Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched: (96 commits)
  sched: keep total / count stats in addition to the max for
  sched, futex: detach sched.h and futex.h
  sched: fix: don't take a mutex from interrupt context
  sched: print backtrace of running tasks too
  printk: use ktime_get()
  softlockup: fix signedness
  sched: latencytop support
  sched: fix goto retry in pick_next_task_rt()
  timers: don't #error on higher HZ values
  sched: monitor clock underflows in /proc/sched_debug
  sched: fix rq->clock warps on frequency changes
  sched: fix, always create kernel threads with normal priority
  debug: clean up kernel/profile.c
  sched: remove the !PREEMPT_BKL code
  sched: make PREEMPT_BKL the default
  debug: track and print last unloaded module in the oops trace
  debug: show being-loaded/being-unloaded indicator for modules
  sched: rt-watchdog: fix .rlim_max = RLIM_INFINITY
  sched: rt-group: reduce rescheduling
  hrtimer: unlock hrtimer_wakeup
  ...

19 files changed, 581 insertions, 160 deletions

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 92f2029a34f..0be8d65bc3c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -71,18 +71,27 @@ static inline void unregister_cpu_notifier(struct notifier_block *nb)
 
 int cpu_up(unsigned int cpu);
 
+extern void cpu_hotplug_init(void);
+
 #else
 
 static inline int register_cpu_notifier(struct notifier_block *nb)
 {
 	return 0;
 }
+
 static inline void unregister_cpu_notifier(struct notifier_block *nb)
 {
 }
 
+static inline void cpu_hotplug_init(void)
+{
+}
+
 #endif /* CONFIG_SMP */
 extern struct sysdev_class cpu_sysdev_class;
+extern void cpu_maps_update_begin(void);
+extern void cpu_maps_update_done(void);
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* Stop CPUs going up and down. */
@@ -97,8 +106,8 @@ static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
 	mutex_unlock(cpu_hp_mutex);
 }
 
-extern void lock_cpu_hotplug(void);
-extern void unlock_cpu_hotplug(void);
+extern void get_online_cpus(void);
+extern void put_online_cpus(void);
 #define hotcpu_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
 		{ .notifier_call = fn, .priority = pri };	\
@@ -115,8 +124,8 @@ static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
 static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
 { }
 
-#define lock_cpu_hotplug()	do { } while (0)
-#define unlock_cpu_hotplug()	do { } while (0)
+#define get_online_cpus()	do { } while (0)
+#define put_online_cpus()	do { } while (0)
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 /* These aren't inline functions due to a GCC bug. */
 #define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 1678a5de701..f4a5871767f 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -47,6 +47,7 @@ struct task_struct;
 
 #ifdef CONFIG_LOCKDEP
 extern void debug_show_all_locks(void);
+extern void __debug_show_held_locks(struct task_struct *task);
 extern void debug_show_held_locks(struct task_struct *task);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
 extern void debug_check_no_locks_held(struct task_struct *task);
@@ -55,6 +56,10 @@ static inline void debug_show_all_locks(void)
 {
 }
 
+static inline void __debug_show_held_locks(struct task_struct *task)
+{
+}
+
 static inline void debug_show_held_locks(struct task_struct *task)
 {
 }
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 92d420fe03f..1a15f8e237a 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -1,8 +1,12 @@
 #ifndef _LINUX_FUTEX_H
 #define _LINUX_FUTEX_H
 
-#include <linux/sched.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
 
+struct inode;
+struct mm_struct;
+struct task_struct;
 union ktime;
 
 /* Second argument to futex syscall */
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 8d302298a16..2961ec78804 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -72,11 +72,7 @@
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
 
-#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
-# define in_atomic()	((preempt_count() & ~PREEMPT_ACTIVE) != kernel_locked())
-#else
-# define in_atomic()	((preempt_count() & ~PREEMPT_ACTIVE) != 0)
-#endif
+#define in_atomic()		((preempt_count() & ~PREEMPT_ACTIVE) != 0)
 
