sched: Reduce runqueue lock contention -v3

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -845,18 +845,39 @@ static inline int task_current(struct rq
 	return rq->curr == p;
 }
 
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline int task_running(struct rq *rq, struct task_struct *p)
 {
+#ifdef CONFIG_SMP
+	return p->on_cpu;
+#else
 	return task_current(rq, p);
+#endif
 }
 
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * We can optimise this out completely for !SMP, because the
+	 * SMP rebalancing from interrupt is the only thing that cares
+	 * here.
+	 */
+	next->on_cpu = 1;
+#endif
 }
 
 static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
+	 * We must ensure this doesn't happen until the switch is completely
+	 * finished.
+	 */
+	smp_wmb();
+	prev->on_cpu = 0;
+#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
 	rq->lock.owner = current;

@@ -872,15 +893,6 @@ static inline void finish_lock_switch(st
 }
 
 #else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline int task_running(struct rq *rq, struct task_struct *p)
-{
-#ifdef CONFIG_SMP
-	return p->oncpu;
-#else
-	return task_current(rq, p);
-#endif
-}
-
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
 #ifdef CONFIG_SMP

@@ -889,7 +901,7 @@ static inline void prepare_lock_switch(s
 	 * SMP rebalancing from interrupt is the only thing that cares
 	 * here.
 	 */
-	next->oncpu = 1;
+	next->on_cpu = 1;
 #endif
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	raw_spin_unlock_irq(&rq->lock);

@@ -902,12 +914,12 @@ static inline void finish_lock_switch(st
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->oncpu is cleared, the task can be moved to a different CPU.
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 */
 	smp_wmb();
-	prev->oncpu = 0;
+	prev->on_cpu = 0;
 #endif
 #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_enable();

@@ -2645,8 +2657,8 @@ void sched_fork(struct task_struct *p, i
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
-	p->oncpu = 0;
+#if defined(CONFIG_SMP)
+	p->on_cpu = 0;
 #endif
 #ifdef CONFIG_PREEMPT
 	/* Want to start with kernel preemption disabled. */

@@ -5557,8 +5569,8 @@ void __cpuinit init_idle(struct task_str
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
-	idle->oncpu = 1;
+#if defined(CONFIG_SMP)
+	idle->on_cpu = 1;
 #endif
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1198,9 +1198,7 @@ struct task_struct {
 	int lock_depth;		/* BKL lock depth */
 
 #ifdef CONFIG_SMP
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
-	int oncpu;
-#endif
+	int on_cpu;
 #endif
 
 	int prio, static_prio, normal_prio;

Index: linux-2.6/include/linux/mutex.h
===================================================================
@@ -51,7 +51,7 @@ struct mutex {
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
-	struct thread_info	*owner;
+	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;

Index: linux-2.6/kernel/mutex-debug.c
===================================================================
@@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lo
 		return;
 
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info());
+	DEBUG_LOCKS_WARN_ON(lock->owner != current);
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
 }

Index: linux-2.6/kernel/mutex-debug.h
===================================================================
@@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mute
 
 static inline void mutex_set_owner(struct mutex *lock)
 {
-	lock->owner = current_thread_info();
+	lock->owner = current;
 }
 
 static inline void mutex_clear_owner(struct mutex *lock)

Index: linux-2.6/kernel/mutex.c
===================================================================
@@ -160,7 +160,7 @@ __mutex_lock_common(struct mutex *lock, 
 	 */
 
 	for (;;) {
-		struct thread_info *owner;
+		struct task_struct *owner;
 
 		/*
 		 * If we own the BKL, then don't spin. The owner of

Index: linux-2.6/kernel/mutex.h
===================================================================
@@ -19,7 +19,7 @@
 #ifdef CONFIG_SMP
 static inline void mutex_set_owner(struct mutex *lock)
 {
-	lock->owner = current_thread_info();
+	lock->owner = current;
 }
 
 static inline void mutex_clear_owner(struct mutex *lock)

103 lines not on this page · raw message

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -360,7 +360,7 @@ extern signed long schedule_timeout_inte
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
-extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
+extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
 struct user_namespace;

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2383,10 +2383,10 @@ static inline void ttwu_activate(struct 
 	activate_task(rq, p, en_flags);
 }
 
-static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
-					int wake_flags, bool success)
+static void
+ttwu_post_activation(struct task_struct *p, struct rq *rq, int wake_flags)
 {
-	trace_sched_wakeup(p, success);
+	trace_sched_wakeup(p, true);
 	check_preempt_curr(rq, p, wake_flags);
 
 	p->state = TASK_RUNNING;

@@ -2406,7 +2406,7 @@ static inline void ttwu_post_activation(
 	}
 #endif
 	/* if a worker is waking up, notify workqueue */
-	if ((p->flags & PF_WQ_WORKER) && success)
+	if (p->flags & PF_WQ_WORKER)
 		wq_worker_waking_up(p, cpu_of(rq));
 }
 

@@ -2505,9 +2505,9 @@ static int try_to_wake_up(struct task_st
 #endif /* CONFIG_SMP */
 	ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
 		      cpu == this_cpu, en_flags);
-	success = 1;
 out_running:
-	ttwu_post_activation(p, rq, wake_flags, success);
+	ttwu_post_activation(p, rq, wake_flags);
+	success = 1;
 out:
 	task_rq_unlock(rq, &flags);
 	put_cpu();

@@ -2526,7 +2526,6 @@ static int try_to_wake_up(struct task_st
 static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
-	bool success = false;
 
 	BUG_ON(rq != this_rq());
 	BUG_ON(p == current);

@@ -2541,9 +2540,8 @@ static void try_to_wake_up_local(struct 
 			schedstat_inc(rq, ttwu_local);
 		}
 		ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
-		success = true;
 	}
-	ttwu_post_activation(p, rq, 0, success);
+	ttwu_post_activation(p, rq, 0);
 }
 
 /**

@@ -2705,7 +2703,7 @@ void wake_up_new_task(struct task_struct
 
 	rq = task_rq_lock(p, &flags);
 	activate_task(rq, p, 0);
-	trace_sched_wakeup_new(p, 1);
+	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2366,21 +2366,36 @@ static void update_avg(u64 *avg, u64 sam
 }
 #endif
 
