sched: Reduce runqueue lock contention -v6

Index: linux-2.6/arch/alpha/kernel/smp.c
===================================================================
@@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs)
 
 		switch (which) {
 		case IPI_RESCHEDULE:
-			/* Reschedule callback.  Everything to be done
-			   is done by the interrupt return path.  */
+			scheduler_ipi();
 			break;
 
 		case IPI_CALL_FUNC:

Index: linux-2.6/arch/arm/kernel/smp.c
===================================================================
@@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do
 		break;
 
 	case IPI_RESCHEDULE:
-		/*
-		 * nothing more to do - eveything is
-		 * done on the interrupt return path
-		 */
+		scheduler_ipi();
 		break;
 
 	case IPI_CALL_FUNC:

Index: linux-2.6/arch/blackfin/mach-common/smp.c
===================================================================
@@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int 
 	while (msg_queue->count) {
 		msg = &msg_queue->ipi_message[msg_queue->head];
 		switch (msg->type) {
+		case BFIN_IPI_RESCHEDULE:
+			scheduler_ipi();
+			break;
 		case BFIN_IPI_CALL_FUNC:
 			spin_unlock_irqrestore(&msg_queue->lock, flags);
 			ipi_call_function(cpu, msg);

Index: linux-2.6/arch/cris/arch-v32/kernel/smp.c
===================================================================
@@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int ir
 
 	ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi);
 
+	if (ipi.vector & IPI_SCHEDULE) {
+		scheduler_ipi();
+	}
 	if (ipi.vector & IPI_CALL) {
-	         func(info);
+		func(info);
 	}
 	if (ipi.vector & IPI_FLUSH_TLB) {
-		     if (flush_mm == FLUSH_ALL)
-			 __flush_tlb_all();
-		     else if (flush_vma == FLUSH_ALL)
+		if (flush_mm == FLUSH_ALL)
+			__flush_tlb_all();
+		else if (flush_vma == FLUSH_ALL)
 			__flush_tlb_mm(flush_mm);
-		     else
+		else
 			__flush_tlb_page(flush_vma, flush_addr);
 	}
 

Index: linux-2.6/arch/ia64/kernel/irq_ia64.c
===================================================================
@@ -31,6 +31,7 @@
 #include <linux/irq.h>
 #include <linux/ratelimit.h>
 #include <linux/acpi.h>
+#include <linux/sched.h>
 
 #include <asm/delay.h>
 #include <asm/intrinsics.h>

@@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, str
 			smp_local_flush_tlb();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector))) {
+			scheduler_ipi();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else {
 			ia64_setreg(_IA64_REG_CR_TPR, vector);

Index: linux-2.6/arch/ia64/xen/irq_xen.c
===================================================================
@@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt;
 static int xen_slab_ready;
 
 #ifdef CONFIG_SMP
+#include <linux/sched.h>
+
 /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ,
  * it ends up to issue several memory accesses upon percpu data and
  * thus adds unnecessary traffic to other paths.

@@ -99,7 +101,13 @@ static int xen_slab_ready;
 static irqreturn_t
 xen_dummy_handler(int irq, void *dev_id)
 {
+	return IRQ_HANDLED;
+}
 
+static irqreturn_t
+xen_resched_handler(int irq, void *dev_id)
+{
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 

@@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqactio
 };
 
 static struct irqaction xen_resched_irqaction = {
-	.handler =	xen_dummy_handler,
+	.handler =	xen_resched_handler,
 	.flags =	IRQF_DISABLED,
 	.name =		"resched"
 };

Index: linux-2.6/arch/m32r/kernel/smp.c
===================================================================
@@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id)
  *
  * Description:  This routine executes on CPU which received
  *               'RESCHEDULE_IPI'.
- *               Rescheduling is processed at the exit of interrupt
- *               operation.
  *
  * Born on Date: 2002.02.05
  *

@@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id)
  *==========================================================================*/
 void smp_reschedule_interrupt(void)
 {
-	/* nothing to do */
+	scheduler_ipi();
 }
 
 /*==========================================================================*

Index: linux-2.6/arch/mips/kernel/smtc.c
===================================================================
@@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, str
 
 static void ipi_resched_interrupt(void)
 {
-	/* Return from interrupt should be enough to cause scheduler check */
+	scheduler_ipi();
 }
 
 static void ipi_call_interrupt(void)