 #ifdef CONFIG_PREEMPT
 # define PREEMPT_CHECK_OFFSET 1
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 7a9398e1970..49067f14fac 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -115,10 +115,8 @@ struct hrtimer {
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
-#ifdef CONFIG_HIGH_RES_TIMERS
 	enum hrtimer_cb_mode		cb_mode;
 	struct list_head		cb_entry;
-#endif
 #ifdef CONFIG_TIMER_STATS
 	void				*start_site;
 	char				start_comm[16];
@@ -194,10 +192,10 @@ struct hrtimer_cpu_base {
 	spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
+	struct list_head		cb_pending;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t				expires_next;
 	int				hres_active;
-	struct list_head		cb_pending;
 	unsigned long			nr_events;
 #endif
 };
@@ -217,6 +215,11 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 	return timer->base->get_time();
 }
 
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+	return timer->base->cpu_base->hres_active;
+}
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -248,6 +251,10 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 	return timer->base->softirq_time;
 }
 
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+	return 0;
+}
 #endif
 
 extern ktime_t ktime_get(void);
@@ -310,6 +317,7 @@ extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
+extern void hrtimer_run_pending(void);
 
 /* Bootup initialization: */
 extern void __init hrtimers_init(void);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index cae35b6b9ae..796019b22b6 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -132,9 +132,12 @@ extern struct group_info init_groups;
 	.cpus_allowed	= CPU_MASK_ALL,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
-	.run_list	= LIST_HEAD_INIT(tsk.run_list),			\
+	.rt		= {						\
+		.run_list	= LIST_HEAD_INIT(tsk.rt.run_list),	\
+		.time_slice	= HZ, 					\
+		.nr_cpus_allowed = NR_CPUS,				\
+	},								\
 	.ioprio		= 0,						\
-	.time_slice	= HZ,						\
 	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
 	.ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children),		\
 	.ptrace_list	= LIST_HEAD_INIT(tsk.ptrace_list),		\
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 2306920fa38..c3db4a00f1f 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -256,6 +256,7 @@ enum
 #ifdef CONFIG_HIGH_RES_TIMERS
 	HRTIMER_SOFTIRQ,
 #endif
+	RCU_SOFTIRQ, 	/* Preferable RCU should always be the last softirq */
 };
 
 /* softirq mask and active fields moved to irq_cpustat_t in
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 8b080024bbc..7ba9e47bf06 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -29,6 +29,12 @@
 # define SHIFT_HZ	9
 #elif HZ >= 768 && HZ < 1536
 # define SHIFT_HZ	10
+#elif HZ >= 1536 && HZ < 3072
+# define SHIFT_HZ	11
+#elif HZ >= 3072 && HZ < 6144
+# define SHIFT_HZ	12
+#elif HZ >= 6144 && HZ < 12288
+# define SHIFT_HZ	13
 #else
 # error You lose.
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 94bc9965696..a7283c9bead 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -105,8 +105,8 @@ struct user;
  * supposed to.
  */
 #ifdef CONFIG_PREEMPT_VOLUNTARY
-extern int cond_resched(void);
-# define might_resched() cond_resched()
+extern int _cond_resched(void);
+# define might_resched() _cond_resched()
 #else
 # define might_resched() do { } while (0)
 #endif
diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h
new file mode 100644
index 00000000000..901c2d6377a
--- /dev/null
+++ b/include/linux/latencytop.h
@@ -0,0 +1,44 @@
+/*
+ * latencytop.h: Infrastructure for displaying latency
+ *
+ * (C) Copyright 2008 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ */
+
+#ifndef _INCLUDE_GUARD_LATENCYTOP_H_
+#define _INCLUDE_GUARD_LATENCYTOP_H_
+
+#ifdef CONFIG_LATENCYTOP
+
+#define LT_SAVECOUNT		32
+#define LT_BACKTRACEDEPTH	12
+
+struct latency_record {
+	unsigned long	backtrace[LT_BACKTRACEDEPTH];
+	unsigned int	count;
+	unsigned long	time;
+	unsigned long	max;
+};
+
+
+struct task_struct;
+
+void account_scheduler_latency(struct task_struct *task, int usecs, int inter);
+
+void clear_all_latency_tracing(struct task_struct *p);
+
+#else
+
+static inline void
+account_scheduler_latency(struct task_struct *task, int usecs, int inter)
+{
+}
+
+static inline void clear_all_latency_tracing(struct task_struct *p)
+{
+}
+
+#endif
+
+#endif
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 0c40cc0b4a3..5dfbc684ce7 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -207,9 +207,7 @@ static inline int notifier_to_errno(int ret)
 #define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
 #define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
-#define CPU_LOCK_ACQUIRE	0x0008 /* Acquire all hotcpu locks */
-#define CPU_LOCK_RELEASE	0x0009 /* Release all hotcpu locks */
-#define CPU_DYING		0x000A /* CPU (unsigned)v not running any task,
+#define CPU_DYING		0x0008 /* CPU (unsigned)v not running any task,
 				        * not handling interrupts, soon dead */
 
