Merge branches 'sched-core-for-linus' and 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (60 commits)
  sched: Fix and optimise calculation of the weight-inverse
  sched: Avoid going ahead if ->cpus_allowed is not changed
  sched, rt: Update rq clock when unthrottling of an otherwise idle CPU
  sched: Remove unused parameters from sched_fork() and wake_up_new_task()
  sched: Shorten the construction of the span cpu mask of sched domain
  sched: Wrap the 'cfs_rq->nr_spread_over' field with CONFIG_SCHED_DEBUG
  sched: Remove unused 'this_best_prio arg' from balance_tasks()
  sched: Remove noop in alloc_rt_sched_group()
  sched: Get rid of lock_depth
  sched: Remove obsolete comment from scheduler_tick()
  sched: Fix sched_domain iterations vs. RCU
  sched: Next buddy hint on sleep and preempt path
  sched: Make set_*_buddy() work on non-task entities
  sched: Remove need_migrate_task()
  sched: Move the second half of ttwu() to the remote cpu
  sched: Restructure ttwu() some more
  sched: Rename ttwu_post_activation() to ttwu_do_wakeup()
  sched: Remove rq argument from ttwu_stat()
  sched: Remove rq->lock from the first half of ttwu()
  sched: Drop rq->lock from sched_exec()
  ...

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Fix rt_rq runtime leakage bug

Documentation/trace/kprobetrace.txt

@@ -120,7 +120,6 @@ format:
         field:unsigned char common_flags;       offset:2;       size:1; signed:0;
         field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
         field:int common_pid;   offset:4;       size:4; signed:1;
-        field:int common_lock_depth;    offset:8;       size:4; signed:1;
 
         field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
         field:int __probe_nargs;        offset:16;      size:4; signed:1;

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:

arch/arm/kernel/smp.c

@@ -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:

arch/blackfin/mach-common/smp.c

@@ -177,6 +177,9 @@ 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);

arch/cris/arch-v32/kernel/smp.c

@@ -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);
 	}
 

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, 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);

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_irqaction = {
 };
 
 static struct irqaction xen_resched_irqaction = {
-	.handler =	xen_dummy_handler,
+	.handler =	xen_resched_handler,
 	.flags =	IRQF_DISABLED,
 	.name =		"resched"
 };

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();
 }
 
 /*==========================================================================*

arch/mips/cavium-octeon/smp.c

@@ -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)

arch/mips/kernel/smtc.c

@@ -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)

arch/mips/mti-malta/malta-int.c

@@ -308,6 +308,8 @@ static void ipi_call_dispatch(void)
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
+	scheduler_ipi();
+
 	return IRQ_HANDLED;
 }
 

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;
 	}
 }

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();

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();

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();

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;
 }
 

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:

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(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;
 }
 

arch/s390/kernel/smp.c

@@ -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();
 

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();

arch/sparc/include/asm/topology_64.h

@@ -65,6 +65,10 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #define smt_capable()				(sparc64_multi_core)
 #endif /* CONFIG_SMP */
 
-#define cpu_coregroup_mask(cpu)			(&cpu_core_map[cpu])
+extern cpumask_t cpu_core_map[NR_CPUS];
+static inline const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+        return &cpu_core_map[cpu];
+}
 
 #endif /* _ASM_SPARC64_TOPOLOGY_H */

arch/sparc/kernel/smp_32.c

@@ -129,7 +129,9 @@ 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)

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

arch/tile/kernel/smp.c

@@ -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;
 }

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':

arch/x86/kernel/smp.c

@@ -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
 	 */

arch/x86/xen/smp.c

@@ -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;
 }

include/linux/init_task.h

@@ -134,7 +134,6 @@ extern struct cred init_cred;
 	.stack		= &init_thread_info,				\
 	.usage		= ATOMIC_INIT(2),				\
 	.flags		= PF_KTHREAD,					\
-	.lock_depth	= -1,						\
 	.prio		= MAX_PRIO-20,					\
 	.static_prio	= MAX_PRIO-20,					\
 	.normal_prio	= MAX_PRIO-20,					\