Index: linux-2.6/arch/mips/sibyte/bcm1480/smp.c
===================================================================
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>

@@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	__raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();

Index: linux-2.6/arch/mips/sibyte/sb1250/smp.c
===================================================================
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>

@@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();

Index: linux-2.6/arch/mn10300/kernel/smp.c
===================================================================
@@ -494,14 +494,11 @@ void smp_send_stop(void)
  * @irq: The interrupt number.
  * @dev_id: The device ID.
  *
- * We need do nothing here, since the scheduling will be effected on our way
- * back through entry.S.
- *
  * Returns IRQ_HANDLED to indicate we handled the interrupt successfully.
  */
 static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id)
 {
-	/* do nothing */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 

Index: linux-2.6/arch/parisc/kernel/smp.c
===================================================================
@@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id) 
 				
 			case IPI_RESCHEDULE:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu);
-				/*
-				 * Reschedule callback.  Everything to be
-				 * done is done by the interrupt return path.
-				 */
+				scheduler_ipi();
 				break;
 
 			case IPI_CALL_FUNC:

Index: linux-2.6/arch/powerpc/kernel/smp.c
===================================================================
@@ -116,7 +116,7 @@ void smp_message_recv(int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
-		/* we notice need_resched on exit */
+		scheduler_ipi();
 		break;
 	case PPC_MSG_CALL_FUNC_SINGLE:
 		generic_smp_call_function_single_interrupt();

@@ -146,7 +146,7 @@ static irqreturn_t call_function_action(
 
 static irqreturn_t reschedule_action(int irq, void *data)
 {
-	/* we just need the return path side effect of checking need_resched */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 

Index: linux-2.6/arch/s390/kernel/smp.c
===================================================================
@@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsign
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++;
 	/*
 	 * handle bit signal external calls
-	 *
-	 * For the ec_schedule signal we have to do nothing. All the work
-	 * is done automatically when we return from the interrupt.
 	 */
 	bits = xchg(&S390_lowcore.ext_call_fast, 0);
 
+	if (test_bit(ec_schedule, &bits))
+		scheduler_ipi();
+
 	if (test_bit(ec_call_function, &bits))
 		generic_smp_call_function_interrupt();
 

Index: linux-2.6/arch/sh/kernel/smp.c
===================================================================
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 #include <asm/processor.h>
 #include <asm/system.h>

@@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case SMP_MSG_RESCHEDULE:
+		scheduler_ipi();
 		break;
 	case SMP_MSG_FUNCTION_SINGLE:
 		generic_smp_call_function_single_interrupt();

Index: linux-2.6/arch/sparc/kernel/smp_32.c
===================================================================
@@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_
 
 void smp_send_reschedule(int cpu)
 {
-	/* See sparc64 */
+	/*
+	 * XXX missing reschedule IPI, see scheduler_ipi()
+	 */
 }
 
 void smp_send_stop(void)

Index: linux-2.6/arch/sparc/kernel/smp_64.c
===================================================================
@@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu)
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	scheduler_ipi();
 }
 
 /* This is a nop because we capture all other cpus

Index: linux-2.6/arch/tile/kernel/smp.c
===================================================================
@@ -189,12 +189,8 @@ void flush_icache_range(unsigned long st
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	/*
-	 * Nothing to do here; when we return from interrupt, the
-	 * rescheduling will occur there. But do bump the interrupt
-	 * profiler count in the meantime.
-	 */
 	__get_cpu_var(irq_stat).irq_resched_count++;
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }

Index: linux-2.6/arch/um/kernel/smp.c
===================================================================
@@ -173,7 +173,7 @@ void IPI_handler(int cpu)
 			break;
 
 		case 'R':
-			set_tsk_need_resched(current);
+			scheduler_ipi();
 			break;
 
 		case 'S':

Index: linux-2.6/arch/x86/kernel/smp.c
===================================================================
@@ -194,14 +194,13 @@ static void native_stop_other_cpus(int w
 }
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */

Index: linux-2.6/arch/x86/xen/smp.c
===================================================================
@@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_int
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -2189,6 +2189,7 @@ extern void set_task_comm(struct task_st
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+static inline void scheduler_ipi(void) { }
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
 static inline unsigned long wait_task_inactive(struct task_struct *p,