 /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
new file mode 100644
index 00000000000..4d6624260b4
--- /dev/null
+++ b/include/linux/rcuclassic.h
@@ -0,0 +1,164 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (classic version)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2001
+ *
+ * Author: Dipankar Sarma <dipankar@in.ibm.com>
+ *
+ * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
+ * Papers:
+ * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
+ * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * 		Documentation/RCU
+ *
+ */
+
+#ifndef __LINUX_RCUCLASSIC_H
+#define __LINUX_RCUCLASSIC_H
+
+#ifdef __KERNEL__
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/seqlock.h>
+
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+	long	cur;		/* Current batch number.                      */
+	long	completed;	/* Number of the last completed batch         */
+	int	next_pending;	/* Is the next batch already waiting?         */
+
+	int	signaled;
+
+	spinlock_t	lock	____cacheline_internodealigned_in_smp;
+	cpumask_t	cpumask; /* CPUs that need to switch in order    */
+				 /* for current batch to proceed.        */
+} ____cacheline_internodealigned_in_smp;
+
+/* Is batch a before batch b ? */
+static inline int rcu_batch_before(long a, long b)
+{
+	return (a - b) < 0;
+}
+
+/* Is batch a after batch b ? */
+static inline int rcu_batch_after(long a, long b)
+{
+	return (a - b) > 0;
+}
+
+/*
+ * Per-CPU data for Read-Copy UPdate.
+ * nxtlist - new callbacks are added here
+ * curlist - current batch for which quiescent cycle started if any
+ */
+struct rcu_data {
+	/* 1) quiescent state handling : */
+	long		quiescbatch;     /* Batch # for grace period */
+	int		passed_quiesc;	 /* User-mode/idle loop etc. */
+	int		qs_pending;	 /* core waits for quiesc state */
+
+	/* 2) batch handling */
+	long  	       	batch;           /* Batch # for current RCU batch */
+	struct rcu_head *nxtlist;
+	struct rcu_head **nxttail;
+	long            qlen; 	 	 /* # of queued callbacks */
+	struct rcu_head *curlist;
+	struct rcu_head **curtail;
+	struct rcu_head *donelist;
+	struct rcu_head **donetail;
+	long		blimit;		 /* Upper limit on a processed batch */
+	int cpu;
+	struct rcu_head barrier;
+};
+
+DECLARE_PER_CPU(struct rcu_data, rcu_data);
+DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
+
+/*
+ * Increment the quiescent state counter.
+ * The counter is a bit degenerated: We do not need to know
+ * how many quiescent states passed, just if there was at least
+ * one since the start of the grace period. Thus just a flag.
+ */
+static inline void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+	rdp->passed_quiesc = 1;
+}
+static inline void rcu_bh_qsctr_inc(int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+	rdp->passed_quiesc = 1;
+}
+
+extern int rcu_pending(int cpu);
+extern int rcu_needs_cpu(int cpu);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern struct lockdep_map rcu_lock_map;
+# define rcu_read_acquire()	\
+			lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_)
+# define rcu_read_release()	lock_release(&rcu_lock_map, 1, _THIS_IP_)
+#else
+# define rcu_read_acquire()	do { } while (0)
+# define rcu_read_release()	do { } while (0)
+#endif
+
+#define __rcu_read_lock() \
+	do { \
+		preempt_disable(); \
+		__acquire(RCU); \
+		rcu_read_acquire(); \
+	} while (0)
+#define __rcu_read_unlock() \
+	do { \
+		rcu_read_release(); \
+		__release(RCU); \
+		preempt_enable(); \
+	} while (0)
+#define __rcu_read_lock_bh() \
+	do { \
+		local_bh_disable(); \
+		__acquire(RCU_BH); \
+		rcu_read_acquire(); \
+	} while (0)
+#define __rcu_read_unlock_bh() \
+	do { \
+		rcu_read_release(); \
+		__release(RCU_BH); \
+		local_bh_enable(); \
+	} while (0)
+
+#define __synchronize_sched() synchronize_rcu()
+
+extern void __rcu_init(void);
+extern void rcu_check_callbacks(int cpu, int user);
+extern void rcu_restart_cpu(int cpu);
+
+extern long rcu_batches_completed(void);
+extern long rcu_batches_completed_bh(void);
+
+#endif /* __KERNEL__ */
+#endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index cc24a01df94..d32c14de270 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -15,7 +15,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
- * Copyright (C) IBM Corporation, 2001
+ * Copyright IBM Corporation, 2001
  *
  * Author: Dipankar Sarma <dipankar@in.ibm.com>
  * 
@@ -53,96 +53,18 @@ struct rcu_head {
 	void (*func)(struct rcu_head *head);
 };
 