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;

include/linux/sched.h

@@ -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;
@@ -731,10 +731,6 @@ struct sched_info {
 	/* timestamps */
 	unsigned long long last_arrival,/* when we last ran on a cpu */
 			   last_queued;	/* when we were last queued to run */
-#ifdef CONFIG_SCHEDSTATS
-	/* BKL stats */
-	unsigned int bkl_count;
-#endif
 };
 #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
 
@@ -868,6 +864,7 @@ static inline int sd_power_saving_flags(void)
 
 struct sched_group {
 	struct sched_group *next;	/* Must be a circular list */
+	atomic_t ref;
 
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
@@ -882,9 +879,6 @@ struct sched_group {
 	 * NOTE: this field is variable length. (Allocated dynamically
 	 * by attaching extra space to the end of the structure,
 	 * depending on how many CPUs the kernel has booted up with)
-	 *
-	 * It is also be embedded into static data structures at build
-	 * time. (See 'struct static_sched_group' in kernel/sched.c)
 	 */
 	unsigned long cpumask[0];
 };
@@ -894,17 +888,6 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
 	return to_cpumask(sg->cpumask);
 }
 
-enum sched_domain_level {
-	SD_LV_NONE = 0,
-	SD_LV_SIBLING,
-	SD_LV_MC,
-	SD_LV_BOOK,
-	SD_LV_CPU,
-	SD_LV_NODE,
-	SD_LV_ALLNODES,
-	SD_LV_MAX
-};
-
 struct sched_domain_attr {
 	int relax_domain_level;
 };
@@ -913,6 +896,8 @@ struct sched_domain_attr {
 	.relax_domain_level = -1,			\
 }
 
+extern int sched_domain_level_max;
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -930,7 +915,7 @@ struct sched_domain {
 	unsigned int forkexec_idx;
 	unsigned int smt_gain;
 	int flags;			/* See SD_* */
-	enum sched_domain_level level;
+	int level;
 
 	/* Runtime fields. */
 	unsigned long last_balance;	/* init to jiffies. units in jiffies */
@@ -973,6 +958,10 @@ struct sched_domain {
 #ifdef CONFIG_SCHED_DEBUG
 	char *name;
 #endif
+	union {
+		void *private;		/* used during construction */
+		struct rcu_head rcu;	/* used during destruction */
+	};
 
 	unsigned int span_weight;
 	/*
@@ -981,9 +970,6 @@ struct sched_domain {
 	 * NOTE: this field is variable length. (Allocated dynamically
 	 * by attaching extra space to the end of the structure,
 	 * depending on how many CPUs the kernel has booted up with)
-	 *
-	 * It is also be embedded into static data structures at build
-	 * time. (See 'struct static_sched_domain' in kernel/sched.c)
 	 */
 	unsigned long span[0];
 };
@@ -1048,8 +1034,12 @@ 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
 
@@ -1067,12 +1057,11 @@ 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);
-	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,
@@ -1197,13 +1186,11 @@ struct task_struct {
 	unsigned int flags;	/* per process flags, defined below */
 	unsigned int ptrace;
 
-	int lock_depth;		/* BKL lock depth */
-
 #ifdef CONFIG_SMP
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
-	int oncpu;
-#endif
+	struct task_struct *wake_entry;
+	int on_cpu;
 #endif
+	int on_rq;
 
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;
@@ -1274,6 +1261,7 @@ 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;
@@ -2063,14 +2051,13 @@ extern void xtime_update(unsigned long ticks);
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
-extern void wake_up_new_task(struct task_struct *tsk,
-				unsigned long clone_flags);
+extern void wake_up_new_task(struct task_struct *tsk);
 #ifdef CONFIG_SMP
  extern void kick_process(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(struct task_struct *p, int clone_flags);
+extern void sched_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
@@ -2195,8 +2182,10 @@ 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
+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)
 {

init/Kconfig

@@ -827,6 +827,11 @@ config SCHED_AUTOGROUP
 	  desktop applications.  Task group autogeneration is currently based
 	  upon task session.
 