-static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
-				 bool is_sync, bool is_migrate, bool is_local,
-				 unsigned long en_flags)
+static void
+ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags)
 {
+#ifdef CONFIG_SCHEDSTATS
+	int this_cpu = smp_processor_id();
+
+	schedstat_inc(rq, ttwu_count);
 	schedstat_inc(p, se.statistics.nr_wakeups);
-	if (is_sync)
+
+	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.statistics.nr_wakeups_sync);
-	if (is_migrate)
+
+	if (cpu != task_cpu(p))
 		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-	if (is_local)
+
+	if (cpu == this_cpu) {
+		schedstat_inc(rq, ttwu_local);
 		schedstat_inc(p, se.statistics.nr_wakeups_local);
-	else
-		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+	} else {
+		struct sched_domain *sd;
 
-	activate_task(rq, p, en_flags);
+		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+		for_each_domain(this_cpu, sd) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+				schedstat_inc(sd, ttwu_wake_remote);
+				break;
+			}
+		}
+	}
+#endif /* CONFIG_SCHEDSTATS */
 }
 
 static void

@@ -2440,12 +2455,12 @@ static int try_to_wake_up(struct task_st
 	if (!(p->state & state))
 		goto out;
 
+	cpu = task_cpu(p);
+
 	if (p->se.on_rq)
 		goto out_running;
 
-	cpu = task_cpu(p);
 	orig_cpu = cpu;
-
 #ifdef CONFIG_SMP
 	if (unlikely(task_running(rq, p)))
 		goto out_activate;

@@ -2486,27 +2501,12 @@ static int try_to_wake_up(struct task_st
 	WARN_ON(task_cpu(p) != cpu);
 	WARN_ON(p->state != TASK_WAKING);
 
-#ifdef CONFIG_SCHEDSTATS
-	schedstat_inc(rq, ttwu_count);
-	if (cpu == this_cpu)
-		schedstat_inc(rq, ttwu_local);
-	else {
-		struct sched_domain *sd;
-		for_each_domain(this_cpu, sd) {
-			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-				schedstat_inc(sd, ttwu_wake_remote);
-				break;
-			}
-		}
-	}
-#endif /* CONFIG_SCHEDSTATS */
-
 out_activate:
 #endif /* CONFIG_SMP */
-	ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
-		      cpu == this_cpu, en_flags);
+	activate_task(rq, p, en_flags);
 out_running:
 	ttwu_post_activation(p, rq, wake_flags);
+	ttwu_stat(rq, p, cpu, wake_flags);
 	success = 1;
 out:
 	task_rq_unlock(rq, &flags);

@@ -2534,14 +2534,11 @@ static void try_to_wake_up_local(struct 
 	if (!(p->state & TASK_NORMAL))
 		return;
 
-	if (!p->se.on_rq) {
-		if (likely(!task_running(rq, p))) {
-			schedstat_inc(rq, ttwu_count);
-			schedstat_inc(rq, ttwu_local);
-		}
-		ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
-	}
+	if (!p->se.on_rq)
+		activate_task(rq, p, ENQUEUE_WAKEUP);
+
 	ttwu_post_activation(p, rq, 0);
+	ttwu_stat(rq, p, smp_processor_id(), 0);
 }
 
 /**

Index: linux-2.6/arch/x86/include/asm/spinlock.h
===================================================================
@@ -158,18 +158,32 @@ static __always_inline void __ticket_spi
 }
 #endif
 
+#define TICKET_MASK ((1 << TICKET_SHIFT) - 1)
+
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
-	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
+	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK);
 }
 
 static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
-	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
+	return (((tmp >> TICKET_SHIFT) - tmp) & TICKET_MASK) > 1;
+}
+
+static inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	int tmp = ACCESS_ONCE(lock->slock);
+
+	if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK))
+		return; /* not locked */
+
+	/* wait until the current lock holder goes away */
+	while ((lock->slock & TICKET_MASK) == (tmp & TICKET_MASK))
+		cpu_relax();
 }
 
 #ifndef CONFIG_PARAVIRT_SPINLOCKS

@@ -206,7 +220,11 @@ static __always_inline void arch_spin_lo
 	arch_spin_lock(lock);
 }
 
-#endif	/* CONFIG_PARAVIRT_SPINLOCKS */
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	__ticket_spin_unlock_wait(lock);
+}
+#else
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {

@@ -214,6 +232,8 @@ static inline void arch_spin_unlock_wait
 		cpu_relax();
 }
 
+#endif	/* CONFIG_PARAVIRT_SPINLOCKS */
+
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.

index d0faca1..0545bef 100644
@@ -14,8 +14,6 @@
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_spin_is_locked(x)	((x)->lock != 0)
-#define arch_spin_unlock_wait(x) \
-		do { cpu_relax(); } while ((x)->lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t * lock)
 {

index 17eb355..91ede71 100644
@@ -34,8 +34,6 @@ static inline void dsb_sev(void)
  */
 
 #define arch_spin_is_locked(x)		((x)->lock != 0)
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 

index 1942ccf..d1630fc 100644
@@ -46,12 +46,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	__raw_spin_unlock_asm(&lock->lock);
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	while (arch_spin_is_locked(lock))
-		cpu_relax();
-}
-
 static inline int arch_read_can_lock(arch_rwlock_t *rw)
 {
 	return __raw_uncached_fetch_asm(&rw->lock) > 0;

index f171a66..01da21c 100644
@@ -22,12 +22,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 			  : "memory");
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	while (arch_spin_is_locked(lock))
-		cpu_relax();
-}
-
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	return cris_spin_trylock((void *)&lock->slock);

index 1a91c91..7c4de8b 100644
@@ -75,20 +75,6 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 	ACCESS_ONCE(*p) = (tmp + 2) & ~1;
 }
 
-static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	int	*p = (int *)&lock->lock, ticket;
-
-	ia64_invala();
-
-	for (;;) {
-		asm volatile ("ld4.c.nc %0=[%1]" : "=r"(ticket) : "r"(p) : "memory");
-		if (!(((ticket >> TICKET_SHIFT) ^ ticket) & TICKET_MASK))
-			return;
-		cpu_relax();
-	}
-}
-
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	long tmp = ACCESS_ONCE(lock->lock);