+#ifdef CONFIG_CLASSIC_RCU
+#include <linux/rcuclassic.h>
+#else /* #ifdef CONFIG_CLASSIC_RCU */
+#include <linux/rcupreempt.h>
+#endif /* #else #ifdef CONFIG_CLASSIC_RCU */
+
 #define RCU_HEAD_INIT 	{ .next = NULL, .func = NULL }
 #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
 #define INIT_RCU_HEAD(ptr) do { \
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 
-
-
-/* Global control variables for rcupdate callback mechanism. */
-struct rcu_ctrlblk {
-	long	cur;		/* Current batch number.                      */
-	long	completed;	/* Number of the last completed batch         */
-	int	next_pending;	/* Is the next batch already waiting?         */
-
-	int	signaled;
-
-	spinlock_t	lock	____cacheline_internodealigned_in_smp;
-	cpumask_t	cpumask; /* CPUs that need to switch in order    */
-	                         /* for current batch to proceed.        */
-} ____cacheline_internodealigned_in_smp;
-
-/* Is batch a before batch b ? */
-static inline int rcu_batch_before(long a, long b)
-{
-        return (a - b) < 0;
-}
-
-/* Is batch a after batch b ? */
-static inline int rcu_batch_after(long a, long b)
-{
-        return (a - b) > 0;
-}
-
-/*
- * Per-CPU data for Read-Copy UPdate.
- * nxtlist - new callbacks are added here
- * curlist - current batch for which quiescent cycle started if any
- */
-struct rcu_data {
-	/* 1) quiescent state handling : */
-	long		quiescbatch;     /* Batch # for grace period */
-	int		passed_quiesc;	 /* User-mode/idle loop etc. */
-	int		qs_pending;	 /* core waits for quiesc state */
-
-	/* 2) batch handling */
-	long  	       	batch;           /* Batch # for current RCU batch */
-	struct rcu_head *nxtlist;
-	struct rcu_head **nxttail;
-	long            qlen; 	 	 /* # of queued callbacks */
-	struct rcu_head *curlist;
-	struct rcu_head **curtail;
-	struct rcu_head *donelist;
-	struct rcu_head **donetail;
-	long		blimit;		 /* Upper limit on a processed batch */
-	int cpu;
-	struct rcu_head barrier;
-};
-
-DECLARE_PER_CPU(struct rcu_data, rcu_data);
-DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
-
-/*
- * Increment the quiescent state counter.
- * The counter is a bit degenerated: We do not need to know
- * how many quiescent states passed, just if there was at least
- * one since the start of the grace period. Thus just a flag.
- */
-static inline void rcu_qsctr_inc(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	rdp->passed_quiesc = 1;
-}
-static inline void rcu_bh_qsctr_inc(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
-	rdp->passed_quiesc = 1;
-}
-
-extern int rcu_pending(int cpu);
-extern int rcu_needs_cpu(int cpu);
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-extern struct lockdep_map rcu_lock_map;
-# define rcu_read_acquire()	lock_acquire(&rcu_lock_map, 0, 0, 2, 1, _THIS_IP_)
-# define rcu_read_release()	lock_release(&rcu_lock_map, 1, _THIS_IP_)
-#else
-# define rcu_read_acquire()	do { } while (0)
-# define rcu_read_release()	do { } while (0)
-#endif
-
 /**
  * rcu_read_lock - mark the beginning of an RCU read-side critical section.
  *
@@ -172,24 +94,13 @@ extern struct lockdep_map rcu_lock_map;
  *
  * It is illegal to block while in an RCU read-side critical section.
  */
-#define rcu_read_lock() \
-	do { \
-		preempt_disable(); \
-		__acquire(RCU); \
-		rcu_read_acquire(); \
-	} while(0)
+#define rcu_read_lock() __rcu_read_lock()
 
