Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (28 commits)
  rcu: Move end of special early-boot RCU operation earlier
  rcu: Changes from reviews: avoid casts, fix/add warnings, improve comments
  rcu: Create rcutree plugins to handle hotplug CPU for multi-level trees
  rcu: Remove lockdep annotations from RCU's _notrace() API members
  rcu: Add #ifdef to suppress __rcu_offline_cpu() warning in !HOTPLUG_CPU builds
  rcu: Add CPU-offline processing for single-node configurations
  rcu: Add "notrace" to RCU function headers used by ftrace
  rcu: Remove CONFIG_PREEMPT_RCU
  rcu: Merge preemptable-RCU functionality into hierarchical RCU
  rcu: Simplify rcu_pending()/rcu_check_callbacks() API
  rcu: Use debugfs_remove_recursive() simplify code.
  rcu: Merge per-RCU-flavor initialization into pre-existing macro
  rcu: Fix online/offline indication for rcudata.csv trace file
  rcu: Consolidate sparse and lockdep declarations in include/linux/rcupdate.h
  rcu: Renamings to increase RCU clarity
  rcu: Move private definitions from include/linux/rcutree.h to kernel/rcutree.h
  rcu: Expunge lingering references to CONFIG_CLASSIC_RCU, optimize on !SMP
  rcu: Delay rcu_barrier() wait until beginning of next CPU-hotunplug operation.
  rcu: Fix typo in rcu_irq_exit() comment header
  rcu: Make rcupreempt_trace.c look at offline CPUs
  ...

10 files changed, 157 insertions, 673 deletions

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 4d668e05d458..47536197ffdd 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -48,6 +48,15 @@ struct notifier_block;
 
 #ifdef CONFIG_SMP
 /* Need to know about CPUs going up/down? */
+#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
+#define cpu_notifier(fn, pri) {                                 \
+        static struct notifier_block fn##_nb __cpuinitdata =    \
+                { .notifier_call = fn, .priority = pri };       \
+        register_cpu_notifier(&fn##_nb);                        \
+}
+#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
+#define cpu_notifier(fn, pri)   do { (void)(fn); } while (0)
+#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
 #ifdef CONFIG_HOTPLUG_CPU
 extern int register_cpu_notifier(struct notifier_block *nb);
 extern void unregister_cpu_notifier(struct notifier_block *nb);
@@ -74,6 +83,8 @@ extern void cpu_maps_update_done(void);
 
 #else   /* CONFIG_SMP */
 
+#define cpu_notifier(fn, pri)   do { (void)(fn); } while (0)
+
 static inline int register_cpu_notifier(struct notifier_block *nb)
 {
         return 0;
@@ -99,11 +110,7 @@ extern struct sysdev_class cpu_sysdev_class;
 
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
-#define hotcpu_notifier(fn, pri) {                              \
-        static struct notifier_block fn##_nb __cpuinitdata =    \
-                { .notifier_call = fn, .priority = pri };       \
-        register_cpu_notifier(&fn##_nb);                        \
-}
+#define hotcpu_notifier(fn, pri)        cpu_notifier(fn, pri)
 #define register_hotcpu_notifier(nb)    register_cpu_notifier(nb)
 #define unregister_hotcpu_notifier(nb)  unregister_cpu_notifier(nb)
 int cpu_down(unsigned int cpu);
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 8246c697863d..330cb31bb496 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -132,7 +132,7 @@ static inline void account_system_vtime(struct task_struct *tsk)
 }
 #endif
 
-#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU)
+#if defined(CONFIG_NO_HZ)
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
 extern void rcu_nmi_enter(void);
@@ -142,7 +142,7 @@ extern void rcu_nmi_exit(void);
 # define rcu_irq_exit() do { } while (0)
 # define rcu_nmi_enter() do { } while (0)
 # define rcu_nmi_exit() do { } while (0)
-#endif /* #if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) */
+#endif /* #if defined(CONFIG_NO_HZ) */
 