@@ -135,11 +121,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 	arch_spin_lock(lock);
 }
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	__ticket_spin_unlock_wait(lock);
-}
-
 #define arch_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
 #define arch_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
 

index 179a064..0e099cc 100644
@@ -26,8 +26,6 @@
 
 #define arch_spin_is_locked(x)		(*(volatile int *)(&(x)->slock) <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-		do { cpu_relax(); } while (arch_spin_is_locked(x))
 
 /**
  * arch_spin_trylock - Try spin lock and return a result

index 396e402..711425f 100644
@@ -42,8 +42,6 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 }
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-	while (arch_spin_is_locked(x)) { cpu_relax(); }
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {

index 9342915..3460e5d 100644
@@ -23,7 +23,6 @@
  */
 
 #define arch_spin_is_locked(x)	(*(volatile signed char *)(&(x)->slock) != 0)
-#define arch_spin_unlock_wait(x) do { barrier(); } while (arch_spin_is_locked(x))
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {

index 74036f4..b419128 100644
@@ -12,8 +12,6 @@ static inline int arch_spin_is_locked(arch_spinlock_t *x)
 }
 
 #define arch_spin_lock(lock) arch_spin_lock_flags(lock, 0)
-#define arch_spin_unlock_wait(x) \
-		do { cpu_relax(); } while (arch_spin_is_locked(x))
 
 static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 					 unsigned long flags)

index f9611bd..c9fd936 100644
@@ -150,13 +150,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	lock->slock = 0;
 }
 
-#ifdef CONFIG_PPC64
-extern void arch_spin_unlock_wait(arch_spinlock_t *lock);
-#else
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
-#endif
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.

index 9b8182e..e800d5f 100644
@@ -82,14 +82,3 @@ void __rw_yield(arch_rwlock_t *rw)
 }
 #endif
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	while (lock->slock) {
-		HMT_low();
-		if (SHARED_PROCESSOR)
-			__spin_yield(lock);
-	}
-	HMT_medium();
-}
-
-EXPORT_SYMBOL(arch_spin_unlock_wait);

index 56612fc..cb98ce7 100644
@@ -35,9 +35,6 @@ _raw_compare_and_swap(volatile unsigned int *lock,
  */
 
 #define arch_spin_is_locked(x) ((x)->owner_cpu != 0)
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) \
-		 arch_spin_relax(lock); } while (0)
 
 extern void arch_spin_lock_wait(arch_spinlock_t *);
 extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);

index bdc0f3b..7ac8916 100644
@@ -25,8 +25,6 @@
 
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's

index 7f9b9db..f10958a 100644
@@ -12,9 +12,6 @@
 
 #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0)
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	__asm__ __volatile__(

index 073936a..2845f6e 100644
@@ -23,10 +23,6 @@
 
 #define arch_spin_is_locked(lp)	((lp)->lock != 0)
 
-#define arch_spin_unlock_wait(lp)	\
-	do {	rmb();			\
-	} while((lp)->lock)
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;

index 88efdde..3ccb768 100644
@@ -61,8 +61,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	lock->current_ticket = old_ticket + TICKET_QUANTUM;
 }
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock);
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.

index 5cd1c40..72a6507 100644
@@ -61,14 +61,6 @@ int arch_spin_trylock(arch_spinlock_t *lock)
 }
 EXPORT_SYMBOL(arch_spin_trylock);
 
-void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	u32 iterations = 0;
-	while (arch_spin_is_locked(lock))
-		delay_backoff(iterations++);
-}
-EXPORT_SYMBOL(arch_spin_unlock_wait);
-
 /*
  * The low byte is always reserved to be the marker for a "tns" operation
  * since the low bit is set to "1" by a tns.  The next seven bits are

index 3089f70..f23106f 100644
@@ -208,12 +208,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	while (arch_spin_is_locked(lock))
-		cpu_relax();
-}
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.

index 17a6378..f246965 100644
@@ -668,8 +668,10 @@ void ata_scsi_error(struct Scsi_Host *host)
 
 		/* initialize eh_tries */
 		ap->eh_tries = ATA_EH_MAX_TRIES;
-	} else
-		spin_unlock_wait(ap->lock);
+	} else {
+		spin_lock_irqsave(ap->lock, flags);
+		spin_unlock_irqrestore(ap->lock, flags);
+	}
 
 	/* If we timed raced normal completion and there is nothing to
 	   recover nr_timedout == 0 why exactly are we doing error recovery ? */

index 80e5358..d7b89ef 100644
@@ -122,12 +122,6 @@ do {								\
 static inline void smp_mb__after_lock(void) { smp_mb(); }
 #endif
 
-/**
- * raw_spin_unlock_wait - wait until the spinlock gets unlocked
- * @lock: the spinlock in question.
- */
-#define raw_spin_unlock_wait(lock)	arch_spin_unlock_wait(&(lock)->raw_lock)
-
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock);
 #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock)

@@ -355,11 +349,6 @@ static inline int spin_trylock_irq(spinlock_t *lock)
 	raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
 })
 
-static inline void spin_unlock_wait(spinlock_t *lock)
-{
-	raw_spin_unlock_wait(&lock->rlock);
-}
-
 static inline int spin_is_locked(spinlock_t *lock)
 {
 	return raw_spin_is_locked(&lock->rlock);

index b14f6a9..53c7a86 100644
@@ -70,7 +70,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 #define arch_read_can_lock(lock)	(((void)(lock), 1))
 #define arch_write_can_lock(lock)	(((void)(lock), 1))
 
-#define arch_spin_unlock_wait(lock) \
-		do { cpu_relax(); } while (arch_spin_is_locked(lock))
-
 #endif /* __LINUX_SPINLOCK_UP_H */

index 676149a..2c6b725 100644
@@ -956,7 +956,8 @@ NORET_TYPE void do_exit(long code)
 	 * an exiting task cleaning up the robust pi futexes.
 	 */
 	smp_mb();
-	raw_spin_unlock_wait(&tsk->pi_lock);
+	raw_spin_lock_irq(&tsk->pi_lock);
+	raw_spin_unlock_irq(&tsk->pi_lock);
 
 	if (unlikely(in_atomic()))
 		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1200,6 +1200,7 @@ struct task_struct {
 #ifdef CONFIG_SMP
 	int on_cpu;
 #endif
+	int on_rq;
 