 /**
  * rcu_read_unlock - marks the end of an RCU read-side critical section.
  *
  * See rcu_read_lock() for more information.
  */
-#define rcu_read_unlock() \
-	do { \
-		rcu_read_release(); \
-		__release(RCU); \
-		preempt_enable(); \
-	} while(0)
 
 /*
  * So where is rcu_write_lock()?  It does not exist, as there is no
@@ -200,6 +111,7 @@ extern struct lockdep_map rcu_lock_map;
  * used as well.  RCU does not care how the writers keep out of each
  * others' way, as long as they do so.
  */
+#define rcu_read_unlock() __rcu_read_unlock()
 
 /**
  * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
@@ -212,24 +124,14 @@ extern struct lockdep_map rcu_lock_map;
  * can use just rcu_read_lock().
  *
  */
-#define rcu_read_lock_bh() \
-	do { \
-		local_bh_disable(); \
-		__acquire(RCU_BH); \
-		rcu_read_acquire(); \
-	} while(0)
+#define rcu_read_lock_bh() __rcu_read_lock_bh()
 
 /*
  * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
  *
  * See rcu_read_lock_bh() for more information.
  */
-#define rcu_read_unlock_bh() \
-	do { \
-		rcu_read_release(); \
-		__release(RCU_BH); \
-		local_bh_enable(); \
-	} while(0)
+#define rcu_read_unlock_bh() __rcu_read_unlock_bh()
 
 /*
  * Prevent the compiler from merging or refetching accesses.  The compiler
@@ -293,21 +195,52 @@ extern struct lockdep_map rcu_lock_map;
  * In "classic RCU", these two guarantees happen to be one and
  * the same, but can differ in realtime RCU implementations.
  */
-#define synchronize_sched() synchronize_rcu()
+#define synchronize_sched() __synchronize_sched()
 
-extern void rcu_init(void);
-extern void rcu_check_callbacks(int cpu, int user);
-extern void rcu_restart_cpu(int cpu);
-extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
+/**
+ * call_rcu - Queue an RCU callback for invocation after a grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual update function to be invoked after the grace period
+ *
+ * The update function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed.  RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
+ * and may be nested.
+ */
+extern void call_rcu(struct rcu_head *head,
+			      void (*func)(struct rcu_head *head));
 
-/* Exported interfaces */
-extern void FASTCALL(call_rcu(struct rcu_head *head, 
-				void (*func)(struct rcu_head *head)));
-extern void FASTCALL(call_rcu_bh(struct rcu_head *head,
-				void (*func)(struct rcu_head *head)));
+/**
+ * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual update function to be invoked after the grace period
+ *
+ * The update function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_bh() assumes
+ * that the read-side critical sections end on completion of a softirq
+ * handler. This means that read-side critical sections in process
+ * context must not be interrupted by softirqs. This interface is to be
+ * used when most of the read-side critical sections are in softirq context.
+ * RCU read-side critical sections are delimited by :
+ *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
+ *  OR
+ *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
+ *  These may be nested.
+ */
+extern void call_rcu_bh(struct rcu_head *head,
+			void (*func)(struct rcu_head *head));
+
+/* Exported common interfaces */
 extern void synchronize_rcu(void);
 extern void rcu_barrier(void);
+extern long rcu_batches_completed(void);
+extern long rcu_batches_completed_bh(void);
+
+/* Internal to kernel */
+extern void rcu_init(void);
+extern int rcu_needs_cpu(int cpu);
 
