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
  ...

Documentation/RCU/RTFP.txt

@@ -743,3 +743,80 @@ Revised:
 	RCU, realtime RCU, sleepable RCU, performance.
 "
 }
+
+@article{PaulEMcKenney2008RCUOSR
+,author="Paul E. McKenney and Jonathan Walpole"
+,title="Introducing technology into the {Linux} kernel: a case study"
+,Year="2008"
+,journal="SIGOPS Oper. Syst. Rev."
+,volume="42"
+,number="5"
+,pages="4--17"
+,issn="0163-5980"
+,doi={http://doi.acm.org/10.1145/1400097.1400099}
+,publisher="ACM"
+,address="New York, NY, USA"
+,annotation={
+	Linux changed RCU to a far greater degree than RCU has changed Linux.
+}
+}
+
+@unpublished{PaulEMcKenney2008HierarchicalRCU
+,Author="Paul E. McKenney"
+,Title="Hierarchical {RCU}"
+,month="November"
+,day="3"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/305782/}
+[Viewed November 6, 2008]"
+,annotation="
+	RCU with combining-tree-based grace-period detection,
+	permitting it to handle thousands of CPUs.
+"
+}
+
+@conference{PaulEMcKenney2009MaliciousURCU
+,Author="Paul E. McKenney"
+,Title="Using a Malicious User-Level {RCU} to Torture {RCU}-Based Algorithms"
+,Booktitle="linux.conf.au 2009"
+,month="January"
+,year="2009"
+,address="Hobart, Australia"
+,note="Available:
+\url{http://www.rdrop.com/users/paulmck/RCU/urcutorture.2009.01.22a.pdf}
+[Viewed February 2, 2009]"
+,annotation="
+	Realtime RCU and torture-testing RCU uses.
+"
+}
+
+@unpublished{MathieuDesnoyers2009URCU
+,Author="Mathieu Desnoyers"
+,Title="[{RFC} git tree] Userspace {RCU} (urcu) for {Linux}"
+,month="February"
+,day="5"
+,year="2009"
+,note="Available:
+\url{http://lkml.org/lkml/2009/2/5/572}
+\url{git://lttng.org/userspace-rcu.git}
+[Viewed February 20, 2009]"
+,annotation="
+	Mathieu Desnoyers's user-space RCU implementation.
+	git://lttng.org/userspace-rcu.git
+"
+}
+
+@unpublished{PaulEMcKenney2009BloatWatchRCU
+,Author="Paul E. McKenney"
+,Title="{RCU}: The {Bloatwatch} Edition"
+,month="March"
+,day="17"
+,year="2009"
+,note="Available:
+\url{http://lwn.net/Articles/323929/}
+[Viewed March 20, 2009]"
+,annotation="
+	Uniprocessor assumptions allow simplified RCU implementation.
+"
+}

Documentation/RCU/UP.txt

@@ -2,14 +2,13 @@ RCU on Uniprocessor Systems
 
 
 A common misconception is that, on UP systems, the call_rcu() primitive
-may immediately invoke its function, and that the synchronize_rcu()
-primitive may return immediately.  The basis of this misconception
+may immediately invoke its function.  The basis of this misconception
 is that since there is only one CPU, it should not be necessary to
 wait for anything else to get done, since there are no other CPUs for
 anything else to be happening on.  Although this approach will -sort- -of-
 work a surprising amount of the time, it is a very bad idea in general.
-This document presents three examples that demonstrate exactly how bad an
-idea this is.
+This document presents three examples that demonstrate exactly how bad
+an idea this is.
 
 
 Example 1: softirq Suicide
@@ -82,11 +81,18 @@ Quick Quiz #2: What locking restriction must RCU callbacks respect?
 
 Summary
 
-Permitting call_rcu() to immediately invoke its arguments or permitting
-synchronize_rcu() to immediately return breaks RCU, even on a UP system.
-So do not do it!  Even on a UP system, the RCU infrastructure -must-
-respect grace periods, and -must- invoke callbacks from a known environment
-in which no locks are held.
+Permitting call_rcu() to immediately invoke its arguments breaks RCU,
+even on a UP system.  So do not do it!  Even on a UP system, the RCU
+infrastructure -must- respect grace periods, and -must- invoke callbacks
+from a known environment in which no locks are held.
+
+It -is- safe for synchronize_sched() and synchronize_rcu_bh() to return
+immediately on an UP system.  It is also safe for synchronize_rcu()
+to return immediately on UP systems, except when running preemptable
+RCU.
+
+Quick Quiz #3: Why can't synchronize_rcu() return immediately on
+	UP systems running preemptable RCU?
 