Index: linux-2.6/arch/mips/cavium-octeon/smp.c
===================================================================
@@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	/* Check if we've been told to flush the icache */
 	if (action & SMP_ICACHE_FLUSH)

Index: linux-2.6/arch/mips/mti-malta/malta-int.c
===================================================================
@@ -309,6 +309,8 @@ static void ipi_call_dispatch(void)
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
+	scheduler_ipi();
+
 	return IRQ_HANDLED;
 }
 

Index: linux-2.6/arch/mips/pmc-sierra/yosemite/smp.c
===================================================================
@@ -55,6 +55,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 
 	case 1:

@@ -63,6 +65,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 	}
 }

Index: linux-2.6/arch/mips/sgi-ip27/ip27-irq.c
===================================================================
@@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void)
 #ifdef CONFIG_SMP
 	if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
 		smp_call_function_interrupt();

index 42aa078..5a621c6 100644
@@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs)
 
 		switch (which) {
 		case IPI_RESCHEDULE:
-			/* Reschedule callback.  Everything to be done
-			   is done by the interrupt return path.  */
+			scheduler_ipi();
 			break;
 
 		case IPI_CALL_FUNC:

index 8fe05ad..7a561eb 100644
@@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_RESCHEDULE:
-		/*
-		 * nothing more to do - eveything is
-		 * done on the interrupt return path
-		 */
+		scheduler_ipi();
 		break;
 
 	case IPI_CALL_FUNC:

index 6e17a26..326bb86 100644
@@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 	while (msg_queue->count) {
 		msg = &msg_queue->ipi_message[msg_queue->head];
 		switch (msg->type) {
+		case BFIN_IPI_RESCHEDULE:
+			scheduler_ipi();
+			break;
 		case BFIN_IPI_CALL_FUNC:
 			spin_unlock_irqrestore(&msg_queue->lock, flags);
 			ipi_call_function(cpu, msg);

index 4c9e3e1..66cc756 100644
@@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id)
 
 	ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi);
 
+	if (ipi.vector & IPI_SCHEDULE) {
+		scheduler_ipi();
+	}
 	if (ipi.vector & IPI_CALL) {
-	         func(info);
+		func(info);
 	}
 	if (ipi.vector & IPI_FLUSH_TLB) {
-		     if (flush_mm == FLUSH_ALL)
-			 __flush_tlb_all();
-		     else if (flush_vma == FLUSH_ALL)
+		if (flush_mm == FLUSH_ALL)
+			__flush_tlb_all();
+		else if (flush_vma == FLUSH_ALL)
 			__flush_tlb_mm(flush_mm);
-		     else
+		else
 			__flush_tlb_page(flush_vma, flush_addr);
 	}
 

index 5b70474..782c3a35 100644
@@ -31,6 +31,7 @@
 #include <linux/irq.h>
 #include <linux/ratelimit.h>
 #include <linux/acpi.h>
+#include <linux/sched.h>
 
 #include <asm/delay.h>
 #include <asm/intrinsics.h>

@@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 			smp_local_flush_tlb();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector))) {
+			scheduler_ipi();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else {
 			ia64_setreg(_IA64_REG_CR_TPR, vector);

index 108bb85..b279e14 100644
@@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt;
 static int xen_slab_ready;
 
 #ifdef CONFIG_SMP
+#include <linux/sched.h>
+
 /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ,
  * it ends up to issue several memory accesses upon percpu data and
  * thus adds unnecessary traffic to other paths.

@@ -99,7 +101,13 @@ static int xen_slab_ready;
 static irqreturn_t
 xen_dummy_handler(int irq, void *dev_id)
 {
+	return IRQ_HANDLED;
+}
 
+static irqreturn_t
+xen_resched_handler(int irq, void *dev_id)
+{
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 

@@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = {
 };
 
 static struct irqaction xen_resched_irqaction = {
-	.handler =	xen_dummy_handler,
+	.handler =	xen_resched_handler,
 	.flags =	IRQF_DISABLED,
 	.name =		"resched"
 };

index 31cef20..fc10b39 100644
@@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id)
  *
  * Description:  This routine executes on CPU which received
  *               'RESCHEDULE_IPI'.
- *               Rescheduling is processed at the exit of interrupt
- *               operation.
  *
  * Born on Date: 2002.02.05
  *