 /*
  * It is safe to do non-atomic ops on ->hardirq_context,
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 7fc01b13be43..9e7f2e8fc66e 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -94,6 +94,16 @@ extern struct group_info init_groups;
 # define CAP_INIT_BSET  CAP_INIT_EFF_SET
 #endif
 
+#ifdef CONFIG_TREE_PREEMPT_RCU
+#define INIT_TASK_RCU_PREEMPT(tsk)                                      \
+        .rcu_read_lock_nesting = 0,                                     \
+        .rcu_read_unlock_special = 0,                                   \
+        .rcu_blocked_node = NULL,                                       \
+        .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),
+#else
+#define INIT_TASK_RCU_PREEMPT(tsk)
+#endif
+
 extern struct cred init_cred;
 
 #ifdef CONFIG_PERF_COUNTERS
@@ -173,6 +183,7 @@ extern struct cred init_cred;
         INIT_LOCKDEP                                                    \
         INIT_FTRACE_GRAPH                                               \
         INIT_TRACE_RECURSION                                            \
+        INIT_TASK_RCU_PREEMPT(tsk)                                      \
 }
 
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index aec3252afcf5..ed5d7501e181 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -132,7 +132,7 @@ static inline int page_cache_get_speculative(struct page *page)
 {
         VM_BUG_ON(in_interrupt());
 
-#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
+#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
 # ifdef CONFIG_PREEMPT
         VM_BUG_ON(!in_atomic());
 # endif
@@ -170,7 +170,7 @@ static inline int page_cache_add_speculative(struct page *page, int count)
 {
         VM_BUG_ON(in_interrupt());
 
-#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
+#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
 # ifdef CONFIG_PREEMPT
         VM_BUG_ON(!in_atomic());
 # endif
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
deleted file mode 100644
index bfd92e1e5d2c..000000000000
--- a/include/linux/rcuclassic.h
+++ /dev/null
@@ -1,178 +0,0 @@
-/*
- * 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
-
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
-
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK    (10 * HZ) /* for rcp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK  (30 * HZ) /* for rcp->jiffies_stall */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-/* Global control variables for rcupdate callback mechanism. */
-struct rcu_ctrlblk {
-        long    cur;            /* Current batch number.                      */
-        long    completed;      /* Number of the last completed batch         */
-        long    pending;        /* Number of the last pending batch           */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-        unsigned long gp_start; /* Time at which GP started in jiffies. */
-        unsigned long jiffies_stall;
-                                /* Time at which to check for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-        int     signaled;
-
-        spinlock_t      lock    ____cacheline_internodealigned_in_smp;
-        DECLARE_BITMAP(cpumask, NR_CPUS); /* CPUs that need to switch 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. */
-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 */
-        /*
-         * if nxtlist is not NULL, then:
-         * batch:
-         *      The batch # for the last entry of nxtlist
-         * [*nxttail[1], NULL = *nxttail[2]):
-         *      Entries that batch # <= batch
-         * [*nxttail[0], *nxttail[1]):
-         *      Entries that batch # <= batch - 1
-         * [nxtlist, *nxttail[0]):
-         *      Entries that batch # <= batch - 2
-         *      The grace period for these entries has completed, and
-         *      the other grace-period-completed entries may be moved
-         *      here temporarily in rcu_process_callbacks().
-         */
-        long            batch;
-        struct rcu_head *nxtlist;
-        struct rcu_head **nxttail[3];
-        long            qlen;            /* # of queued callbacks */
-        struct rcu_head *donelist;
-        struct rcu_head **donetail;
-        long            blimit;          /* Upper limit on a processed batch */
-        int cpu;
-        struct rcu_head barrier;
-};
-
-/*
- * 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.
- */
-extern void rcu_qsctr_inc(int cpu);
-extern void rcu_bh_qsctr_inc(int cpu);
-
-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, NULL, _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()
-
-#define call_rcu_sched(head, func) call_rcu(head, func)
-
-extern void __rcu_init(void);
-#define rcu_init_sched()        do { } while (0)
-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);
-
-#define rcu_enter_nohz()        do { } while (0)
-#define rcu_exit_nohz()         do { } while (0)
-
-/* A context switch is a grace period for rcuclassic. */
-static inline int rcu_blocking_is_gp(void)
-{
-        return num_online_cpus() == 1;
-}
-
-#endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 15fbb3ca634d..95e0615f4d75 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -51,18 +51,26 @@ struct rcu_head {
         void (*func)(struct rcu_head *head);
 };
 
