max_newidle_lb_cost;
 	unsigned long next_decay_max_lb_cost;
 
+	u64 avg_scan_cost;		/* select_idle_sibling */
+
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
@@ -1132,6 +1143,7 @@ struct sched_domain {
 		void *private;		/* used during construction */
 		struct rcu_head rcu;	/* used during destruction */
 	};
+	struct sched_domain_shared *shared;
 
 	unsigned int span_weight;
 	/*
@@ -1165,6 +1177,7 @@ typedef int (*sched_domain_flags_f)(void);
 
 struct sd_data {
 	struct sched_domain **__percpu sd;
+	struct sched_domain_shared **__percpu sds;
 	struct sched_group **__percpu sg;
 	struct sched_group_capacity **__percpu sgc;
 };
@@ -2568,7 +2581,7 @@ static inline bool is_idle_task(const struct task_struct *p)
 	return p->pid == 0;
 }
 extern struct task_struct *curr_task(int cpu);
-extern void set_curr_task(int cpu, struct task_struct *p);
+extern void ia64_set_curr_task(int cpu, struct task_struct *p);
 
 void yield(void);
 
@@ -3206,7 +3219,11 @@ static inline int signal_pending_state(long state, struct task_struct *p)
  * cond_resched_lock() will drop the spinlock before scheduling,
  * cond_resched_softirq() will enable bhs before scheduling.
  */
+#ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
+#else
+static inline int _cond_resched(void) { return 0; }
+#endif
 
 #define cond_resched() ({			\
 	___might_sleep(__FILE__, __LINE__, 0);	\
@@ -3236,6 +3253,15 @@ static inline void cond_resched_rcu(void)
 #endif
 }
 
+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	return p->preempt_disable_ip;
+#else
+	return 0;
+#endif
+}
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPT,
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index d3a2bb712af3..650f3dd6b800 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -103,31 +103,42 @@ static inline void u64_stats_update_end_raw(struct u64_stats_sync *syncp)
 #endif
 }
 
-static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
+static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	return read_seqcount_begin(&syncp->seq);
 #else
-#if BITS_PER_LONG==32
-	preempt_disable();
-#endif
 	return 0;
 #endif
 }
 
-static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
+static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp)
+{
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
+	preempt_disable();
+#endif
+	return __u64_stats_fetch_begin(syncp);
+}
+
+static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
 					 unsigned int start)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	return read_seqcount_retry(&syncp->seq, start);
 #else
-#if BITS_PER_LONG==32
-	preempt_enable();
-#endif
 	return false;
 #endif
 }
 
+static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
+					 unsigned int start)
+{
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
+	preempt_enable();
+#endif
+	return __u64_stats_fetch_retry(syncp, start);
+}
+
 /*
  * In case irq handlers can update u64 counters, readers can use following helpers
  * - SMP 32bit arches use seqcount protection, irq safe.
@@ -136,27 +147,19 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
  */
 static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp)
 {
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	return read_seqcount_begin(&syncp->seq);
-#else
-#if BITS_PER_LONG==32
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
 	local_irq_disable();
 #endif
-	return 0;
-#endif
+	return __u64_stats_fetch_begin(syncp);
 }
 
 static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp,
-					 unsigned int start)
+					     unsigned int start)
 {
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	return read_seqcount_retry(&syncp->seq, start);
-#else
-#if BITS_PER_LONG==32
+#if BITS_PER_LONG==32 && !defined(CONFIG_SMP)
 	local_irq_enable();
 #endif
-	return false;
-#endif
+	return __u64_stats_fetch_retry(syncp, start);
 }
 
 #endif /* _LINUX_U64_STATS_SYNC_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index c3ff74d764fa..2408e8d5c05c 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -248,6 +248,8 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 	(!__builtin_constant_p(state) ||				\
 		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)	\
 
+extern void init_wait_entry(wait_queue_t *__wait, int flags);
+
 /*
  * The below macro ___wait_event() has an explicit shadow of the __ret
  * variable when used from the wait_event_*() macros.
@@ -266,12 +268,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 	wait_queue_t __wait;						\
 	long __ret = ret;	/* explicit shadow */			\
 									\
-	INIT_LIST_HEAD(&__wait.task_list);				\
-	if (exclusive)							\
-		__wait.flags = WQ_FLAG_EXCLUSIVE;			\
-	else								\
-		__wait.flags = 0;					\
-									\
+	init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0);	\
 	for (;;) {							\
 		long __int = prepare_to_wait_event(&wq, &__wait, state);\
 									\
@@ -280,12 +277,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 									\
 		if (___wait_is_interruptible(state) && __int) {		\
 			__ret = __int;					\
-			if (exclusive) {				\
-				abort_exclusive_wait(&wq, &__wait,	\
-						     state, NULL);	\
-				goto __out;				\
-			}						\
-			break;						\
+			goto __out;					\
 		}							\
 									\
 		cmd;							\
@@ -989,7 +981,6 @@ void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
 long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
-void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
 long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
 int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);