 #endif /* __KERNEL__ */
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
new file mode 100644
index 00000000000..ece8eb3e415
--- /dev/null
+++ b/include/linux/rcupreempt.h
@@ -0,0 +1,86 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (RT implementation)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2006
+ *
+ * Author:  Paul McKenney <paulmck@us.ibm.com>
+ *
+ * Based on the original work by Paul McKenney <paul.mckenney@us.ibm.com>
+ * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
+ * Papers:
+ * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
+ * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * 		Documentation/RCU
+ *
+ */
+
+#ifndef __LINUX_RCUPREEMPT_H
+#define __LINUX_RCUPREEMPT_H
+
+#ifdef __KERNEL__
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/seqlock.h>
+
+#define rcu_qsctr_inc(cpu)
+#define rcu_bh_qsctr_inc(cpu)
+#define call_rcu_bh(head, rcu) call_rcu(head, rcu)
+
+extern void __rcu_read_lock(void);
+extern void __rcu_read_unlock(void);
+extern int rcu_pending(int cpu);
+extern int rcu_needs_cpu(int cpu);
+
+#define __rcu_read_lock_bh()	{ rcu_read_lock(); local_bh_disable(); }
+#define __rcu_read_unlock_bh()	{ local_bh_enable(); rcu_read_unlock(); }
+
+extern void __synchronize_sched(void);
+
+extern void __rcu_init(void);
+extern void rcu_check_callbacks(int cpu, int user);
+extern void rcu_restart_cpu(int cpu);
+extern long rcu_batches_completed(void);
+
+/*
+ * Return the number of RCU batches processed thus far. Useful for debug
+ * and statistic. The _bh variant is identifcal to straight RCU
+ */
+static inline long rcu_batches_completed_bh(void)
+{
+	return rcu_batches_completed();
+}
+
+#ifdef CONFIG_RCU_TRACE
+struct rcupreempt_trace;
+extern long *rcupreempt_flipctr(int cpu);
+extern long rcupreempt_data_completed(void);
+extern int rcupreempt_flip_flag(int cpu);
+extern int rcupreempt_mb_flag(int cpu);
+extern char *rcupreempt_try_flip_state_name(void);
+extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu);
+#endif
+
+struct softirq_action;
+
+#endif /* __KERNEL__ */
+#endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcupreempt_trace.h b/include/linux/rcupreempt_trace.h
new file mode 100644
index 00000000000..21cd6b2a5c4
--- /dev/null
+++ b/include/linux/rcupreempt_trace.h
@@ -0,0 +1,99 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (RT implementation)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2006
+ *
+ * Author:  Paul McKenney <paulmck@us.ibm.com>
+ *
+ * Based on the original work by Paul McKenney <paul.mckenney@us.ibm.com>
+ * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
+ * Papers:
+ * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
+ * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001)
+ *
+ * For detailed explanation of the Preemptible Read-Copy Update mechanism see -
+ * 		 http://lwn.net/Articles/253651/
+ */
+
+#ifndef __LINUX_RCUPREEMPT_TRACE_H
+#define __LINUX_RCUPREEMPT_TRACE_H
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+#include <asm/atomic.h>
+
+/*
+ * PREEMPT_RCU data structures.
+ */
+
+struct rcupreempt_trace {
+	long		next_length;
+	long		next_add;
+	long		wait_length;
+	long		wait_add;
+	long		done_length;
+	long		done_add;
+	long		done_remove;
+	atomic_t	done_invoked;
+	long		rcu_check_callbacks;
+	atomic_t	rcu_try_flip_1;
+	atomic_t	rcu_try_flip_e1;
+	long		rcu_try_flip_i1;
+	long		rcu_try_flip_ie1;
+	long		rcu_try_flip_g1;
+	long		rcu_try_flip_a1;
+	long		rcu_try_flip_ae1;
+	long		rcu_try_flip_a2;
+	long		rcu_try_flip_z1;
+	long		rcu_try_flip_ze1;
+	long		rcu_try_flip_z2;
+	long		rcu_try_flip_m1;
+	long		rcu_try_flip_me1;
+	long		rcu_try_flip_m2;
+};
+
+#ifdef CONFIG_RCU_TRACE
+#define RCU_TRACE(fn, arg) 	fn(arg);
+#else
+#define RCU_TRACE(fn, arg)
+#endif
+
+extern void rcupreempt_trace_move2done(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_move2wait(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_e1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_i1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_ie1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_g1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_a1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_ae1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_a2(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_z1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_ze1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_z2(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_m1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_me1(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_try_flip_m2(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_check_callbacks(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_done_remove(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_invoke(struct rcupreempt_trace *trace);
+extern void rcupreempt_trace_next_add(struct rcupreempt_trace *trace);
+
+#endif /* __KERNEL__ */
+#endif /* __LINUX_RCUPREEMPT_TRACE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d6eacda765c..df5b24ee80b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -78,7 +78,6 @@ struct sched_param {
 #include <linux/proportions.h>
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
-#include <linux/futex.h>
 #include <linux/rtmutex.h>
 