@@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id)
  *==========================================================================*/
 void smp_reschedule_interrupt(void)
 {
-	/* nothing to do */
+	scheduler_ipi();
 }
 
 /*==========================================================================*

index ba78b21..76923ee 100644
@@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id)
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	/* Check if we've been told to flush the icache */
 	if (action & SMP_ICACHE_FLUSH)

index 5a88cc4..cedac46 100644
@@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi)
 
 static void ipi_resched_interrupt(void)
 {
-	/* Return from interrupt should be enough to cause scheduler check */
+	scheduler_ipi();
 }
 
 static void ipi_call_interrupt(void)

index 9027061..7d93e6f 100644
@@ -309,6 +309,8 @@ static void ipi_call_dispatch(void)
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
+	scheduler_ipi();
+
 	return IRQ_HANDLED;
 }
 

index efc9e88..2608752 100644
@@ -55,6 +55,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 
 	case 1:

@@ -63,6 +65,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 	}
 }

index 0a04603..b18b04e 100644
@@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void)
 #ifdef CONFIG_SMP
 	if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
 		smp_call_function_interrupt();

index 47b347c..d667875 100644
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>

@@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	__raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();

index c00a5cb..38e7f6b 100644
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>

@@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();

index 226c826..83fb279 100644
@@ -494,14 +494,11 @@ void smp_send_stop(void)
  * @irq: The interrupt number.
  * @dev_id: The device ID.
  *
- * We need do nothing here, since the scheduling will be effected on our way
- * back through entry.S.
- *
  * Returns IRQ_HANDLED to indicate we handled the interrupt successfully.
  */
 static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id)
 {
-	/* do nothing */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 

index 69d63d3..828305f 100644
@@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id)
 				
 			case IPI_RESCHEDULE:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu);
-				/*
-				 * Reschedule callback.  Everything to be
-				 * done is done by the interrupt return path.
-				 */
+				scheduler_ipi();
 				break;
 
 			case IPI_CALL_FUNC:

index cbdbb14..9f9c204 100644
@@ -116,7 +116,7 @@ void smp_message_recv(int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
-		/* we notice need_resched on exit */
+		scheduler_ipi();
 		break;
 	case PPC_MSG_CALL_FUNC_SINGLE:
 		generic_smp_call_function_single_interrupt();

@@ -146,7 +146,7 @@ static irqreturn_t call_function_action(int irq, void *data)
 
 static irqreturn_t reschedule_action(int irq, void *data)
 {
-	/* we just need the return path side effect of checking need_resched */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 

index 63a97db..63c7d9f 100644
@@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++;
 	/*
 	 * handle bit signal external calls
-	 *
-	 * For the ec_schedule signal we have to do nothing. All the work
-	 * is done automatically when we return from the interrupt.
 	 */
 	bits = xchg(&S390_lowcore.ext_call_fast, 0);
 
+	if (test_bit(ec_schedule, &bits))
+		scheduler_ipi();
+
 	if (test_bit(ec_call_function, &bits))
 		generic_smp_call_function_interrupt();
 

index 509b36b..6207561 100644
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 #include <asm/processor.h>
 #include <asm/system.h>

@@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case SMP_MSG_RESCHEDULE:
+		scheduler_ipi();
 		break;
 	case SMP_MSG_FUNCTION_SINGLE:
 		generic_smp_call_function_single_interrupt();

index 91c10fb..f95690c 100644
@@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 };
 
 void smp_send_reschedule(int cpu)
 {
-	/* See sparc64 */
+	/*
+	 * XXX missing reschedule IPI, see scheduler_ipi()
+	 */
 }
 
 void smp_send_stop(void)

index 3e94a8c..9478da7 100644
@@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu)
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	scheduler_ipi();
 }
 