 
 Answer to Quick Quiz #1:
@@ -117,3 +123,13 @@ Answer to Quick Quiz #2:
 	callbacks acquire locks directly.  However, a great many RCU
 	callbacks do acquire locks -indirectly-, for example, via
 	the kfree() primitive.
+
+Answer to Quick Quiz #3:
+	Why can't synchronize_rcu() return immediately on UP systems
+	running preemptable RCU?
+
+	Because some other task might have been preempted in the middle
+	of an RCU read-side critical section.  If synchronize_rcu()
+	simply immediately returned, it would prematurely signal the
+	end of the grace period, which would come as a nasty shock to
+	that other thread when it started running again.

Documentation/RCU/checklist.txt

@@ -11,7 +11,10 @@ over a rather long period of time, but improvements are always welcome!
 	structure is updated more than about 10% of the time, then
 	you should strongly consider some other approach, unless
 	detailed performance measurements show that RCU is nonetheless
-	the right tool for the job.
+	the right tool for the job.  Yes, you might think of RCU
+	as simply cutting overhead off of the readers and imposing it
+	on the writers.  That is exactly why normal uses of RCU will
+	do much more reading than updating.
 
 	Another exception is where performance is not an issue, and RCU
 	provides a simpler implementation.  An example of this situation
@@ -240,10 +243,11 @@ over a rather long period of time, but improvements are always welcome!
 	instead need to use synchronize_irq() or synchronize_sched().
 
 12.	Any lock acquired by an RCU callback must be acquired elsewhere
-	with irq disabled, e.g., via spin_lock_irqsave().  Failing to
-	disable irq on a given acquisition of that lock will result in
-	deadlock as soon as the RCU callback happens to interrupt that
-	acquisition's critical section.
+	with softirq disabled, e.g., via spin_lock_irqsave(),
+	spin_lock_bh(), etc.  Failing to disable irq on a given
+	acquisition of that lock will result in deadlock as soon as the
+	RCU callback happens to interrupt that acquisition's critical
+	section.
 
 13.	RCU callbacks can be and are executed in parallel.  In many cases,
 	the callback code simply wrappers around kfree(), so that this
@@ -310,3 +314,9 @@ over a rather long period of time, but improvements are always welcome!
 	Because these primitives only wait for pre-existing readers,
 	it is the caller's responsibility to guarantee safety to
 	any subsequent readers.
+
+16.	The various RCU read-side primitives do -not- contain memory
+	barriers.  The CPU (and in some cases, the compiler) is free
+	to reorder code into and out of RCU read-side critical sections.
+	It is the responsibility of the RCU update-side primitives to
+	deal with this.

Documentation/RCU/rcu.txt

@@ -36,7 +36,7 @@ o	How can the updater tell when a grace period has completed
 	executed in user mode, or executed in the idle loop, we can
 	safely free up that item.
 
-	Preemptible variants of RCU (CONFIG_PREEMPT_RCU) get the
+	Preemptible variants of RCU (CONFIG_TREE_PREEMPT_RCU) get the
 	same effect, but require that the readers manipulate CPU-local
 	counters.  These counters allow limited types of blocking
 	within RCU read-side critical sections.  SRCU also uses
@@ -79,10 +79,10 @@ o	I hear that RCU is patented?  What is with that?
 o	I hear that RCU needs work in order to support realtime kernels?
 
 	This work is largely completed.  Realtime-friendly RCU can be
-	enabled via the CONFIG_PREEMPT_RCU kernel configuration parameter.
-	However, work is in progress for enabling priority boosting of
-	preempted RCU read-side critical sections.  This is needed if you
-	have CPU-bound realtime threads.
+	enabled via the CONFIG_TREE_PREEMPT_RCU kernel configuration
+	parameter.  However, work is in progress for enabling priority
+	boosting of preempted RCU read-side critical sections.	This is
+	needed if you have CPU-bound realtime threads.
 
 o	Where can I find more information on RCU?
 

Documentation/RCU/rcubarrier.txt

@@ -170,6 +170,13 @@ module invokes call_rcu() from timers, you will need to first cancel all
 the timers, and only then invoke rcu_barrier() to wait for any remaining
 RCU callbacks to complete.
 