 #include <linux/time.h>
@@ -88,11 +87,13 @@ struct sched_param {
 #include <linux/hrtimer.h>
 #include <linux/task_io_accounting.h>
 #include <linux/kobject.h>
+#include <linux/latencytop.h>
 
 #include <asm/processor.h>
 
 struct exec_domain;
 struct futex_pi_state;
+struct robust_list_head;
 struct bio;
 
 /*
@@ -230,6 +231,8 @@ static inline int select_nohz_load_balancer(int cpu)
 }
 #endif
 
+extern unsigned long rt_needs_cpu(int cpu);
+
 /*
  * Only dump TASK_* tasks. (0 for all tasks)
  */
@@ -257,13 +260,19 @@ extern void trap_init(void);
 extern void account_process_tick(struct task_struct *task, int user);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
+extern void hrtick_resched(void);
+
+extern void sched_show_task(struct task_struct *p);
 
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 extern void softlockup_tick(void);
 extern void spawn_softlockup_task(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern int softlockup_thresh;
+extern unsigned long  softlockup_thresh;
+extern unsigned long sysctl_hung_task_check_count;
+extern unsigned long sysctl_hung_task_timeout_secs;
+extern unsigned long sysctl_hung_task_warnings;
 #else
 static inline void softlockup_tick(void)
 {
@@ -822,6 +831,7 @@ struct sched_class {
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
 	void (*yield_task) (struct rq *rq);
+	int  (*select_task_rq)(struct task_struct *p, int sync);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
 
@@ -837,11 +847,25 @@ struct sched_class {
 	int (*move_one_task) (struct rq *this_rq, int this_cpu,
 			      struct rq *busiest, struct sched_domain *sd,
 			      enum cpu_idle_type idle);
+	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
+	void (*post_schedule) (struct rq *this_rq);
+	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
 #endif
 
 	void (*set_curr_task) (struct rq *rq);
-	void (*task_tick) (struct rq *rq, struct task_struct *p);
+	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_new) (struct rq *rq, struct task_struct *p);
+	void (*set_cpus_allowed)(struct task_struct *p, cpumask_t *newmask);
+
+	void (*join_domain)(struct rq *rq);
+	void (*leave_domain)(struct rq *rq);
+
+	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
+			       int running);
+	void (*switched_to) (struct rq *this_rq, struct task_struct *task,
+			     int running);
+	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
+			     int oldprio, int running);
 };
 
 struct load_weight {
@@ -871,6 +895,8 @@ struct sched_entity {
 #ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
 	u64			wait_max;
+	u64			wait_count;
+	u64			wait_sum;
 
 	u64			sleep_start;
 	u64			sleep_max;
@@ -909,6 +935,21 @@ struct sched_entity {
 #endif
 };
 
+struct sched_rt_entity {
+	struct list_head run_list;
+	unsigned int time_slice;
+	unsigned long timeout;
+	int nr_cpus_allowed;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	struct sched_rt_entity	*parent;
+	/* rq on which this entity is (to be) queued: */
+	struct rt_rq		*rt_rq;
+	/* rq "owned" by this entity/group: */
+	struct rt_rq		*my_q;
+#endif
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -925,9 +966,9 @@ struct task_struct {
 #endif
 
 	int prio, static_prio, normal_prio;
-	struct list_head run_list;
 	const struct sched_class *sched_class;
 	struct sched_entity se;
+	struct sched_rt_entity rt;
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* list of struct preempt_notifier: */
@@ -951,7 +992,11 @@ struct task_struct {
 