+config SCHED_TTWU_QUEUE
+	bool
+	depends on !SPARC32
+	default y
+
 config MM_OWNER
 	bool
 

kernel/cpuset.c

@@ -1159,7 +1159,7 @@ int current_cpuset_is_being_rebound(void)
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
 #ifdef CONFIG_SMP
-	if (val < -1 || val >= SD_LV_MAX)
+	if (val < -1 || val >= sched_domain_level_max)
 		return -EINVAL;
 #endif
 

kernel/fork.c

@@ -1103,7 +1103,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	posix_cpu_timers_init(p);
 
-	p->lock_depth = -1;		/* -1 = no lock */
 	do_posix_clock_monotonic_gettime(&p->start_time);
 	p->real_start_time = p->start_time;
 	monotonic_to_bootbased(&p->real_start_time);
@@ -1153,7 +1152,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p, clone_flags);
+	sched_fork(p);
 
 	retval = perf_event_init_task(p);
 	if (retval)
@@ -1464,7 +1463,7 @@ long do_fork(unsigned long clone_flags,
 		 */
 		p->flags &= ~PF_STARTING;
 
-		wake_up_new_task(p, clone_flags);
+		wake_up_new_task(p);
 
 		tracehook_report_clone_complete(trace, regs,
 						clone_flags, nr, p);

kernel/mutex-debug.c

@@ -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);
 }

kernel/mutex-debug.h

@@ -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)

kernel/mutex.c

@@ -160,14 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 */
 
 	for (;;) {
-		struct thread_info *owner;
-
-		/*
-		 * If we own the BKL, then don't spin. The owner of
-		 * the mutex might be waiting on us to release the BKL.
-		 */
-		if (unlikely(current->lock_depth >= 0))
-			break;
+		struct task_struct *owner;
 
 		/*
 		 * If there's an owner, wait for it to either

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)

kernel/sched_debug.c

@@ -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);
@@ -296,9 +296,6 @@ static void print_cpu(struct seq_file *m, int cpu)
 	P(ttwu_count);
 	P(ttwu_local);
 
-	SEQ_printf(m, "  .%-30s: %d\n", "bkl_count",
-				rq->rq_sched_info.bkl_count);
-
 #undef P
 #undef P64
 #endif
@@ -441,7 +438,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	P(se.statistics.wait_count);
 	PN(se.statistics.iowait_sum);
 	P(se.statistics.iowait_count);
-	P(sched_info.bkl_count);
 	P(se.nr_migrations);
 	P(se.statistics.nr_migrations_cold);
 	P(se.statistics.nr_failed_migrations_affine);

kernel/sched_fair.c

@@ -358,6 +358,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 	}
 
 	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+#ifndef CONFIG_64BIT
+	smp_wmb();
+	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
+#endif
 }
 
 /*
@@ -1340,6 +1344,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	hrtick_update(rq);
 }
 
+static void set_next_buddy(struct sched_entity *se);
+
 /*
  * The dequeue_task method is called before nr_running is
  * decreased. We remove the task from the rbtree and
@@ -1349,14 +1355,22 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
+	int task_sleep = flags & DEQUEUE_SLEEP;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
 		/* Don't dequeue parent if it has other entities besides us */
-		if (cfs_rq->load.weight)
+		if (cfs_rq->load.weight) {
+			/*
+			 * Bias pick_next to pick a task from this cfs_rq, as
+			 * p is sleeping when it is within its sched_slice.
+			 */
+			if (task_sleep && parent_entity(se))
+				set_next_buddy(parent_entity(se));
 			break;
+		}
 		flags |= DEQUEUE_SLEEP;
 	}
 
@@ -1372,12 +1386,25 @@ 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);
+	u64 min_vruntime;
 