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -1759,7 +1759,6 @@ static void enqueue_task(struct rq *rq, 
 	update_rq_clock(rq);
 	sched_info_queued(p);
 	p->sched_class->enqueue_task(rq, p, flags);
-	p->se.on_rq = 1;
 }
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)

@@ -1767,7 +1766,6 @@ static void dequeue_task(struct rq *rq, 
 	update_rq_clock(rq);
 	sched_info_dequeued(p);
 	p->sched_class->dequeue_task(rq, p, flags);
-	p->se.on_rq = 0;
 }
 
 /*

@@ -1780,6 +1778,7 @@ static void activate_task(struct rq *rq,
 
 	enqueue_task(rq, p, flags);
 	inc_nr_running(rq);
+	p->on_rq = 1;
 }
 
 /*

@@ -2070,7 +2069,7 @@ static void check_preempt_curr(struct rq
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+	if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 

@@ -2145,7 +2144,7 @@ static bool migrate_task(struct task_str
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
 	 */
-	return p->se.on_rq || task_running(rq, p);
+	return p->on_rq || task_running(rq, p);
 }
 
 /*

@@ -2205,7 +2204,7 @@ unsigned long wait_task_inactive(struct 
 		rq = task_rq_lock(p, &flags);
 		trace_sched_wait_task(p);
 		running = task_running(rq, p);
-		on_rq = p->se.on_rq;
+		on_rq = p->on_rq;
 		ncsw = 0;
 		if (!match_state || p->state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */

@@ -2457,7 +2456,7 @@ static int try_to_wake_up(struct task_st
 
 	cpu = task_cpu(p);
 
-	if (p->se.on_rq)
+	if (p->on_rq)
 		goto out_running;
 
 	orig_cpu = cpu;

@@ -2534,7 +2533,7 @@ static void try_to_wake_up_local(struct 
 	if (!(p->state & TASK_NORMAL))
 		return;
 
-	if (!p->se.on_rq)
+	if (!p->on_rq)
 		activate_task(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_post_activation(p, rq, 0);

@@ -2571,18 +2570,20 @@ int wake_up_state(struct task_struct *p,
  */
 static void __sched_fork(struct task_struct *p)
 {
+	p->on_rq				= 0;
+
+	p->se.on_rq			= 0;
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
+	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
-	p->se.on_rq = 0;
-	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);

@@ -3904,7 +3905,7 @@ static inline void schedule_debug(struct
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-	if (prev->se.on_rq)
+	if (prev->on_rq)
 		update_rq_clock(rq);
 	prev->sched_class->put_prev_task(rq, prev);
 }

@@ -3983,6 +3984,7 @@ asmlinkage void __sched schedule(void)
 					try_to_wake_up_local(to_wakeup);
 			}
 			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+			prev->on_rq = 0;
 		}
 		switch_count = &prev->nvcsw;
 	}

@@ -4546,7 +4548,7 @@ void rt_mutex_setprio(struct task_struct
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
 		dequeue_task(rq, p, 0);

@@ -4595,7 +4597,7 @@ void set_user_nice(struct task_struct *p
 		p->static_prio = NICE_TO_PRIO(nice);
 		goto out_unlock;
 	}
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	if (on_rq)
 		dequeue_task(rq, p, 0);
 

@@ -4729,8 +4731,6 @@ static struct task_struct *find_process_
 static void
 __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
 {
-	BUG_ON(p->se.on_rq);
-
 	p->policy = policy;
 	p->rt_priority = prio;
 	p->normal_prio = normal_prio(p);

@@ -4878,7 +4878,7 @@ static int __sched_setscheduler(struct t
 		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 		goto recheck;
 	}
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
 		deactivate_task(rq, p, 0);

@@ -5737,7 +5737,7 @@ static int __migrate_task(struct task_st
 	 * If we're not on a rq, the next wake-up will ensure we're
 	 * placed properly.
 	 */
-	if (p->se.on_rq) {
+	if (p->on_rq) {
 		deactivate_task(rq_src, p, 0);
 		set_task_cpu(p, dest_cpu);
 		activate_task(rq_dest, p, 0);

@@ -8106,7 +8106,7 @@ static void normalize_task(struct rq *rq
 {
 	int on_rq;
 
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	if (on_rq)
 		deactivate_task(rq, p, 0);
 	__setscheduler(rq, p, SCHED_NORMAL, 0);

@@ -8449,7 +8449,7 @@ void sched_move_task(struct task_struct 
 	rq = task_rq_lock(tsk, &flags);
 
 	running = task_current(rq, tsk);
-	on_rq = tsk->se.on_rq;
+	on_rq = tsk->on_rq;
 
 	if (on_rq)
 		dequeue_task(rq, tsk, 0);

Index: linux-2.6/kernel/sched_debug.c
===================================================================
@@ -127,7 +127,7 @@ static void print_rq(struct seq_file *m,
 	read_lock_irqsave(&tasklist_lock, flags);
 
 	do_each_thread(g, p) {
-		if (!p->se.on_rq || task_cpu(p) != rq_cpu)
+		if (!p->on_rq || task_cpu(p) != rq_cpu)
 			continue;
 
 		print_task(m, rq, p);

Index: linux-2.6/kernel/sched_rt.c
===================================================================
@@ -1132,7 +1132,7 @@ static void put_prev_task_rt(struct rq *
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
 	 */
-	if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
+	if (p->on_rq && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 

@@ -1283,7 +1283,7 @@ static struct rq *find_lock_lowest_rq(st
 				     !cpumask_test_cpu(lowest_rq->cpu,
 						       &task->cpus_allowed) ||
 				     task_running(rq, task) ||
-				     !task->se.on_rq)) {
+				     !task->on_rq)) {
 
 				raw_spin_unlock(&lowest_rq->lock);
 				lowest_rq = NULL;