-/* Internal to kernel, but needed by rcupreempt.h. */
+/* Exported common interfaces */
+extern void synchronize_rcu(void);
+extern void synchronize_rcu_bh(void);
+extern void rcu_barrier(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
+extern void synchronize_sched_expedited(void);
+extern int sched_expedited_torture_stats(char *page);
+
+/* Internal to kernel */
+extern void rcu_init(void);
+extern void rcu_scheduler_starting(void);
+extern int rcu_needs_cpu(int cpu);
 extern int rcu_scheduler_active;
 
-#if defined(CONFIG_CLASSIC_RCU)
-#include <linux/rcuclassic.h>
-#elif defined(CONFIG_TREE_RCU)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
-#elif defined(CONFIG_PREEMPT_RCU)
-#include <linux/rcupreempt.h>
 #else
 #error "Unknown RCU implementation specified to kernel configuration"
-#endif /* #else #if defined(CONFIG_CLASSIC_RCU) */
+#endif
 
 #define RCU_HEAD_INIT   { .next = NULL, .func = NULL }
 #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
@@ -70,6 +78,16 @@ extern int rcu_scheduler_active;
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 
+#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, NULL, _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.
  *
@@ -99,7 +117,12 @@ extern int rcu_scheduler_active;
  *
  * It is illegal to block while in an RCU read-side critical section.
  */
-#define rcu_read_lock() __rcu_read_lock()
+static inline void rcu_read_lock(void)
+{
+        __rcu_read_lock();
+        __acquire(RCU);
+        rcu_read_acquire();
+}
 
 /**
  * rcu_read_unlock - marks the end of an RCU read-side critical section.
@@ -116,7 +139,12 @@ extern int rcu_scheduler_active;
  * 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()
+static inline void rcu_read_unlock(void)
+{
+        rcu_read_release();
+        __release(RCU);
+        __rcu_read_unlock();
+}
 
 /**
  * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
@@ -129,14 +157,24 @@ extern int rcu_scheduler_active;
  * can use just rcu_read_lock().
  *
  */
-#define rcu_read_lock_bh() __rcu_read_lock_bh()
+static inline void rcu_read_lock_bh(void)
+{
+        __rcu_read_lock_bh();
+        __acquire(RCU_BH);
+        rcu_read_acquire();
+}
 
 /*
  * 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() __rcu_read_unlock_bh()
+static inline void rcu_read_unlock_bh(void)
+{
+        rcu_read_release();
+        __release(RCU_BH);
+        __rcu_read_unlock_bh();
+}
 
 /**
  * rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
@@ -147,17 +185,34 @@ extern int rcu_scheduler_active;
  * - call_rcu_sched() and rcu_barrier_sched()
  * on the write-side to insure proper synchronization.
  */
-#define rcu_read_lock_sched() preempt_disable()
-#define rcu_read_lock_sched_notrace() preempt_disable_notrace()
+static inline void rcu_read_lock_sched(void)
+{
+        preempt_disable();
+        __acquire(RCU_SCHED);
+        rcu_read_acquire();
+}
+static inline notrace void rcu_read_lock_sched_notrace(void)
+{
+        preempt_disable_notrace();
+        __acquire(RCU_SCHED);
+}
 