-	se->vruntime -= cfs_rq->min_vruntime;
+#ifndef CONFIG_64BIT
+	u64 min_vruntime_copy;
+
+	do {
+		min_vruntime_copy = cfs_rq->min_vruntime_copy;
+		smp_rmb();
+		min_vruntime = cfs_rq->min_vruntime;
+	} while (min_vruntime != min_vruntime_copy);
+#else
+	min_vruntime = cfs_rq->min_vruntime;
+#endif
+
+	se->vruntime -= min_vruntime;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1622,6 +1649,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	/*
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
+	rcu_read_lock();
 	for_each_domain(target, sd) {
 		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
 			break;
@@ -1641,6 +1669,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
 			break;
 	}
+	rcu_read_unlock();
 
 	return target;
 }
@@ -1657,7 +1686,7 @@ 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();
@@ -1673,6 +1702,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 		new_cpu = prev_cpu;
 	}
 
+	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
 		if (!(tmp->flags & SD_LOAD_BALANCE))
 			continue;
@@ -1723,9 +1753,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 
 	if (affine_sd) {
 		if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
-			return select_idle_sibling(p, cpu);
-		else
-			return select_idle_sibling(p, prev_cpu);
+			prev_cpu = cpu;
+
+		new_cpu = select_idle_sibling(p, prev_cpu);
+		goto unlock;
 	}
 
 	while (sd) {
@@ -1766,6 +1797,8 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 		}
 		/* while loop will break here if sd == NULL */
 	}
+unlock:
+	rcu_read_unlock();
 
 	return new_cpu;
 }
@@ -1789,10 +1822,7 @@ wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 	 * This is especially important for buddies when the leftmost
 	 * task is higher priority than the buddy.
 	 */
-	if (unlikely(se->load.weight != NICE_0_LOAD))
-		gran = calc_delta_fair(gran, se);
-
-	return gran;
+	return calc_delta_fair(gran, se);
 }
 
 /*
@@ -1826,26 +1856,26 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 
 static void set_last_buddy(struct sched_entity *se)
 {
-	if (likely(task_of(se)->policy != SCHED_IDLE)) {
-		for_each_sched_entity(se)
-			cfs_rq_of(se)->last = se;
-	}
+	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+		return;
+
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->last = se;
 }
 
 static void set_next_buddy(struct sched_entity *se)
 {
-	if (likely(task_of(se)->policy != SCHED_IDLE)) {
-		for_each_sched_entity(se)
-			cfs_rq_of(se)->next = se;
-	}
+	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+		return;
+
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->next = se;
 }
 
 static void set_skip_buddy(struct sched_entity *se)
 {
-	if (likely(task_of(se)->policy != SCHED_IDLE)) {
-		for_each_sched_entity(se)
-			cfs_rq_of(se)->skip = se;
-	}
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->skip = se;
 }
 
 /*
@@ -1857,12 +1887,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
+	int next_buddy_marked = 0;
 
 	if (unlikely(se == pse))
 		return;
 
-	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
+	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
 		set_next_buddy(pse);
+		next_buddy_marked = 1;
+	}
 
 	/*
 	 * We can come here with TIF_NEED_RESCHED already set from new task
@@ -1890,8 +1923,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	update_curr(cfs_rq);
 	find_matching_se(&se, &pse);
 	BUG_ON(!pse);
-	if (wakeup_preempt_entity(se, pse) == 1)
+	if (wakeup_preempt_entity(se, pse) == 1) {
+		/*
+		 * Bias pick_next to pick the sched entity that is
+		 * triggering this preemption.
+		 */
+		if (!next_buddy_marked)
+			set_next_buddy(pse);
 		goto preempt;
+	}
 
 	return;
 