@@ -1317,7 +1317,7 @@ static struct task_struct *pick_next_pus
 	BUG_ON(task_current(rq, p));
 	BUG_ON(p->rt.nr_cpus_allowed <= 1);
 
-	BUG_ON(!p->se.on_rq);
+	BUG_ON(!p->on_rq);
 	BUG_ON(!rt_task(p));
 
 	return p;

@@ -1463,7 +1463,7 @@ static int pull_rt_task(struct rq *this_
 		 */
 		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
 			WARN_ON(p == src_rq->curr);
-			WARN_ON(!p->se.on_rq);
+			WARN_ON(!p->on_rq);
 
 			/*
 			 * There's a chance that p is higher in priority

@@ -1534,7 +1534,7 @@ static void set_cpus_allowed_rt(struct t
 	 * Update the migration status of the RQ if we have an RT task
 	 * which is running AND changing its weight value.
 	 */
-	if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
+	if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) {
 		struct rq *rq = task_rq(p);
 
 		if (!task_current(rq, p)) {

Index: linux-2.6/kernel/sched_stoptask.c
===================================================================
@@ -26,7 +26,7 @@ static struct task_struct *pick_next_tas
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->se.on_rq)
+	if (stop && stop->on_rq)
 		return stop;
 
 	return NULL;

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2301,7 +2301,7 @@ void task_oncpu_function_call(struct tas
 
 #ifdef CONFIG_SMP
 /*
- * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ * ->cpus_allowed is protected by both rq->lock and p->pi_lock
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {

@@ -2334,7 +2334,7 @@ static int select_fallback_rq(int cpu, s
 }
 
 /*
- * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
 int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)

@@ -2450,7 +2450,8 @@ static int try_to_wake_up(struct task_st
 	this_cpu = get_cpu();
 
 	smp_wmb();
-	rq = task_rq_lock(p, &flags);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rq = __task_rq_lock(p);
 	if (!(p->state & state))
 		goto out;
 

@@ -2508,7 +2509,8 @@ static int try_to_wake_up(struct task_st
 	ttwu_stat(rq, p, cpu, wake_flags);
 	success = 1;
 out:
-	task_rq_unlock(rq, &flags);
+	__task_rq_unlock(rq);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 	put_cpu();
 
 	return success;

@@ -4543,6 +4545,8 @@ void rt_mutex_setprio(struct task_struct
 
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
+	lockdep_assert_held(&p->pi_lock);
+
 	rq = task_rq_lock(p, &flags);
 
 	trace_sched_pi_setprio(p, prio);

@@ -5150,7 +5154,6 @@ long sched_getaffinity(pid_t pid, struct
 {
 	struct task_struct *p;
 	unsigned long flags;
-	struct rq *rq;
 	int retval;
 
 	get_online_cpus();

@@ -5165,9 +5168,9 @@ long sched_getaffinity(pid_t pid, struct
 	if (retval)
 		goto out_unlock;
 
-	rq = task_rq_lock(p, &flags);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
-	task_rq_unlock(rq, &flags);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
 	rcu_read_unlock();

@@ -5652,18 +5655,8 @@ int set_cpus_allowed_ptr(struct task_str
 	unsigned int dest_cpu;
 	int ret = 0;
 
-	/*
-	 * Serialize against TASK_WAKING so that ttwu() and wunt() can
-	 * drop the rq->lock and still rely on ->cpus_allowed.
-	 */
-again:
-	while (task_is_waking(p))
-		cpu_relax();
-	rq = task_rq_lock(p, &flags);
-	if (task_is_waking(p)) {
-		task_rq_unlock(rq, &flags);
-		goto again;
-	}
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rq = __task_rq_lock(p);
 
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;

@@ -5691,13 +5684,15 @@ int set_cpus_allowed_ptr(struct task_str
 	if (migrate_task(p, rq)) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
-		task_rq_unlock(rq, &flags);
+		__task_rq_unlock(rq);
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
 	}
 out:
-	task_rq_unlock(rq, &flags);
+	__task_rq_unlock(rq);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 	return ret;
 }

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1063,8 +1063,7 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
-			       int sd_flag, int flags);
+	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2138,13 +2138,14 @@ static int migration_cpu_stop(void *data
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static bool migrate_task(struct task_struct *p, struct rq *rq)
+static bool need_migrate_task(struct task_struct *p)
 {
 	/*
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
 	 */
-	return p->on_rq || task_running(rq, p);
+	smp_rmb(); /* finish_lock_switch() */
+	return p->on_rq || p->on_cpu;
 }
 
 /*

@@ -2337,9 +2338,9 @@ static int select_fallback_rq(int cpu, s
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
+	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need

@@ -2484,7 +2485,7 @@ static int try_to_wake_up(struct task_st
 		en_flags |= ENQUEUE_WAKING;
 	}
 
-	cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
+	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
 	if (cpu != orig_cpu)
 		set_task_cpu(p, cpu);
 	__task_rq_unlock(rq);

@@ -2680,24 +2681,17 @@ void wake_up_new_task(struct task_struct
 {
 	unsigned long flags;
 	struct rq *rq;
-	int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
 	rq = task_rq_lock(p, &flags);
-	p->state = TASK_WAKING;
 
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
-	 *
-	 * We set TASK_WAKING so that select_task_rq() can drop rq->lock
-	 * without people poking at ->cpus_allowed.
 	 */
-	cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
-	set_task_cpu(p, cpu);
+	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
 
-	p->state = TASK_RUNNING;
 	task_rq_unlock(rq, &flags);
 #endif
 

@@ -2710,7 +2704,6 @@ void wake_up_new_task(struct task_struct
 		p->sched_class->task_woken(rq, p);
 #endif
 	task_rq_unlock(rq, &flags);
-	put_cpu();
 }
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS

@@ -3416,27 +3409,22 @@ void sched_exec(void)
 {
 	struct task_struct *p = current;
 	unsigned long flags;
-	struct rq *rq;
 	int dest_cpu;
 
-	rq = task_rq_lock(p, &flags);
-	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
-	/*
-	 * select_task_rq() can race against ->cpus_allowed
-	 */
-	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-	    likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
+	if (likely(cpu_active(dest_cpu)) && need_migrate_task(p)) {
 		struct migration_arg arg = { p, dest_cpu };
 
