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: (31 commits)
  rcu: Make RCU's CPU-stall detector be default
  rcu: Add expedited grace-period support for preemptible RCU
  rcu: Enable fourth level of TREE_RCU hierarchy
  rcu: Rename "quiet" functions
  rcu: Re-arrange code to reduce #ifdef pain
  rcu: Eliminate unneeded function wrapping
  rcu: Fix grace-period-stall bug on large systems with CPU hotplug
  rcu: Eliminate __rcu_pending() false positives
  rcu: Further cleanups of use of lastcomp
  rcu: Simplify association of forced quiescent states with grace periods
  rcu: Accelerate callback processing on CPUs not detecting GP end
  rcu: Mark init-time-only rcu_bootup_announce() as __init
  rcu: Simplify association of quiescent states with grace periods
  rcu: Rename dynticks_completed to completed_fqs
  rcu: Enable synchronize_sched_expedited() fastpath
  rcu: Remove inline from forward-referenced functions
  rcu: Fix note_new_gpnum() uses of ->gpnum
  rcu: Fix synchronization for rcu_process_gp_end() uses of ->completed counter
  rcu: Prepare for synchronization fixes: clean up for non-NO_HZ handling of ->completed counter
  rcu: Cleanup: balance rcu_irq_enter()/rcu_irq_exit() calls
  ...

20 files changed, 1234 insertions, 581 deletions

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 187bbf10c92..8608fd85e92 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -1,185 +1,10 @@
 CONFIG_RCU_TRACE debugfs Files and Formats
 