 /* This is a nop because we capture all other cpus

index a429310..c52224d 100644
@@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end)
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	/*
-	 * Nothing to do here; when we return from interrupt, the
-	 * rescheduling will occur there. But do bump the interrupt
-	 * profiler count in the meantime.
-	 */
 	__get_cpu_var(irq_stat).irq_resched_count++;
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }

index 106bf27..eefb107 100644
@@ -173,7 +173,7 @@ void IPI_handler(int cpu)
 			break;
 
 		case 'R':
-			set_tsk_need_resched(current);
+			scheduler_ipi();
 			break;
 
 		case 'S':

index 513deac..013e7eb 100644
@@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait)
 }
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */

index 3061244..762b46a 100644
@@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }

index 4ec2c02..758e27a 100644
@@ -2189,8 +2189,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+static inline void scheduler_ipi(void) { }
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void scheduler_ipi(void) { }
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {

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 758e27a..3435837 100644
@@ -1200,9 +1200,7 @@ 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;

97 lines not on this page · raw message

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 94b48bd..c75471d 100644
@@ -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 3435837..1738504 100644
@@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout);
 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 ec815a9..73da83a 100644
@@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock)
 		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 57d527a..0799fd3 100644
@@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
 
 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 c4195fa..fe4706c 100644
@@ -160,7 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 */
 
 	for (;;) {
-		struct thread_info *owner;
+		struct task_struct *owner;
 
 		/*
 		 * If we own the BKL, then don't spin. The owner of

index 67578ca..4115fbf 100644
@@ -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/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
===================================================================
@@ -2447,7 +2447,7 @@ 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));
 }
 

index 81ab58e..3919aa4 100644
@@ -2427,10 +2427,10 @@ static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
 		wq_worker_waking_up(p, cpu_of(rq));
 }
 
-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;

@@ -2546,9 +2546,9 @@ out_activate:
 #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();

@@ -2567,7 +2567,6 @@ out:
 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);

@@ -2582,9 +2581,8 @@ static void try_to_wake_up_local(struct task_struct *p)
 			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);
 }
 
 /**

@@ -2747,7 +2745,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 
 	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
===================================================================
@@ -2408,21 +2408,38 @@ 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)
+
+#ifdef CONFIG_SMP
+	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_SMP */
+#endif /* CONFIG_SCHEDSTATS */
 }
 
 static void

@@ -2482,12 +2499,12 @@ 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;

@@ -2528,27 +2545,12 @@ 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);

@@ -2576,14 +2578,11 @@ 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 3919aa4..4481638 100644
@@ -2406,20 +2406,43 @@ static void update_avg(u64 *avg, u64 sample)
 }
 #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
+#ifdef CONFIG_SMP
+	int this_cpu = smp_processor_id();
+
+	if (cpu == this_cpu) {
+		schedstat_inc(rq, ttwu_local);
+		schedstat_inc(p, se.statistics.nr_wakeups_local);
+	} else {
+		struct sched_domain *sd;
+
+		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_SMP */
+
+	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)
-		schedstat_inc(p, se.statistics.nr_wakeups_local);
-	else
-		schedstat_inc(p, se.statistics.nr_wakeups_remote);
 
+#endif /* CONFIG_SCHEDSTATS */
+}
+
+static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
+{
 	activate_task(rq, p, en_flags);
 
 	/* if a worker is waking up, notify workqueue */

@@ -2481,12 +2504,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	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;

@@ -2527,27 +2550,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	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);
+	ttwu_activate(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);

@@ -2575,14 +2583,11 @@ static void try_to_wake_up_local(struct task_struct *p)
 	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)
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+
 	ttwu_post_activation(p, rq, 0);
+	ttwu_stat(rq, p, smp_processor_id(), 0);
 }
 
 /**

Index: linux-2.6/include/linux/sched.h
===================================================================
@@ -1208,6 +1208,7 @@ 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
===================================================================
@@ -1788,7 +1788,6 @@ 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)

@@ -1796,7 +1795,6 @@ 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;
 }
 
 /*

@@ -2131,7 +2129,7 @@ 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;
 }
 

@@ -2206,7 +2204,7 @@ 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);
 }
 
 /*

@@ -2266,7 +2264,7 @@ 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 */

@@ -2502,7 +2500,7 @@ 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;

@@ -2549,6 +2547,7 @@ static int try_to_wake_up(struct task_st
 out_activate:
 #endif /* CONFIG_SMP */
 	activate_task(rq, p, en_flags);
+	p->on_rq = 1;
 out_running:
 	ttwu_post_activation(p, rq, wake_flags);
 	ttwu_stat(rq, p, cpu, wake_flags);