@@ -2102,7 +2142,7 @@ static unsigned long
 balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	      unsigned long max_load_move, struct sched_domain *sd,
 	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
+	      struct cfs_rq *busiest_cfs_rq)
 {
 	int loops = 0, pulled = 0;
 	long rem_load_move = max_load_move;
@@ -2140,9 +2180,6 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		 */
 		if (rem_load_move <= 0)
 			break;
-
-		if (p->prio < *this_best_prio)
-			*this_best_prio = p->prio;
 	}
 out:
 	/*
@@ -2202,7 +2239,7 @@ static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
+		  int *all_pinned)
 {
 	long rem_load_move = max_load_move;
 	int busiest_cpu = cpu_of(busiest);
@@ -2227,7 +2264,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		rem_load = div_u64(rem_load, busiest_h_load + 1);
 
 		moved_load = balance_tasks(this_rq, this_cpu, busiest,
-				rem_load, sd, idle, all_pinned, this_best_prio,
+				rem_load, sd, idle, all_pinned,
 				busiest_cfs_rq);
 
 		if (!moved_load)
@@ -2253,11 +2290,11 @@ static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
+		  int *all_pinned)
 {
 	return balance_tasks(this_rq, this_cpu, busiest,
 			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &busiest->cfs);
+			&busiest->cfs);
 }
 #endif
 
@@ -2274,12 +2311,11 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		      int *all_pinned)
 {
 	unsigned long total_load_moved = 0, load_moved;
-	int this_best_prio = this_rq->curr->prio;
 
 	do {
 		load_moved = load_balance_fair(this_rq, this_cpu, busiest,
 				max_load_move - total_load_moved,
-				sd, idle, all_pinned, &this_best_prio);
+				sd, idle, all_pinned);
 
 		total_load_moved += load_moved;
 
@@ -2648,7 +2684,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 	/*
 	 * Only siblings can have significantly less than SCHED_LOAD_SCALE
 	 */
-	if (sd->level != SD_LV_SIBLING)
+	if (!(sd->flags & SD_SHARE_CPUPOWER))
 		return 0;
 
 	/*
@@ -3465,6 +3501,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	raw_spin_unlock(&this_rq->lock);
 
 	update_shares(this_cpu);
+	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 		int balance = 1;
@@ -3486,6 +3523,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 			break;
 		}
 	}
+	rcu_read_unlock();
 
 	raw_spin_lock(&this_rq->lock);
 
@@ -3534,6 +3572,7 @@ static int active_load_balance_cpu_stop(void *data)
 	double_lock_balance(busiest_rq, target_rq);
 
 	/* Search for an sd spanning us and the target CPU. */
+	rcu_read_lock();
 	for_each_domain(target_cpu, sd) {
 		if ((sd->flags & SD_LOAD_BALANCE) &&
 		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
@@ -3549,6 +3588,7 @@ static int active_load_balance_cpu_stop(void *data)
 		else
 			schedstat_inc(sd, alb_failed);
 	}
+	rcu_read_unlock();
 	double_unlock_balance(busiest_rq, target_rq);
 out_unlock:
 	busiest_rq->active_balance = 0;
@@ -3675,6 +3715,7 @@ static int find_new_ilb(int cpu)
 {
 	struct sched_domain *sd;
 	struct sched_group *ilb_group;
+	int ilb = nr_cpu_ids;
 
 	/*
 	 * Have idle load balancer selection from semi-idle packages only
@@ -3690,20 +3731,25 @@ static int find_new_ilb(int cpu)
 	if (cpumask_weight(nohz.idle_cpus_mask) < 2)
 		goto out_done;
 
+	rcu_read_lock();
 	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
 		ilb_group = sd->groups;
 
 		do {
-			if (is_semi_idle_group(ilb_group))
-				return cpumask_first(nohz.grp_idle_mask);
+			if (is_semi_idle_group(ilb_group)) {
+				ilb = cpumask_first(nohz.grp_idle_mask);
+				goto unlock;
+			}
 
 			ilb_group = ilb_group->next;
 
 		} while (ilb_group != sd->groups);
 	}
+unlock:
+	rcu_read_unlock();
 
 out_done:
-	return nr_cpu_ids;
+	return ilb;
 }
 #else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
 static inline int find_new_ilb(int call_cpu)
@@ -3848,6 +3894,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 
 	update_shares(cpu);
 
+	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
@@ -3893,6 +3940,7 @@ out:
 		if (!balance)
 			break;
 	}
+	rcu_read_unlock();
 
 	/*
 	 * next_balance will be updated only when there is a need.