 
-The rcupreempt and rcutree implementations of RCU provide debugfs trace
-output that summarizes counters and state.  This information is useful for
-debugging RCU itself, and can sometimes also help to debug abuses of RCU.
-Note that the rcuclassic implementation of RCU does not provide debugfs
-trace output.
-
-The following sections describe the debugfs files and formats for
-preemptable RCU (rcupreempt) and hierarchical RCU (rcutree).
-
-
-Preemptable RCU debugfs Files and Formats
-
-This implementation of RCU provides three debugfs files under the
-top-level directory RCU: rcu/rcuctrs (which displays the per-CPU
-counters used by preemptable RCU) rcu/rcugp (which displays grace-period
-counters), and rcu/rcustats (which internal counters for debugging RCU).
-
-The output of "cat rcu/rcuctrs" looks as follows:
-
-CPU last cur F M
-  0    5  -5 0 0
-  1   -1   0 0 0
-  2    0   1 0 0
-  3    0   1 0 0
-  4    0   1 0 0
-  5    0   1 0 0
-  6    0   2 0 0
-  7    0  -1 0 0
-  8    0   1 0 0
-ggp = 26226, state = waitzero
-
-The per-CPU fields are as follows:
-
-o	"CPU" gives the CPU number.  Offline CPUs are not displayed.
-
-o	"last" gives the value of the counter that is being decremented
-	for the current grace period phase.  In the example above,
-	the counters sum to 4, indicating that there are still four
-	RCU read-side critical sections still running that started
-	before the last counter flip.
-
-o	"cur" gives the value of the counter that is currently being
-	both incremented (by rcu_read_lock()) and decremented (by
-	rcu_read_unlock()).  In the example above, the counters sum to
-	1, indicating that there is only one RCU read-side critical section
-	still running that started after the last counter flip.
-
-o	"F" indicates whether RCU is waiting for this CPU to acknowledge
-	a counter flip.  In the above example, RCU is not waiting on any,
-	which is consistent with the state being "waitzero" rather than
-	"waitack".
-
-o	"M" indicates whether RCU is waiting for this CPU to execute a
-	memory barrier.  In the above example, RCU is not waiting on any,
-	which is consistent with the state being "waitzero" rather than
-	"waitmb".
-
-o	"ggp" is the global grace-period counter.
-
-o	"state" is the RCU state, which can be one of the following:
-
-	o	"idle": there is no grace period in progress.
-
-	o	"waitack": RCU just incremented the global grace-period
-		counter, which has the effect of reversing the roles of
-		the "last" and "cur" counters above, and is waiting for
-		all the CPUs to acknowledge the flip.  Once the flip has
-		been acknowledged, CPUs will no longer be incrementing
-		what are now the "last" counters, so that their sum will
-		decrease monotonically down to zero.
-
-	o	"waitzero": RCU is waiting for the sum of the "last" counters
-		to decrease to zero.
-
-	o	"waitmb": RCU is waiting for each CPU to execute a memory
-		barrier, which ensures that instructions from a given CPU's
-		last RCU read-side critical section cannot be reordered
-		with instructions following the memory-barrier instruction.
-
-The output of "cat rcu/rcugp" looks as follows:
-
-oldggp=48870  newggp=48873
-
-Note that reading from this file provokes a synchronize_rcu().  The
-"oldggp" value is that of "ggp" from rcu/rcuctrs above, taken before
-executing the synchronize_rcu(), and the "newggp" value is also the
-"ggp" value, but taken after the synchronize_rcu() command returns.
-
-
-The output of "cat rcu/rcugp" looks as follows:
-
-na=1337955 nl=40 wa=1337915 wl=44 da=1337871 dl=0 dr=1337871 di=1337871
-1=50989 e1=6138 i1=49722 ie1=82 g1=49640 a1=315203 ae1=265563 a2=49640
-z1=1401244 ze1=1351605 z2=49639 m1=5661253 me1=5611614 m2=49639
-
-These are counters tracking internal preemptable-RCU events, however,
-some of them may be useful for debugging algorithms using RCU.  In
-particular, the "nl", "wl", and "dl" values track the number of RCU
-callbacks in various states.  The fields are as follows:
-
-o	"na" is the total number of RCU callbacks that have been enqueued
-	since boot.
-
-o	"nl" is the number of RCU callbacks waiting for the previous
-	grace period to end so that they can start waiting on the next
-	grace period.
-
-o	"wa" is the total number of RCU callbacks that have started waiting
-	for a grace period since boot.  "na" should be roughly equal to
-	"nl" plus "wa".
-
-o	"wl" is the number of RCU callbacks currently waiting for their
-	grace period to end.
-
-o	"da" is the total number of RCU callbacks whose grace periods
-	have completed since boot.  "wa" should be roughly equal to
-	"wl" plus "da".
-
-o	"dr" is the total number of RCU callbacks that have been removed
-	from the list of callbacks ready to invoke.  "dr" should be roughly
-	equal to "da".
-
-o	"di" is the total number of RCU callbacks that have been invoked
-	since boot.  "di" should be roughly equal to "da", though some
-	early versions of preemptable RCU had a bug so that only the
-	last CPU's count of invocations was displayed, rather than the
-	sum of all CPU's counts.
-
-o	"1" is the number of calls to rcu_try_flip().  This should be
-	roughly equal to the sum of "e1", "i1", "a1", "z1", and "m1"
-	described below.  In other words, the number of times that
-	the state machine is visited should be equal to the sum of the
-	number of times that each state is visited plus the number of
-	times that the state-machine lock acquisition failed.
-
-o	"e1" is the number of times that rcu_try_flip() was unable to
-	acquire the fliplock.
-
-o	"i1" is the number of calls to rcu_try_flip_idle().
-
-o	"ie1" is the number of times rcu_try_flip_idle() exited early
-	due to the calling CPU having no work for RCU.
-
-o	"g1" is the number of times that rcu_try_flip_idle() decided
-	to start a new grace period.  "i1" should be roughly equal to
-	"ie1" plus "g1".
-
-o	"a1" is the number of calls to rcu_try_flip_waitack().
-
-o	"ae1" is the number of times that rcu_try_flip_waitack() found
-	that at least one CPU had not yet acknowledge the new grace period
-	(AKA "counter flip").
-
-o	"a2" is the number of time rcu_try_flip_waitack() found that
-	all CPUs had acknowledged.  "a1" should be roughly equal to
-	"ae1" plus "a2".  (This particular output was collected on
-	a 128-CPU machine, hence the smaller-than-usual fraction of
-	calls to rcu_try_flip_waitack() finding all CPUs having already
-	acknowledged.)
-
-o	"z1" is the number of calls to rcu_try_flip_waitzero().
-
-o	"ze1" is the number of times that rcu_try_flip_waitzero() found
-	that not all of the old RCU read-side critical sections had
-	completed.
-
-o	"z2" is the number of times that rcu_try_flip_waitzero() finds
-	the sum of the counters equal to zero, in other words, that
-	all of the old RCU read-side critical sections had completed.
-	The value of "z1" should be roughly equal to "ze1" plus
-	"z2".
-
-o	"m1" is the number of calls to rcu_try_flip_waitmb().
-
-o	"me1" is the number of times that rcu_try_flip_waitmb() finds
-	that at least one CPU has not yet executed a memory barrier.
-
-o	"m2" is the number of times that rcu_try_flip_waitmb() finds that
-	all CPUs have executed a memory barrier.
+The rcutree implementation of RCU provides debugfs trace output that
+summarizes counters and state.  This information is useful for debugging
+RCU itself, and can sometimes also help to debug abuses of RCU.
+The following sections describe the debugfs files and formats.
 