@@ -2579,7 +2578,7 @@ 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);

@@ -2616,19 +2615,21 @@ 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;
 	p->se.vruntime			= 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);

@@ -2746,6 +2747,7 @@ void wake_up_new_task(struct task_struct
 
 	rq = task_rq_lock(p, &flags);
 	activate_task(rq, p, 0);
+	p->on_rq = 1;
 	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP

@@ -4047,7 +4049,7 @@ 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);
 }

@@ -4126,6 +4128,7 @@ 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;
 	}

@@ -4687,7 +4690,7 @@ 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);

@@ -4735,7 +4738,7 @@ 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);
 

@@ -4869,8 +4872,6 @@ 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);

@@ -5022,7 +5023,7 @@ 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);

@@ -5939,7 +5940,7 @@ 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);

@@ -7930,7 +7931,7 @@ static void normalize_task(struct rq *rq
 	int old_prio = p->prio;
 	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);

@@ -8276,7 +8277,7 @@ 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
===================================================================
@@ -152,7 +152,7 @@ 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
===================================================================
@@ -1136,7 +1136,7 @@ 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 (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 

@@ -1287,7 +1287,7 @@ 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;

@@ -1321,7 +1321,7 @@ 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;

@@ -1467,7 +1467,7 @@ 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

@@ -1538,7 +1538,7 @@ 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)) {

@@ -1608,7 +1608,7 @@ static void switched_from_rt(struct rq *
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (p->se.on_rq && !rq->rt.rt_nr_running)
+	if (p->on_rq && !rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
 

@@ -1638,7 +1638,7 @@ static void switched_to_rt(struct rq *rq
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (p->se.on_rq && rq->curr != p) {
+	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->rt.overloaded && push_rt_task(rq) &&
 		    /* Don't resched if we changed runqueues */

@@ -1657,7 +1657,7 @@ static void switched_to_rt(struct rq *rq
 static void
 prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (!p->se.on_rq)
+	if (!p->on_rq)
 		return;
 
 	if (rq->curr == 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 1738504..b33a700 100644
@@ -1202,6 +1202,7 @@ struct task_struct {
 #ifdef CONFIG_SMP
 	int on_cpu;
 #endif
+	int on_rq;
 
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;

index 4481638..dece28e 100644
@@ -1785,7 +1785,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	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)

@@ -1793,7 +1792,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	update_rq_clock(rq);
 	sched_info_dequeued(p);
 	p->sched_class->dequeue_task(rq, p, flags);
-	p->se.on_rq = 0;
 }
 
 /*

@@ -2128,7 +2126,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * 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;
 }
 

@@ -2203,7 +2201,7 @@ static bool migrate_task(struct task_struct *p, struct rq *rq)
 	 * 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);
 }
 
 /*

@@ -2263,7 +2261,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		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 */

@@ -2444,6 +2442,7 @@ ttwu_stat(struct rq *rq, struct task_struct *p, int cpu, int wake_flags)
 static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
 {
 	activate_task(rq, p, en_flags);
+	p->on_rq = 1;
 
 	/* if a worker is waking up, notify workqueue */
 	if (p->flags & PF_WQ_WORKER)

@@ -2506,7 +2505,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 	cpu = task_cpu(p);
 
-	if (p->se.on_rq)
+	if (p->on_rq)
 		goto out_running;
 
 	orig_cpu = cpu;

@@ -2583,7 +2582,7 @@ static void try_to_wake_up_local(struct task_struct *p)
 	if (!(p->state & TASK_NORMAL))
 		return;
 
-	if (!p->se.on_rq)
+	if (!p->on_rq)
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_post_activation(p, rq, 0);

@@ -2620,19 +2619,21 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  */
 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;
 	p->se.vruntime			= 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);

@@ -2750,6 +2751,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 
 	rq = task_rq_lock(p, &flags);
 	activate_task(rq, p, 0);
+	p->on_rq = 1;
 	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP

@@ -4051,7 +4053,7 @@ static inline void schedule_debug(struct task_struct *prev)
 
 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);
 }

@@ -4126,7 +4128,9 @@ need_resched:
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
+
 			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+			prev->on_rq = 0;
 