 /*
  * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
  *
  * See rcu_read_lock_sched for more information.
  */
-#define rcu_read_unlock_sched() preempt_enable()
-#define rcu_read_unlock_sched_notrace() preempt_enable_notrace()
-
+static inline void rcu_read_unlock_sched(void)
+{
+        rcu_read_release();
+        __release(RCU_SCHED);
+        preempt_enable();
+}
+static inline notrace void rcu_read_unlock_sched_notrace(void)
+{
+        __release(RCU_SCHED);
+        preempt_enable_notrace();
+}
 
 
 /**
@@ -259,15 +314,4 @@ extern void call_rcu(struct rcu_head *head,
 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 void rcu_barrier_bh(void);
-extern void rcu_barrier_sched(void);
-
-/* Internal to kernel */
-extern void rcu_init(void);
-extern void rcu_scheduler_starting(void);
-extern int rcu_needs_cpu(int cpu);
-
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
deleted file mode 100644
index fce522782ffa..000000000000
--- a/include/linux/rcupreempt.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * 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
-
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/smp.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
-
-extern void rcu_qsctr_inc(int cpu);
-static inline void rcu_bh_qsctr_inc(int cpu) { }
-
-/*
- * Someone might want to pass call_rcu_bh as a function pointer.
- * So this needs to just be a rename and not a macro function.
- *  (no parentheses)
- */
-#define call_rcu_bh             call_rcu
-
-/**
- * call_rcu_sched - Queue RCU callback for invocation after sched 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
- * synchronize_sched()-style grace period elapses, in other words after
- * all currently executing preempt-disabled sections of code (including
- * hardirq handlers, NMI handlers, and local_irq_save() blocks) have
- * completed.
- */
-extern void call_rcu_sched(struct rcu_head *head,
-                           void (*func)(struct rcu_head *head));
-
-extern void __rcu_read_lock(void)       __acquires(RCU);
-extern void __rcu_read_unlock(void)     __releases(RCU);
-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_init_sched(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;
-
-#ifdef CONFIG_NO_HZ
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-#else
-# define rcu_enter_nohz()       do { } while (0)
-# define rcu_exit_nohz()        do { } while (0)
-#endif
-
-/*
- * A context switch is a grace period for rcupreempt synchronize_rcu()
- * only during early boot, before the scheduler has been initialized.
- * So, how the heck do we get a context switch?  Well, if the caller
- * invokes synchronize_rcu(), they are willing to accept a context
- * switch, so we simply pretend that one happened.
- *
- * After boot, there might be a blocked or preempted task in an RCU
- * read-side critical section, so we cannot then take the fastpath.
- */
-static inline int rcu_blocking_is_gp(void)
-{
-        return num_online_cpus() == 1 && !rcu_scheduler_active;
-}
-
-#endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcupreempt_trace.h b/include/linux/rcupreempt_trace.h
deleted file mode 100644
index b99ae073192a..000000000000
--- a/include/linux/rcupreempt_trace.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * 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
-
-#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 /* __LINUX_RCUPREEMPT_TRACE_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 5a5153806c42..a89307717825 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,264 +30,57 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
+extern void rcu_sched_qs(int cpu);
+extern void rcu_bh_qs(int cpu);
 