-		task_rq_unlock(rq, &flags);
-		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
 		return;
 	}
 unlock:
-	task_rq_unlock(rq, &flags);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 }
 
 #endif

@@ -5681,7 +5669,7 @@ int set_cpus_allowed_ptr(struct task_str
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (migrate_task(p, rq)) {
+	if (need_migrate_task(p)) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
 		__task_rq_unlock(rq);

Index: linux-2.6/kernel/sched_fair.c
===================================================================
@@ -1623,7 +1623,7 @@ static int select_idle_sibling(struct ta
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();

Index: linux-2.6/kernel/sched_idletask.c
===================================================================
@@ -7,7 +7,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }

Index: linux-2.6/kernel/sched_rt.c
===================================================================
@@ -973,11 +973,18 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 {
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();
 
+#if 0
+	/*
+	 * XXX without holding rq->lock the below is racy, need to
+	 * rewrite it in a racy but non-dangerous way so that we mostly
+	 * get the benefit of the heuristic but don't crash the kernel
+	 * if we get it wrong ;-)
+	 */
 	/*
 	 * If the current task is an RT task, then
 	 * try to see if we can wake this RT task up on another

@@ -1002,6 +1009,7 @@ select_task_rq_rt(struct rq *rq, struct 
 
 		return (cpu == -1) ? task_cpu(p) : cpu;
 	}
+#endif
 
 	/*
 	 * Otherwise, just let it ride on the affined RQ and the

Index: linux-2.6/kernel/sched_stoptask.c
===================================================================
@@ -9,8 +9,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct rq *rq, struct task_struct *p,
-		    int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2144,8 +2144,9 @@ static bool need_migrate_task(struct tas
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
 	 */
+	bool running = p->on_rq || p->on_cpu;
 	smp_rmb(); /* finish_lock_switch() */
-	return p->on_rq || p->on_cpu;
+	return running;
 }
 
 /*

@@ -3416,7 +3417,7 @@ void sched_exec(void)
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
-	if (likely(cpu_active(dest_cpu)) && need_migrate_task(p)) {
+	if (likely(cpu_active(dest_cpu))) {
 		struct migration_arg arg = { p, dest_cpu };
 
 		raw_spin_unlock_irqrestore(&p->pi_lock, flags);

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1045,8 +1045,12 @@ struct sched_domain;
 #define WF_FORK		0x02		/* child wakeup after fork */
 
 #define ENQUEUE_WAKEUP		1
-#define ENQUEUE_WAKING		2
-#define ENQUEUE_HEAD		4
+#define ENQUEUE_HEAD		2
+#ifdef CONFIG_SMP
+#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
+#else
+#define ENQUEUE_WAKING		0
+#endif
 
 #define DEQUEUE_SLEEP		1
 

@@ -1067,7 +1071,7 @@ struct sched_class {
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
-	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
+	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
 
 	void (*set_cpus_allowed)(struct task_struct *p,

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2481,7 +2481,7 @@ static int try_to_wake_up(struct task_st
 	p->state = TASK_WAKING;
 
 	if (p->sched_class->task_waking) {
-		p->sched_class->task_waking(rq, p);
+		p->sched_class->task_waking(p);
 		en_flags |= ENQUEUE_WAKING;
 	}
 

Index: linux-2.6/kernel/sched_fair.c
===================================================================
@@ -1338,11 +1338,13 @@ static void yield_task_fair(struct rq *r
 
 #ifdef CONFIG_SMP
 
-static void task_waking_fair(struct rq *rq, struct task_struct *p)
+static void task_waking_fair(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
+	lockdep_assert_held(&task_rq(p)->lock);
+
 	se->vruntime -= cfs_rq->min_vruntime;
 }
 

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -928,12 +928,13 @@ static inline void finish_lock_switch(st
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize ->cpus_allowed
- * against ttwu().
+ * In order to be able to call set_task_cpu() without holding the current
+ * task_rq(p)->lock during wake-ups we need to serialize on something else,
+ * use the wakeup task state.
  */
 static inline int task_is_waking(struct task_struct *p)
 {
-	return unlikely(p->state == TASK_WAKING);
+	return p->state == TASK_WAKING;
 }
 
 /*

@@ -948,7 +949,7 @@ static inline struct rq *__task_rq_lock(
 	for (;;) {
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
+		if (likely(rq == task_rq(p) && !task_is_waking(p)))
 			return rq;
 		raw_spin_unlock(&rq->lock);
 	}

@@ -956,8 +957,7 @@ static inline struct rq *__task_rq_lock(
 
 /*
  * task_rq_lock - lock the runqueue a given task resides on and disable
- * interrupts. Note the ordering: we can safely lookup the task_rq without
- * explicitly disabling preemption.
+ * interrupts.
  */
 static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 	__acquires(rq->lock)

@@ -968,7 +968,7 @@ static struct rq *task_rq_lock(struct ta
 		local_irq_save(*flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
+		if (likely(rq == task_rq(p) && !task_is_waking(p)))
 			return rq;
 		raw_spin_unlock_irqrestore(&rq->lock, *flags);
 	}

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1264,6 +1264,7 @@ struct task_struct {
 
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
+	unsigned sched_contributes_to_load:1;
 
 	pid_t pid;
 	pid_t tgid;

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2467,18 +2467,7 @@ static int try_to_wake_up(struct task_st
 	if (unlikely(task_running(rq, p)))
 		goto out_activate;
 
-	/*
-	 * In order to handle concurrent wakeups and release the rq->lock
-	 * we put the task in TASK_WAKING state.
-	 *
-	 * First fix up the nr_uninterruptible count:
-	 */
-	if (task_contributes_to_load(p)) {
-		if (likely(cpu_online(orig_cpu)))
-			rq->nr_uninterruptible--;
-		else
-			this_rq()->nr_uninterruptible--;
-	}
+	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
 
 	if (p->sched_class->task_waking) {

@@ -2503,6 +2492,9 @@ static int try_to_wake_up(struct task_st
 	WARN_ON(task_cpu(p) != cpu);
 	WARN_ON(p->state != TASK_WAKING);
 