 			/*
 			 * If we are going to sleep and we have plugged IO queued, make

@@ -4695,7 +4699,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	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);

@@ -4743,7 +4747,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		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);
 

@@ -4877,8 +4881,6 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 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);

@@ -5044,7 +5046,7 @@ recheck:
 		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);

@@ -5965,7 +5967,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	 * 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);

@@ -8339,7 +8341,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 	int old_prio = p->prio;
 	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);

@@ -8682,7 +8684,7 @@ void sched_move_task(struct task_struct *tsk)
 	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 7bacd83..3669bec6 100644
@@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	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 e7cebdc..9ca4f5f 100644
@@ -1136,7 +1136,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 	 * 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 (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 

@@ -1287,7 +1287,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 				     !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;

@@ -1321,7 +1321,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
 	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;

@@ -1467,7 +1467,7 @@ static int pull_rt_task(struct rq *this_rq)
 		 */
 		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

@@ -1538,7 +1538,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 	 * 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)) {

@@ -1608,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (p->se.on_rq && !rq->rt.rt_nr_running)
+	if (p->on_rq && !rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
 

@@ -1638,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (p->se.on_rq && rq->curr != p) {
+	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->rt.overloaded && push_rt_task(rq) &&
 		    /* Don't resched if we changed runqueues */

@@ -1657,7 +1657,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 static void
 prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (!p->se.on_rq)
+	if (!p->on_rq)
 		return;
 
 	if (rq->curr == p) {

index 1ba2bd4..f607de4 100644
@@ -26,7 +26,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
 	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 dece28e..d398f2f 100644
@@ -2340,7 +2340,7 @@ EXPORT_SYMBOL_GPL(kick_process);
 
 #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)
 {

@@ -2373,7 +2373,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * 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)

@@ -2499,7 +2499,8 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	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;
 

@@ -2557,7 +2558,8 @@ out_running:
 	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;

@@ -4694,6 +4696,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	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);

@@ -5317,7 +5321,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
 	struct task_struct *p;
 	unsigned long flags;
-	struct rq *rq;
 	int retval;
 
 	get_online_cpus();

@@ -5332,9 +5335,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 	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();

@@ -5882,18 +5885,8 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	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;

@@ -5921,13 +5914,15 @@ again:
 	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 +2138,15 @@ 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);
+	bool running = p->on_rq || p->on_cpu;
+	smp_rmb(); /* finish_lock_switch() */
+	return running;
 }
 
 /*

@@ -2337,9 +2339,9 @@ 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 +2486,7 @@ 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);

@@ -2694,7 +2696,7 @@ void wake_up_new_task(struct task_struct
 	 * 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);
+	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
 	set_task_cpu(p, cpu);
 
 	p->state = TASK_RUNNING;

@@ -3420,7 +3422,7 @@ void sched_exec(void)
 	int dest_cpu;
 
 	rq = task_rq_lock(p, &flags);
-	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 

@@ -3428,7 +3430,7 @@ void sched_exec(void)
 	 * 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)) {
+	    likely(cpu_active(dest_cpu)) && need_migrate_task(p)) {
 		struct migration_arg arg = { p, dest_cpu };
 
 		task_rq_unlock(rq, &flags);

@@ -5681,7 +5683,7 @@ 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
===================================================================
@@ -973,13 +973,23 @@ 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)
 {
+	struct task_struct *curr;
+	struct rq *rq;
+	int cpu;
+
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();
 
+	cpu = task_cpu(p);
+	rq = cpu_rq(cpu);
+
+	rcu_read_lock();
+	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
 	/*
-	 * If the current task is an RT task, then
+	 * If the current task on @p's runqueue is an RT task, then
 	 * try to see if we can wake this RT task up on another
 	 * runqueue. Otherwise simply start this RT task
 	 * on its current runqueue.