+Of course, if you module uses call_rcu_bh(), you will need to invoke
+rcu_barrier_bh() before unloading.  Similarly, if your module uses
+call_rcu_sched(), you will need to invoke rcu_barrier_sched() before
+unloading.  If your module uses call_rcu(), call_rcu_bh(), -and-
+call_rcu_sched(), then you will need to invoke each of rcu_barrier(),
+rcu_barrier_bh(), and rcu_barrier_sched().
+
 
 Implementing rcu_barrier()
 

Documentation/RCU/torture.txt

@@ -76,8 +76,10 @@ torture_type	The type of RCU to test: "rcu" for the rcu_read_lock() API,
 		"rcu_sync" for rcu_read_lock() with synchronous reclamation,
 		"rcu_bh" for the rcu_read_lock_bh() API, "rcu_bh_sync" for
 		rcu_read_lock_bh() with synchronous reclamation, "srcu" for
-		the "srcu_read_lock()" API, and "sched" for the use of
-		preempt_disable() together with synchronize_sched().
+		the "srcu_read_lock()" API, "sched" for the use of
+		preempt_disable() together with synchronize_sched(),
+		and "sched_expedited" for the use of preempt_disable()
+		with synchronize_sched_expedited().
 
 verbose		Enable debug printk()s.  Default is disabled.
 
@@ -162,6 +164,23 @@ of the "old" and "current" counters for the corresponding CPU.  The
 "idx" value maps the "old" and "current" values to the underlying array,
 and is useful for debugging.
 
+Similarly, sched_expedited RCU provides the following:
+
+	sched_expedited-torture: rtc: d0000000016c1880 ver: 1090796 tfle: 0 rta: 1090796 rtaf: 0 rtf: 1090787 rtmbe: 0 nt: 27713319
+	sched_expedited-torture: Reader Pipe:  12660320201 95875 0 0 0 0 0 0 0 0 0
+	sched_expedited-torture: Reader Batch:  12660424885 0 0 0 0 0 0 0 0 0 0
+	sched_expedited-torture: Free-Block Circulation:  1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
+	state: -1 / 0:0 3:0 4:0
+
+As before, the first four lines are similar to those for RCU.
+The last line shows the task-migration state.  The first number is
+-1 if synchronize_sched_expedited() is idle, -2 if in the process of
+posting wakeups to the migration kthreads, and N when waiting on CPU N.
+Each of the colon-separated fields following the "/" is a CPU:state pair.
+Valid states are "0" for idle, "1" for waiting for quiescent state,
+"2" for passed through quiescent state, and "3" when a race with a
+CPU-hotplug event forces use of the synchronize_sched() primitive.
+
 
 USAGE
 

Documentation/RCU/trace.txt

@@ -191,8 +191,7 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy).
 
 The output of "cat rcu/rcudata" looks as follows:
 
-rcu:
-rcu:
+rcu_sched:
   0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
   1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
   2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
@@ -306,7 +305,7 @@ comma-separated-variable spreadsheet format.
 
 The output of "cat rcu/rcugp" looks as follows:
 
-rcu: completed=33062  gpnum=33063
+rcu_sched: completed=33062  gpnum=33063
 rcu_bh: completed=464  gpnum=464
 
 Again, this output is for both "rcu" and "rcu_bh".  The fields are
@@ -413,7 +412,7 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 
 The output of "cat rcu/rcu_pending" looks as follows:
 
-rcu:
+rcu_sched:
   0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
   1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
   2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629

Documentation/RCU/whatisRCU.txt

@@ -136,10 +136,10 @@ rcu_read_lock()
 	Used by a reader to inform the reclaimer that the reader is
 	entering an RCU read-side critical section.  It is illegal
 	to block while in an RCU read-side critical section, though
-	kernels built with CONFIG_PREEMPT_RCU can preempt RCU read-side
-	critical sections.  Any RCU-protected data structure accessed
-	during an RCU read-side critical section is guaranteed to remain
-	unreclaimed for the full duration of that critical section.
+	kernels built with CONFIG_TREE_PREEMPT_RCU can preempt RCU
+	read-side critical sections.  Any RCU-protected data structure
+	accessed during an RCU read-side critical section is guaranteed to
+	remain unreclaimed for the full duration of that critical section.
 	Reference counts may be used in conjunction with RCU to maintain
 	longer-term references to data structures.
 
@@ -785,6 +785,7 @@ RCU pointer/list traversal:
 	rcu_dereference
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
+	hlist_nulls_for_each_entry_rcu
 
 	list_for_each_continue_rcu	(to be deprecated in favor of new
 					 list_for_each_entry_continue_rcu)
@@ -807,19 +808,23 @@ RCU:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock		synchronize_net		rcu_barrier
 	rcu_read_unlock		synchronize_rcu
+				synchronize_rcu_expedited
 				call_rcu
 
 
 bh:	Critical sections	Grace period		Barrier
 
 	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
-	rcu_read_unlock_bh
+	rcu_read_unlock_bh	synchronize_rcu_bh
+				synchronize_rcu_bh_expedited
 
 
 sched:	Critical sections	Grace period		Barrier
 
-	[preempt_disable]	synchronize_sched	rcu_barrier_sched
-	[and friends]		call_rcu_sched
+	rcu_read_lock_sched	synchronize_sched	rcu_barrier_sched
+	rcu_read_unlock_sched	call_rcu_sched
+	[preempt_disable]	synchronize_sched_expedited
+	[and friends]
 