 
 Hierarchical RCU debugfs Files and Formats
@@ -210,9 +35,10 @@ rcu_bh:
   6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
   7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
 
-The first section lists the rcu_data structures for rcu, the second for
-rcu_bh.  Each section has one line per CPU, or eight for this 8-CPU system.
-The fields are as follows:
+The first section lists the rcu_data structures for rcu_sched, the second
+for rcu_bh.  Note that CONFIG_TREE_PREEMPT_RCU kernels will have an
+additional section for rcu_preempt.  Each section has one line per CPU,
+or eight for this 8-CPU system.  The fields are as follows:
 
 o	The number at the beginning of each line is the CPU number.
 	CPUs numbers followed by an exclamation mark are offline,
@@ -223,9 +49,9 @@ o	The number at the beginning of each line is the CPU number.
 
 o	"c" is the count of grace periods that this CPU believes have
 	completed.  CPUs in dynticks idle mode may lag quite a ways
-	behind, for example, CPU 4 under "rcu" above, which has slept
-	through the past 25 RCU grace periods.	It is not unusual to
-	see CPUs lagging by thousands of grace periods.
+	behind, for example, CPU 4 under "rcu_sched" above, which has
+	slept through the past 25 RCU grace periods.  It is not unusual
+	to see CPUs lagging by thousands of grace periods.
 
 o	"g" is the count of grace periods that this CPU believes have
 	started.  Again, CPUs in dynticks idle mode may lag behind.
@@ -308,8 +134,10 @@ The output of "cat rcu/rcugp" looks as follows:
 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
-taken from the rcu_state structure, and are as follows:
+Again, this output is for both "rcu_sched" and "rcu_bh".  Note that
+kernels built with CONFIG_TREE_PREEMPT_RCU will have an additional
+"rcu_preempt" line.  The fields are taken from the rcu_state structure,
+and are as follows:
 
 o	"completed" is the number of grace periods that have completed.
 	It is comparable to the "c" field from rcu/rcudata in that a
@@ -324,23 +152,24 @@ o	"gpnum" is the number of grace periods that have started.  It is
 	If these two fields are equal (as they are for "rcu_bh" above),
 	then there is no grace period in progress, in other words, RCU
 	is idle.  On the other hand, if the two fields differ (as they
-	do for "rcu" above), then an RCU grace period is in progress.
+	do for "rcu_sched" above), then an RCU grace period is in progress.
 