@@ -993,21 +1003,25 @@ select_task_rq_rt(struct rq *rq, struct 
 	 * lock?
 	 *
 	 * For equal prio tasks, we just let the scheduler sort it out.
+	 *
+	 * Otherwise, just let it ride on the affined RQ and the
+	 * post-schedule router will push the preempted task away
+	 *
+	 * This test is optimistic, if we get it wrong the load-balancer
+	 * will have to sort it out.
 	 */
-	if (unlikely(rt_task(rq->curr)) &&
-	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio) &&
+	if (curr && unlikely(rt_task(curr)) &&
+	    (curr->rt.nr_cpus_allowed < 2 ||
+	     curr->prio < p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
-		int cpu = find_lowest_rq(p);
+		int target = find_lowest_rq(p);
 
-		return (cpu == -1) ? task_cpu(p) : cpu;
+		if (target != -1)
+			cpu = target;
 	}
+	rcu_read_unlock();
 
-	/*
-	 * Otherwise, just let it ride on the affined RQ and the
-	 * post-schedule router will push the preempted task away
-	 */
-	return task_cpu(p);
+	return cpu;
 }
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)

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 b33a700..ff4e2f9 100644
@@ -1067,8 +1067,7 @@ 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 d398f2f..d4b815d 100644
@@ -2195,13 +2195,15 @@ 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);
+	bool running = p->on_rq || p->on_cpu;
+	smp_rmb(); /* finish_lock_switch() */
+	return running;
 }
 
 /*

@@ -2376,9 +2378,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
  * 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

@@ -2533,7 +2535,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 		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);

@@ -2744,7 +2746,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 	 * 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);
+	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
 	set_task_cpu(p, cpu);
 
 	p->state = TASK_RUNNING;

@@ -3474,7 +3476,7 @@ void sched_exec(void)
 	int dest_cpu;
 
 	rq = task_rq_lock(p, &flags);
-	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 

@@ -3482,7 +3484,7 @@ void sched_exec(void)
 	 * 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)) {
+	    likely(cpu_active(dest_cpu)) && need_migrate_task(p)) {
 		struct migration_arg arg = { p, dest_cpu };
 
 		task_rq_unlock(rq, &flags);

@@ -5911,7 +5913,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		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 4ee50f0..96b2c95 100644
@@ -1657,7 +1657,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
  * 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 a776a63..0a51882 100644
@@ -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 9ca4f5f..19ecb31 100644
@@ -977,13 +977,23 @@ 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)
 {
+	struct task_struct *curr;
+	struct rq *rq;
+	int cpu;
+
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();
 
+	cpu = task_cpu(p);
+	rq = cpu_rq(cpu);
+
+	rcu_read_lock();
+	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
 	/*
-	 * If the current task is an RT task, then
+	 * If the current task on @p's runqueue is an RT task, then
 	 * try to see if we can wake this RT task up on another
 	 * runqueue. Otherwise simply start this RT task
 	 * on its current runqueue.

@@ -997,21 +1007,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 	 * lock?
 	 *
 	 * For equal prio tasks, we just let the scheduler sort it out.
+	 *
+	 * Otherwise, just let it ride on the affined RQ and the
+	 * post-schedule router will push the preempted task away
+	 *
+	 * This test is optimistic, if we get it wrong the load-balancer
+	 * will have to sort it out.
 	 */
-	if (unlikely(rt_task(rq->curr)) &&
-	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio) &&
+	if (curr && unlikely(rt_task(curr)) &&
+	    (curr->rt.nr_cpus_allowed < 2 ||
+	     curr->prio < p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
-		int cpu = find_lowest_rq(p);
+		int target = find_lowest_rq(p);
 
-		return (cpu == -1) ? task_cpu(p) : cpu;
+		if (target != -1)
+			cpu = target;
 	}
+	rcu_read_unlock();
 
-	/*
-	 * Otherwise, just let it ride on the affined RQ and the
-	 * post-schedule router will push the preempted task away
-	 */
-	return task_cpu(p);
+	return cpu;
 }
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)

index f607de4..6f43763 100644
@@ -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/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 ff4e2f9..7f5732f 100644
@@ -1048,8 +1048,12 @@ 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
 

@@ -1071,7 +1075,7 @@ 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 d4b815d..46f42ca 100644
@@ -2531,7 +2531,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	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 96b2c95..ad4c414f 100644
@@ -1372,11 +1372,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 #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
===================================================================
@@ -313,6 +313,9 @@ struct cfs_rq {
 
 	u64 exec_clock;
 	u64 min_vruntime;
+#ifndef CONFIG_64BIT
+	u64 min_vruntime_copy;
+#endif
 
 	struct rb_root tasks_timeline;
 	struct rb_node *rb_leftmost;