 	unsigned int policy;
 	cpumask_t cpus_allowed;
-	unsigned int time_slice;
+
+#ifdef CONFIG_PREEMPT_RCU
+	int rcu_read_lock_nesting;
+	int rcu_flipctr_idx;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -1041,6 +1086,11 @@ struct task_struct {
 /* ipc stuff */
 	struct sysv_sem sysvsem;
 #endif
+#ifdef CONFIG_DETECT_SOFTLOCKUP
+/* hung task detection */
+	unsigned long last_switch_timestamp;
+	unsigned long last_switch_count;
+#endif
 /* CPU-specific state of this task */
 	struct thread_struct thread;
 /* filesystem information */
@@ -1173,6 +1223,10 @@ struct task_struct {
 	int make_it_fail;
 #endif
 	struct prop_local_single dirties;
+#ifdef CONFIG_LATENCYTOP
+	int latency_record_count;
+	struct latency_record latency_record[LT_SAVECOUNT];
+#endif
 };
 
 /*
@@ -1453,6 +1507,12 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_rt_period;
+extern unsigned int sysctl_sched_rt_ratio;
+#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+extern unsigned int sysctl_sched_min_bal_int_shares;
+extern unsigned int sysctl_sched_max_bal_int_shares;
+#endif
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
 		struct file *file, void __user *buffer, size_t *length,
@@ -1845,7 +1905,18 @@ static inline int need_resched(void)
  * cond_resched_lock() will drop the spinlock before scheduling,
  * cond_resched_softirq() will enable bhs before scheduling.
  */
-extern int cond_resched(void);
+#ifdef CONFIG_PREEMPT
+static inline int cond_resched(void)
+{
+	return 0;
+}
+#else
+extern int _cond_resched(void);
+static inline int cond_resched(void)
+{
+	return _cond_resched();
+}
+#endif
 extern int cond_resched_lock(spinlock_t * lock);
 extern int cond_resched_softirq(void);
 
diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h
index 58962c51dee..aab3a4cff4e 100644
--- a/include/linux/smp_lock.h
+++ b/include/linux/smp_lock.h
@@ -17,22 +17,10 @@ extern void __lockfunc __release_kernel_lock(void);
 		__release_kernel_lock();	\
 } while (0)
 
-/*
- * Non-SMP kernels will never block on the kernel lock,
- * so we are better off returning a constant zero from
- * reacquire_kernel_lock() so that the compiler can see
- * it at compile-time.
- */
-#if defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_BKL)
-# define return_value_on_smp return
-#else
-# define return_value_on_smp
-#endif
-
 static inline int reacquire_kernel_lock(struct task_struct *task)
 {
 	if (unlikely(task->lock_depth >= 0))
-		return_value_on_smp __reacquire_kernel_lock();
+		return __reacquire_kernel_lock();
 	return 0;
 }
 
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index e7fa657d0c4..5da9794b2d7 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -9,10 +9,13 @@ struct stack_trace {
 };
 
 extern void save_stack_trace(struct stack_trace *trace);
+extern void save_stack_trace_tsk(struct task_struct *tsk,
+				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
 #else
 # define save_stack_trace(trace)			do { } while (0)
+# define save_stack_trace_tsk(tsk, trace)		do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
 #endif
 
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 47729f18bfd..2352f46160d 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2002, IBM Corp.
  *
- * All rights reserved.          
+ * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -103,6 +103,7 @@
 	.forkexec_idx		= 0,			\
 	.flags			= SD_LOAD_BALANCE	\
 				| SD_BALANCE_NEWIDLE	\
+				| SD_BALANCE_FORK	\
 				| SD_BALANCE_EXEC	\
 				| SD_WAKE_AFFINE	\
 				| SD_WAKE_IDLE		\
@@ -134,6 +135,7 @@
 	.forkexec_idx		= 1,			\
 	.flags			= SD_LOAD_BALANCE	\
 				| SD_BALANCE_NEWIDLE	\
+				| SD_BALANCE_FORK	\
 				| SD_BALANCE_EXEC	\
 				| SD_WAKE_AFFINE	\
 				| SD_WAKE_IDLE		\
@@ -165,6 +167,7 @@
 	.forkexec_idx		= 1,			\
 	.flags			= SD_LOAD_BALANCE	\
 				| SD_BALANCE_NEWIDLE	\
+				| SD_BALANCE_FORK	\
 				| SD_BALANCE_EXEC	\
 				| SD_WAKE_AFFINE	\
 				| BALANCE_FOR_PKG_POWER,\