kernel/sched_features.h

@@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1)
  * Decrement CPU power based on irq activity
  */
 SCHED_FEAT(NONIRQ_POWER, 1)
+
+/*
+ * Queue remote wakeups on the target CPU and process them
+ * using the scheduler IPI. Reduces rq->lock contention/bounces.
+ */
+SCHED_FEAT(TTWU_QUEUE, 1)

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 */
 }

kernel/sched_rt.c

@@ -183,6 +183,14 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 	return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
 }
 
+typedef struct task_group *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for (iter = list_entry_rcu(task_groups.next, typeof(*iter), list); \
+	     (&iter->list != &task_groups) && \
+	     (rt_rq = iter->rt_rq[cpu_of(rq)]); \
+	     iter = list_entry_rcu(iter->list.next, typeof(*iter), list))
+
 static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
 {
 	list_add_rcu(&rt_rq->leaf_rt_rq_list,
@@ -288,6 +296,11 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 	return ktime_to_ns(def_rt_bandwidth.rt_period);
 }
 
+typedef struct rt_rq *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
+
 static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
 {
 }
@@ -402,12 +415,13 @@ next:
 static void __disable_runtime(struct rq *rq)
 {
 	struct root_domain *rd = rq->rd;
+	rt_rq_iter_t iter;
 	struct rt_rq *rt_rq;
 
 	if (unlikely(!scheduler_running))
 		return;
 
-	for_each_leaf_rt_rq(rt_rq, rq) {
+	for_each_rt_rq(rt_rq, iter, rq) {
 		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 		s64 want;
 		int i;
@@ -487,6 +501,7 @@ static void disable_runtime(struct rq *rq)
 
 static void __enable_runtime(struct rq *rq)
 {
+	rt_rq_iter_t iter;
 	struct rt_rq *rt_rq;
 
 	if (unlikely(!scheduler_running))
@@ -495,7 +510,7 @@ static void __enable_runtime(struct rq *rq)
 	/*
 	 * Reset each runqueue's bandwidth settings
 	 */
-	for_each_leaf_rt_rq(rt_rq, rq) {
+	for_each_rt_rq(rt_rq, iter, rq) {
 		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 
 		raw_spin_lock(&rt_b->rt_runtime_lock);
@@ -562,6 +577,13 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
 				rt_rq->rt_throttled = 0;
 				enqueue = 1;
+
+				/*
+				 * Force a clock update if the CPU was idle,
+				 * lest wakeup -> unthrottle time accumulate.
+				 */
+				if (rt_rq->rt_nr_running && rq->curr == rq->idle)
+					rq->skip_clock_update = -1;
 			}
 			if (rt_rq->rt_time || rt_rq->rt_nr_running)
 				idle = 0;
@@ -977,13 +999,23 @@ 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 +1029,25 @@ 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)
@@ -1136,7 +1172,7 @@ 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 +1323,7 @@ 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 +1357,7 @@ 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 +1503,7 @@ 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 +1574,7 @@ 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 +1644,7 @@ 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 +1674,7 @@ 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 +1693,7 @@ 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) {
@@ -1796,10 +1832,11 @@ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 
 static void print_rt_stats(struct seq_file *m, int cpu)
 {
+	rt_rq_iter_t iter;
 	struct rt_rq *rt_rq;
 
 	rcu_read_lock();
-	for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
+	for_each_rt_rq(rt_rq, iter, cpu_rq(cpu))
 		print_rt_rq(m, cpu, rt_rq);
 	rcu_read_unlock();
 }

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 */
 }
@@ -26,7 +25,7 @@ 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;

kernel/trace/trace_kprobe.c

@@ -53,7 +53,6 @@ const char *reserved_field_names[] = {
 	"common_preempt_count",
 	"common_pid",
 	"common_tgid",
-	"common_lock_depth",
 	FIELD_STRING_IP,
 	FIELD_STRING_RETIP,
 	FIELD_STRING_FUNC,

tools/perf/Documentation/perf-script-perl.txt

@@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;

tools/perf/Documentation/perf-script-python.txt

@@ -463,7 +463,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;