-/*
- * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
- * In theory, it should be possible to add more levels straightforwardly.
- * In practice, this has not been tested, so there is probably some
- * bug somewhere.
- */
-#define MAX_RCU_LVLS 3
-#define RCU_FANOUT            (CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_SQ         (RCU_FANOUT * RCU_FANOUT)
-#define RCU_FANOUT_CUBE       (RCU_FANOUT_SQ * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT
-#  define NUM_RCU_LVLS        1
-#  define NUM_RCU_LVL_0       1
-#  define NUM_RCU_LVL_1       (NR_CPUS)
-#  define NUM_RCU_LVL_2       0
-#  define NUM_RCU_LVL_3       0
-#elif NR_CPUS <= RCU_FANOUT_SQ
-#  define NUM_RCU_LVLS        2
-#  define NUM_RCU_LVL_0       1
-#  define NUM_RCU_LVL_1       (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT)
-#  define NUM_RCU_LVL_2       (NR_CPUS)
-#  define NUM_RCU_LVL_3       0
-#elif NR_CPUS <= RCU_FANOUT_CUBE
-#  define NUM_RCU_LVLS        3
-#  define NUM_RCU_LVL_0       1
-#  define NUM_RCU_LVL_1       (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ)
-#  define NUM_RCU_LVL_2       (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT))
-#  define NUM_RCU_LVL_3       NR_CPUS
-#else
-# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT */
-
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
-#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
-
-/*
- * Dynticks per-CPU state.
- */
-struct rcu_dynticks {
-        int dynticks_nesting;   /* Track nesting level, sort of. */
-        int dynticks;           /* Even value for dynticks-idle, else odd. */
-        int dynticks_nmi;       /* Even value for either dynticks-idle or */
-                                /*  not in nmi handler, else odd.  So this */
-                                /*  remains even for nmi from irq handler. */
-};
-
-/*
- * Definition for node within the RCU grace-period-detection hierarchy.
- */
-struct rcu_node {
-        spinlock_t lock;
-        unsigned long qsmask;   /* CPUs or groups that need to switch in */
-                                /*  order for current grace period to proceed.*/
-        unsigned long qsmaskinit;
-                                /* Per-GP initialization for qsmask. */
-        unsigned long grpmask;  /* Mask to apply to parent qsmask. */
-        int     grplo;          /* lowest-numbered CPU or group here. */
-        int     grphi;          /* highest-numbered CPU or group here. */
-        u8      grpnum;         /* CPU/group number for next level up. */
-        u8      level;          /* root is at level 0. */
-        struct rcu_node *parent;
-} ____cacheline_internodealigned_in_smp;
-
-/* Index values for nxttail array in struct rcu_data. */
-#define RCU_DONE_TAIL           0       /* Also RCU_WAIT head. */
-#define RCU_WAIT_TAIL           1       /* Also RCU_NEXT_READY head. */
-#define RCU_NEXT_READY_TAIL     2       /* Also RCU_NEXT head. */
-#define RCU_NEXT_TAIL           3
-#define RCU_NEXT_SIZE           4
-
-/* Per-CPU data for read-copy update. */
-struct rcu_data {
-        /* 1) quiescent-state and grace-period handling : */
-        long            completed;      /* Track rsp->completed gp number */
-                                        /*  in order to detect GP end. */
-        long            gpnum;          /* Highest gp number that this CPU */
-                                        /*  is aware of having started. */
-        long            passed_quiesc_completed;
-                                        /* Value of completed at time of qs. */
-        bool            passed_quiesc;  /* User-mode/idle loop etc. */
-        bool            qs_pending;     /* Core waits for quiesc state. */
-        bool            beenonline;     /* CPU online at least once. */
-        struct rcu_node *mynode;        /* This CPU's leaf of hierarchy */
-        unsigned long grpmask;          /* Mask to apply to leaf qsmask. */
-
-        /* 2) batch handling */
-        /*
-         * If nxtlist is not NULL, it is partitioned as follows.
-         * Any of the partitions might be empty, in which case the
-         * pointer to that partition will be equal to the pointer for
-         * the following partition.  When the list is empty, all of
-         * the nxttail elements point to nxtlist, which is NULL.
-         *
-         * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]):
-         *      Entries that might have arrived after current GP ended
-         * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
-         *      Entries known to have arrived before current GP ended
-         * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
-         *      Entries that batch # <= ->completed - 1: waiting for current GP
-         * [nxtlist, *nxttail[RCU_DONE_TAIL]):
-         *      Entries that batch # <= ->completed
-         *      The grace period for these entries has completed, and
-         *      the other grace-period-completed entries may be moved
-         *      here temporarily in rcu_process_callbacks().