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible--;
+
 out_activate:
 #endif /* CONFIG_SMP */
 	activate_task(rq, p, en_flags);

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2513,9 +2513,9 @@ static int try_to_wake_up(struct task_st
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
  *
- * Put @p on the run-queue if it's not alredy there.  The caller must
+ * Put @p on the run-queue if it's not alredy there. The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.  this_rq() stays locked over invocation.
+ * the current task.
  */
 static void try_to_wake_up_local(struct task_struct *p)
 {

@@ -2523,16 +2523,21 @@ static void try_to_wake_up_local(struct 
 
 	BUG_ON(rq != this_rq());
 	BUG_ON(p == current);
-	lockdep_assert_held(&rq->lock);
+
+	raw_spin_unlock(&rq->lock);
+	raw_spin_lock(&p->pi_lock);
+	raw_spin_lock(&rq->lock);
 
 	if (!(p->state & TASK_NORMAL))
-		return;
+		goto out;
 
 	if (!p->on_rq)
 		activate_task(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_post_activation(p, rq, 0);
 	ttwu_stat(rq, p, smp_processor_id(), 0);
+out:
+	raw_spin_unlock(&p->pi_lock);
 }
 
 /**

@@ -3925,6 +3930,7 @@ pick_next_task(struct rq *rq)
  */
 asmlinkage void __sched schedule(void)
 {
+	struct task_struct *to_wakeup = NULL;
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;

@@ -3958,21 +3964,21 @@ asmlinkage void __sched schedule(void)
 			 * task to maintain concurrency.  If so, wake
 			 * up the task.
 			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
+			if (prev->flags & PF_WQ_WORKER)
 				to_wakeup = wq_worker_sleeping(prev, cpu);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup);
-			}
 			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 			prev->on_rq = 0;
 		}
 		switch_count = &prev->nvcsw;
 	}
 
+	/*
+	 * All three: try_to_wake_up_local(), pre_schedule() and idle_balance()
+	 * can drop rq->lock.
+	 */
+	if (to_wakeup)
+		try_to_wake_up_local(to_wakeup);
 	pre_schedule(rq, prev);
-
 	if (unlikely(!rq->nr_running))
 		idle_balance(cpu, rq);
 

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2440,69 +2440,70 @@ ttwu_post_activation(struct task_struct 
  * Returns %true if @p was woken up, %false if it was already running
  * or @state didn't match @p's state.
  */
-static int try_to_wake_up(struct task_struct *p, unsigned int state,
-			  int wake_flags)
+static int
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 {
-	int cpu, orig_cpu, this_cpu, success = 0;
+	int cpu, this_cpu, success = 0;
 	unsigned long flags;
-	unsigned long en_flags = ENQUEUE_WAKEUP;
 	struct rq *rq;
 
 	this_cpu = get_cpu();
 
 	smp_wmb();
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	rq = __task_rq_lock(p);
 	if (!(p->state & state))
 		goto out;
 
 	cpu = task_cpu(p);
 
-	if (p->on_rq)
-		goto out_running;
+	if (p->on_rq) {
+		rq = __task_rq_lock(p);
+		if (p->on_rq)
+			goto out_running;
+		__task_rq_unlock(rq);
+	}
 
-	orig_cpu = cpu;
 #ifdef CONFIG_SMP
-	if (unlikely(task_running(rq, p)))
-		goto out_activate;
+	while (p->on_cpu)
+		cpu_relax();
 
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
+	/*
+	 * Separate the TASK_WAKING write from the rq->lock unlock wait.
+	 *
+	 * We need to wait for the current rq->lock owner to finish because
+	 * existing task_rq_lock() holders will not have observed
+	 * TASK_WAKING yet and we don't want to move the task from under
+	 * their feet.
+	 */
+	smp_mb();
+	raw_spin_unlock_wait(&task_rq(p)->lock);
 
-	if (p->sched_class->task_waking) {
+	if (p->sched_class->task_waking)
 		p->sched_class->task_waking(p);
-		en_flags |= ENQUEUE_WAKING;
-	}
 
 	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu)
-		set_task_cpu(p, cpu);
-	__task_rq_unlock(rq);
+#endif /* CONFIG_SMP */
 
 	rq = cpu_rq(cpu);
 	raw_spin_lock(&rq->lock);
 
-	/*
-	 * We migrated the task without holding either rq->lock, however
-	 * since the task is not on the task list itself, nobody else
-	 * will try and migrate the task, hence the rq should match the
-	 * cpu we just moved it to.
-	 */
-	WARN_ON(task_cpu(p) != cpu);
-	WARN_ON(p->state != TASK_WAKING);
+#ifdef CONFIG_SMP
+	if (cpu != task_cpu(p))
+		set_task_cpu(p, cpu);
 
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
+#endif
 
-out_activate:
-#endif /* CONFIG_SMP */
-	activate_task(rq, p, en_flags);
+	activate_task(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
 out_running:
 	ttwu_post_activation(p, rq, wake_flags);
 	ttwu_stat(rq, p, cpu, wake_flags);
 	success = 1;
-out:
 	__task_rq_unlock(rq);
+out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 	put_cpu();
 

Index: linux-2.6/kernel/sched_fair.c
===================================================================
@@ -1343,8 +1343,7 @@ static void task_waking_fair(struct task
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-	lockdep_assert_held(&task_rq(p)->lock);
-
+	// XXX racy on 32bit
 	se->vruntime -= cfs_rq->min_vruntime;
 }
 

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2367,10 +2367,11 @@ static void update_avg(u64 *avg, u64 sam
 #endif
 
 static void
-ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags)
+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
 #ifdef CONFIG_SCHEDSTATS
 	int this_cpu = smp_processor_id();
+	struct rq *rq = this_rq();
 
 	schedstat_inc(rq, ttwu_count);
 	schedstat_inc(p, se.statistics.nr_wakeups);

@@ -2491,9 +2492,10 @@ try_to_wake_up(struct task_struct *p, un
 	activate_task(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
 out_running:
 	ttwu_post_activation(p, rq, wake_flags);
-	ttwu_stat(rq, p, cpu, wake_flags);
 	success = 1;
 	__task_rq_unlock(rq);
+
+	ttwu_stat(p, cpu, wake_flags);
 out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 	put_cpu();