 
 The output of "cat rcu/rcuhier" looks as follows, with very long lines:
 
-c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6
-1/1 0:127 ^0    
-3/3 0:35 ^0    0/0 36:71 ^1    0/0 72:107 ^2    0/0 108:127 ^3    
-3/3f 0:5 ^0    2/3 6:11 ^1    0/0 12:17 ^2    0/0 18:23 ^3    0/0 24:29 ^4    0/0 30:35 ^5    0/0 36:41 ^0    0/0 42:47 ^1    0/0 48:53 ^2    0/0 54:59 ^3    0/0 60:65 ^4    0/0 66:71 ^5    0/0 72:77 ^0    0/0 78:83 ^1    0/0 84:89 ^2    0/0 90:95 ^3    0/0 96:101 ^4    0/0 102:107 ^5    0/0 108:113 ^0    0/0 114:119 ^1    0/0 120:125 ^2    0/0 126:127 ^3    
+c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6 oqlen=0
+1/1 .>. 0:127 ^0    
+3/3 .>. 0:35 ^0    0/0 .>. 36:71 ^1    0/0 .>. 72:107 ^2    0/0 .>. 108:127 ^3    
+3/3f .>. 0:5 ^0    2/3 .>. 6:11 ^1    0/0 .>. 12:17 ^2    0/0 .>. 18:23 ^3    0/0 .>. 24:29 ^4    0/0 .>. 30:35 ^5    0/0 .>. 36:41 ^0    0/0 .>. 42:47 ^1    0/0 .>. 48:53 ^2    0/0 .>. 54:59 ^3    0/0 .>. 60:65 ^4    0/0 .>. 66:71 ^5    0/0 .>. 72:77 ^0    0/0 .>. 78:83 ^1    0/0 .>. 84:89 ^2    0/0 .>. 90:95 ^3    0/0 .>. 96:101 ^4    0/0 .>. 102:107 ^5    0/0 .>. 108:113 ^0    0/0 .>. 114:119 ^1    0/0 .>. 120:125 ^2    0/0 .>. 126:127 ^3    
 rcu_bh:
-c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0
-0/1 0:127 ^0    
-0/3 0:35 ^0    0/0 36:71 ^1    0/0 72:107 ^2    0/0 108:127 ^3    
-0/3f 0:5 ^0    0/3 6:11 ^1    0/0 12:17 ^2    0/0 18:23 ^3    0/0 24:29 ^4    0/0 30:35 ^5    0/0 36:41 ^0    0/0 42:47 ^1    0/0 48:53 ^2    0/0 54:59 ^3    0/0 60:65 ^4    0/0 66:71 ^5    0/0 72:77 ^0    0/0 78:83 ^1    0/0 84:89 ^2    0/0 90:95 ^3    0/0 96:101 ^4    0/0 102:107 ^5    0/0 108:113 ^0    0/0 114:119 ^1    0/0 120:125 ^2    0/0 126:127 ^3
+c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0 oqlen=0
+0/1 .>. 0:127 ^0    
+0/3 .>. 0:35 ^0    0/0 .>. 36:71 ^1    0/0 .>. 72:107 ^2    0/0 .>. 108:127 ^3    
+0/3f .>. 0:5 ^0    0/3 .>. 6:11 ^1    0/0 .>. 12:17 ^2    0/0 .>. 18:23 ^3    0/0 .>. 24:29 ^4    0/0 .>. 30:35 ^5    0/0 .>. 36:41 ^0    0/0 .>. 42:47 ^1    0/0 .>. 48:53 ^2    0/0 .>. 54:59 ^3    0/0 .>. 60:65 ^4    0/0 .>. 66:71 ^5    0/0 .>. 72:77 ^0    0/0 .>. 78:83 ^1    0/0 .>. 84:89 ^2    0/0 .>. 90:95 ^3    0/0 .>. 96:101 ^4    0/0 .>. 102:107 ^5    0/0 .>. 108:113 ^0    0/0 .>. 114:119 ^1    0/0 .>. 120:125 ^2    0/0 .>. 126:127 ^3
 
-This is once again split into "rcu" and "rcu_bh" portions.  The fields are
-as follows:
+This is once again split into "rcu_sched" and "rcu_bh" portions,
+and CONFIG_TREE_PREEMPT_RCU kernels will again have an additional
+"rcu_preempt" section.  The fields are as follows:
 
 o	"c" is exactly the same as "completed" under rcu/rcugp.
 
@@ -372,6 +201,11 @@ o	"fqlh" is the number of calls to force_quiescent_state() that
 	exited immediately (without even being counted in nfqs above)
 	due to contention on ->fqslock.
 