-         */
-        struct rcu_head *nxtlist;
-        struct rcu_head **nxttail[RCU_NEXT_SIZE];
-        long            qlen;           /* # of queued callbacks */
-        long            blimit;         /* Upper limit on a processed batch */
-
-#ifdef CONFIG_NO_HZ
-        /* 3) dynticks interface. */
-        struct rcu_dynticks *dynticks;  /* Shared per-CPU dynticks state. */
-        int dynticks_snap;              /* Per-GP tracking for dynticks. */
-        int dynticks_nmi_snap;          /* Per-GP tracking for dynticks_nmi. */
-#endif /* #ifdef CONFIG_NO_HZ */
-
-        /* 4) reasons this CPU needed to be kicked by force_quiescent_state */
-#ifdef CONFIG_NO_HZ
-        unsigned long dynticks_fqs;     /* Kicked due to dynticks idle. */
-#endif /* #ifdef CONFIG_NO_HZ */
-        unsigned long offline_fqs;      /* Kicked due to being offline. */
-        unsigned long resched_ipi;      /* Sent a resched IPI. */
-
-        /* 5) __rcu_pending() statistics. */
-        long n_rcu_pending;             /* rcu_pending() calls since boot. */
-        long n_rp_qs_pending;
-        long n_rp_cb_ready;
-        long n_rp_cpu_needs_gp;
-        long n_rp_gp_completed;
-        long n_rp_gp_started;
-        long n_rp_need_fqs;
-        long n_rp_need_nothing;
-
-        int cpu;
-};
-
-/* Values for signaled field in struct rcu_state. */
-#define RCU_GP_INIT             0       /* Grace period being initialized. */
-#define RCU_SAVE_DYNTICK        1       /* Need to scan dyntick state. */
-#define RCU_FORCE_QS            2       /* Need to force quiescent state. */
-#ifdef CONFIG_NO_HZ
-#define RCU_SIGNAL_INIT         RCU_SAVE_DYNTICK
-#else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT         RCU_FORCE_QS
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
-#define RCU_JIFFIES_TILL_FORCE_QS        3      /* for rsp->jiffies_force_qs */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_STALL_RAT_DELAY             2         /* Allow other CPUs time */
-                                                  /*  to take at least one */
-                                                  /*  scheduling clock irq */
-                                                  /*  before ratting on them. */
-
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-
-/*
- * RCU global state, including node hierarchy.  This hierarchy is
- * represented in "heap" form in a dense array.  The root (first level)
- * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
- * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
- * and the third level in ->node[m+1] and following (->node[m+1] referenced
- * by ->level[2]).  The number of levels is determined by the number of
- * CPUs and by CONFIG_RCU_FANOUT.  Small systems will have a "hierarchy"
- * consisting of a single rcu_node.
- */
-struct rcu_state {
-        struct rcu_node node[NUM_RCU_NODES];    /* Hierarchy. */
-        struct rcu_node *level[NUM_RCU_LVLS];   /* Hierarchy levels. */
-        u32 levelcnt[MAX_RCU_LVLS + 1];         /* # nodes in each level. */
-        u8 levelspread[NUM_RCU_LVLS];           /* kids/node in each level. */
-        struct rcu_data *rda[NR_CPUS];          /* array of rdp pointers. */
-
-        /* The following fields are guarded by the root rcu_node's lock. */
-
-        u8      signaled ____cacheline_internodealigned_in_smp;
-                                                /* Force QS state. */
-        long    gpnum;                          /* Current gp number. */
-        long    completed;                      /* # of last completed gp. */
-        spinlock_t onofflock;                   /* exclude on/offline and */
-                                                /*  starting new GP. */
-        spinlock_t fqslock;                     /* Only one task forcing */
-                                                /*  quiescent states. */
-        unsigned long jiffies_force_qs;         /* Time at which to invoke */
-                                                /*  force_quiescent_state(). */
-        unsigned long n_force_qs;               /* Number of calls to */
-                                                /*  force_quiescent_state(). */
-        unsigned long n_force_qs_lh;            /* ~Number of calls leaving */
-                                                /*  due to lock unavailable. */
-        unsigned long n_force_qs_ngp;           /* Number of calls leaving */
-                                                /*  due to no GP active. */
-#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-        unsigned long gp_start;                 /* Time at which GP started, */
-                                                /*  but in jiffies. */
-        unsigned long jiffies_stall;            /* Time at which to check */
-                                                /*  for CPU stalls. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
-        long dynticks_completed;                /* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
-};
+extern int rcu_needs_cpu(int cpu);
 