@@ -2527,7 +2529,7 @@ static void try_to_wake_up_local(struct 
 		activate_task(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_post_activation(p, rq, 0);
-	ttwu_stat(rq, p, smp_processor_id(), 0);
+	ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
 }

Index: linux-2.6/kernel/sched.c
===================================================================
@@ -2399,8 +2399,11 @@ ttwu_stat(struct task_struct *p, int cpu
 #endif /* CONFIG_SCHEDSTATS */
 }
 
+/*
+ * Mark the task runnable and perform wakeup-preemption.
+ */
 static void
-ttwu_post_activation(struct task_struct *p, struct rq *rq, int wake_flags)
+ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	trace_sched_wakeup(p, true);
 	check_preempt_curr(rq, p, wake_flags);

@@ -2492,7 +2495,7 @@ try_to_wake_up(struct task_struct *p, un
 
 	activate_task(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
 out_running:
-	ttwu_post_activation(p, rq, wake_flags);
+	ttwu_do_wakeup(rq, p, wake_flags);
 	success = 1;
 	__task_rq_unlock(rq);
 

@@ -2529,7 +2532,7 @@ static void try_to_wake_up_local(struct 
 	if (!p->on_rq)
 		activate_task(rq, p, ENQUEUE_WAKEUP);
 
-	ttwu_post_activation(p, rq, 0);
+	ttwu_do_wakeup(rq, p, 0);
 	ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);

Index: linux-2.6/arch/x86/kernel/smp.c
===================================================================
@@ -205,6 +205,7 @@ void smp_reschedule_interrupt(struct pt_
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */
+	sched_ttwu_pending();
 }
 
 void smp_call_function_interrupt(struct pt_regs *regs)

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1020,6 +1020,7 @@ partition_sched_domains(int ndoms_new, c
 }
 #endif	/* !CONFIG_SMP */
 
+void sched_ttwu_pending(void);
 
 struct io_context;			/* See blkdev.h */
 

@@ -1201,6 +1202,7 @@ struct task_struct {
 	int lock_depth;		/* BKL lock depth */
 
 #ifdef CONFIG_SMP
+	struct task_struct *wake_entry;
 	int on_cpu;
 #endif
 	int on_rq;

184 lines not on this page · raw message

Index: linux-2.6/kernel/sched_features.h
===================================================================
@@ -64,3 +64,5 @@ SCHED_FEAT(OWNER_SPIN, 1)
  * Decrement CPU power based on irq activity
  */
 SCHED_FEAT(NONIRQ_POWER, 1)
+
+SCHED_FEAT(TTWU_FORCE_REMOTE, 0)

@@ -1,6 +1,6 @@
 /*
  * copyright Oracle 2007.  Licensed under GPLv2
- * To compile: gcc -Wall -o sembench sembench.c -lpthread
+ * To compile: gcc -Wall -o sembench sembench.c -lpthread -lm
  *
  * usage: sembench -t thread count -w wakenum -r runtime -o op
  * op can be: 0 (ipc sem) 1 (nanosleep) 2 (futexes)

@@ -28,8 +28,9 @@
 #include <sys/time.h>
 #include <sys/syscall.h>
 #include <errno.h>
+#include <math.h>
 
-#define VERSION "0.2"
+#define VERSION "0.3"
 
 /* futexes have been around since 2.5.something, but it still seems I
  * need to make my own syscall.  Sigh.

@@ -78,10 +79,55 @@
 
 int *semid_lookup = NULL;
 
+struct stats
+{
+	double n, mean, M2;
+};
+
+static void update_stats(struct stats *stats, long long val)
+{
+	double delta;
+
+	stats->n++;
+	delta = val - stats->mean;
+	stats->mean += delta / stats->n;
+	stats->M2 += delta*(val - stats->mean);
+}
+
+static double avg_stats(struct stats *stats)
+{
+	return stats->mean;
+}
+
+/*
+ * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
+ *
+ *       (\Sum n_i^2) - ((\Sum n_i)^2)/n
+ * s^2 = -------------------------------
+ *                  n - 1
+ *
+ * http://en.wikipedia.org/wiki/Stddev
+ *
+ * The std dev of the mean is related to the std dev by:
+ *
+ *             s
+ * s_mean = -------
+ *          sqrt(n)
+ *
+ */
+static double stddev_stats(struct stats *stats)
+{
+	double variance = stats->M2 / (stats->n - 1);
+	double variance_mean = variance / stats->n;
+
+	return sqrt(variance_mean);
+}
+
 pthread_mutex_t worklist_mutex = PTHREAD_MUTEX_INITIALIZER;
 static unsigned long total_burns = 0;
 static unsigned long min_burns = ~0UL;
 static unsigned long max_burns = 0;
+static struct stats burn_stats;
 static int thread_count = 0;
 struct lockinfo *worklist_head = NULL;
 struct lockinfo *worklist_tail = NULL;

@@ -385,6 +431,7 @@
 		min_burns = burn_count;
 	if (burn_count > max_burns)
 		max_burns = burn_count;
+	update_stats(&burn_stats, burn_count);
 	thread_count--;
 	pthread_mutex_unlock(&worklist_mutex);
 	return (void *)0;

@@ -508,8 +555,9 @@
 	printf("%d threads, waking %d at a time\n", num_threads, wake_num);
 	printf("using %s\n", ops->name);
 	printf("main thread burns: %d\n", burn_count);
-	printf("worker burn count total %lu min %lu max %lu avg %lu\n",
-	       total_burns, min_burns, max_burns, total_burns / num_threads);
+	printf("worker burn count total %lu min %lu max %lu avg %.3f +- %.3f%%\n",
+	       total_burns, min_burns, max_burns, avg_stats(&burn_stats),
+	       100 * stddev_stats(&burn_stats) / avg_stats(&burn_stats));
 	printf("run time %d seconds %lu worker burns per second\n",
 		(int)(now.tv_sec - start.tv_sec),
 		total_burns / (now.tv_sec - start.tv_sec));