 
 SRCU:	Critical sections	Grace period		Barrier
@@ -827,6 +832,9 @@ SRCU:	Critical sections	Grace period		Barrier
 	srcu_read_lock		synchronize_srcu	N/A
 	srcu_read_unlock
 
+SRCU:	Initialization/cleanup
+	init_srcu_struct
+	cleanup_srcu_struct
 
 See the comment headers in the source code (or the docbook generated
 from them) for more information.

arch/ia64/xen/time.c

@@ -133,8 +133,7 @@ consider_steal_time(unsigned long new_itm)
 		account_idle_ticks(blocked);
 		run_local_timers();
 
-		if (rcu_pending(cpu))
-			rcu_check_callbacks(cpu, user_mode(get_irq_regs()));
+		rcu_check_callbacks(cpu, user_mode(get_irq_regs()));
 
 		scheduler_tick();
 		run_posix_cpu_timers(p);

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);

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,

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)					\
 }
 
 

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

include/linux/rcuclassic.h

@@ -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 */

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 */

include/linux/rcupreempt.h

@@ -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 */

include/linux/rcupreempt_trace.h

@@ -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 */

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 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
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+extern void __rcu_read_lock(void);
+extern void __rcu_read_unlock(void);
+extern void exit_rcu(void);
+
+#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);

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);

init/Kconfig

@@ -316,38 +316,28 @@ choice
 	prompt "RCU Implementation"
 	default TREE_RCU
 
-config CLASSIC_RCU
-	bool "Classic RCU"
-	help
-	  This option selects the classic RCU implementation that is
-	  designed for best read-side performance on non-realtime
-	  systems.
-
-	  Select this option if you are unsure.
-
 config TREE_RCU
 	bool "Tree-based hierarchical RCU"
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
-	  thousands of CPUs.
+	  thousands of CPUs.  It also scales down nicely to
+	  smaller systems.
 
-config PREEMPT_RCU
-	bool "Preemptible RCU"
+config TREE_PREEMPT_RCU
+	bool "Preemptable tree-based hierarchical RCU"
 	depends on PREEMPT
 	help
-	  This option reduces the latency of the kernel by making certain
-	  RCU sections preemptible. Normally RCU code is non-preemptible, if
-	  this option is selected then read-only RCU sections become
-	  preemptible. This helps latency, but may expose bugs due to
-	  now-naive assumptions about each RCU read-side critical section
-	  remaining on a given CPU through its execution.
+	  This option selects the RCU implementation that is
+	  designed for very large SMP systems with hundreds or
+	  thousands of CPUs, but for which real-time response
+	  is also required.
 
 endchoice
 
 config RCU_TRACE
 	bool "Enable tracing for RCU"
-	depends on TREE_RCU || PREEMPT_RCU
+	depends on TREE_RCU || TREE_PREEMPT_RCU
 	help
 	  This option provides tracing in RCU which presents stats
 	  in debugfs for debugging RCU implementation.
@@ -359,7 +349,7 @@ config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
 	range 2 32 if !64BIT
-	depends on TREE_RCU
+	depends on TREE_RCU || TREE_PREEMPT_RCU
 	default 64 if 64BIT
 	default 32 if !64BIT
 	help
@@ -374,7 +364,7 @@ config RCU_FANOUT
 
 config RCU_FANOUT_EXACT
 	bool "Disable tree-based hierarchical RCU auto-balancing"
-	depends on TREE_RCU
+	depends on TREE_RCU || TREE_PREEMPT_RCU
 	default n
 	help
 	  This option forces use of the exact RCU_FANOUT value specified,
@@ -387,18 +377,12 @@ config RCU_FANOUT_EXACT
 	  Say N if unsure.
 
 config TREE_RCU_TRACE
-	def_bool RCU_TRACE && TREE_RCU
+	def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
 	select DEBUG_FS
 	help
-	  This option provides tracing for the TREE_RCU implementation,
-	  permitting Makefile to trivially select kernel/rcutree_trace.c.
-
-config PREEMPT_RCU_TRACE
-	def_bool RCU_TRACE && PREEMPT_RCU
-	select DEBUG_FS
-	help
-	  This option provides tracing for the PREEMPT_RCU implementation,
-	  permitting Makefile to trivially select kernel/rcupreempt_trace.c.
+	  This option provides tracing for the TREE_RCU and
+	  TREE_PREEMPT_RCU implementations, permitting Makefile to
+	  trivially select kernel/rcutree_trace.c.
 
 endmenu # "RCU Subsystem"