-extern void rcu_qsctr_inc(int cpu);
-extern void rcu_bh_qsctr_inc(int cpu);
+#ifdef CONFIG_TREE_PREEMPT_RCU
 
-extern int rcu_pending(int cpu);
-extern int rcu_needs_cpu(int cpu);
+extern void __rcu_read_lock(void);
+extern void __rcu_read_unlock(void);
+extern void exit_rcu(void);
 
-#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, NULL, _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
+#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 static inline void __rcu_read_lock(void)
 {
         preempt_disable();
-        __acquire(RCU);
-        rcu_read_acquire();
 }
+
 static inline void __rcu_read_unlock(void)
 {
-        rcu_read_release();
-        __release(RCU);
         preempt_enable();
 }
+
+static inline void exit_rcu(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+
 static inline void __rcu_read_lock_bh(void)
 {
         local_bh_disable();
-        __acquire(RCU_BH);
-        rcu_read_acquire();
 }
 static inline void __rcu_read_unlock_bh(void)
 {
-        rcu_read_release();
-        __release(RCU_BH);
         local_bh_enable();
 }
 
 #define __synchronize_sched() synchronize_rcu()
 
-#define call_rcu_sched(head, func) call_rcu(head, func)
+extern void call_rcu_sched(struct rcu_head *head,
+                           void (*func)(struct rcu_head *rcu));
 
-static inline void rcu_init_sched(void)
+static inline void synchronize_rcu_expedited(void)
 {
+        synchronize_sched_expedited();
+}
+
+static inline void synchronize_rcu_bh_expedited(void)
+{
+        synchronize_sched_expedited();
 }
 
 extern void __rcu_init(void);
@@ -296,6 +89,11 @@ extern void rcu_restart_cpu(int cpu);
 
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
+extern long rcu_batches_completed_sched(void);
+
+static inline void rcu_init_sched(void)
+{
+}
 
 #ifdef CONFIG_NO_HZ
 void rcu_enter_nohz(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9304027673b0..379531c08975 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1163,6 +1163,8 @@ struct sched_rt_entity {
 #endif
 };
 
+struct rcu_node;
+
 struct task_struct {
         volatile long state;    /* -1 unrunnable, 0 runnable, >0 stopped */
         void *stack;
@@ -1206,10 +1208,12 @@ struct task_struct {
         unsigned int policy;
         cpumask_t cpus_allowed;
 
-#ifdef CONFIG_PREEMPT_RCU
+#ifdef CONFIG_TREE_PREEMPT_RCU
         int rcu_read_lock_nesting;
-        int rcu_flipctr_idx;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
+        char rcu_read_unlock_special;
+        struct rcu_node *rcu_blocked_node;
+        struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
         struct sched_info sched_info;
@@ -1725,6 +1729,28 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
+#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
+#define RCU_READ_UNLOCK_GOT_QS  (1 << 2) /* CPU has responded to RCU core. */
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+        p->rcu_read_lock_nesting = 0;
+        p->rcu_read_unlock_special = 0;
+        p->rcu_blocked_node = NULL;
+        INIT_LIST_HEAD(&p->rcu_node_entry);
+}
+
+#else
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+}
+
+#endif
+
 #ifdef CONFIG_SMP
 extern int set_cpus_allowed_ptr(struct task_struct *p,
                                 const struct cpumask *new_mask);