+o	"oqlen" is the number of callbacks on the "orphan" callback
+	list.  RCU callbacks are placed on this list by CPUs going
+	offline, and are "adopted" either by the CPU helping the outgoing
+	CPU or by the next rcu_barrier*() call, whichever comes first.
+
 o	Each element of the form "1/1 0:127 ^0" represents one struct
 	rcu_node.  Each line represents one level of the hierarchy, from
 	root to leaves.  It is best to think of the rcu_data structures
@@ -379,7 +213,7 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 	might be either one, two, or three levels of rcu_node structures,
 	depending on the relationship between CONFIG_RCU_FANOUT and
 	CONFIG_NR_CPUS.
-	
+
 	o	The numbers separated by the "/" are the qsmask followed
 		by the qsmaskinit.  The qsmask will have one bit
 		set for each entity in the next lower level that
@@ -389,10 +223,19 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 		The value of qsmaskinit is assigned to that of qsmask
 		at the beginning of each grace period.
 
-		For example, for "rcu", the qsmask of the first entry
-		of the lowest level is 0x14, meaning that we are still
-		waiting for CPUs 2 and 4 to check in for the current
-		grace period.
+		For example, for "rcu_sched", the qsmask of the first
+		entry of the lowest level is 0x14, meaning that we
+		are still waiting for CPUs 2 and 4 to check in for the
+		current grace period.
+
+	o	The characters separated by the ">" indicate the state
+		of the blocked-tasks lists.  A "T" preceding the ">"
+		indicates that at least one task blocked in an RCU
+		read-side critical section blocks the current grace
+		period, while a "." preceding the ">" indicates otherwise.
+		The character following the ">" indicates similarly for
+		the next grace period.  A "T" should appear in this
+		field only for rcu-preempt.
 
 	o	The numbers separated by the ":" are the range of CPUs
 		served by this struct rcu_node.  This can be helpful
@@ -431,8 +274,9 @@ rcu_bh:
   6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
   7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
 
-As always, this is once again split into "rcu" and "rcu_bh" portions.
-The fields are as follows:
+As always, this is once again split into "rcu_sched" and "rcu_bh"
+portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
+"rcu_preempt" section.  The fields are as follows:
 
 o	"np" is the number of times that __rcu_pending() has been invoked
 	for the corresponding flavor of RCU.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e41a7fecf0d..d542ca243b8 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -830,7 +830,7 @@ sched:	Critical sections	Grace period		Barrier
 SRCU:	Critical sections	Grace period		Barrier
 
 	srcu_read_lock		synchronize_srcu	N/A
-	srcu_read_unlock
+	srcu_read_unlock	synchronize_srcu_expedited
 
 SRCU:	Initialization/cleanup
 	init_srcu_struct
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 6d527ee82b2..d5b387669da 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -139,10 +139,34 @@ static inline void account_system_vtime(struct task_struct *tsk)
 #endif
 
 #if defined(CONFIG_NO_HZ)
+#if defined(CONFIG_TINY_RCU)
+extern void rcu_enter_nohz(void);
+extern void rcu_exit_nohz(void);
+
+static inline void rcu_irq_enter(void)
+{
+	rcu_exit_nohz();
+}
+
+static inline void rcu_irq_exit(void)
+{
+	rcu_enter_nohz();
+}
+
+static inline void rcu_nmi_enter(void)
+{
+}
+
+static inline void rcu_nmi_exit(void)
+{
+}
+
+#else
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
 extern void rcu_nmi_enter(void);
 extern void rcu_nmi_exit(void);
+#endif
 #else
 # define rcu_irq_enter() do { } while (0)
 # define rcu_irq_exit() do { } while (0)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3ebd0b7bcb0..24440f4bf47 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -52,11 +52,6 @@ struct rcu_head {
 };
 
 /* Exported common interfaces */
-#ifdef CONFIG_TREE_PREEMPT_RCU
-extern void synchronize_rcu(void);
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#define synchronize_rcu synchronize_sched
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 extern void synchronize_rcu_bh(void);
 extern void synchronize_sched(void);
 extern void rcu_barrier(void);
@@ -67,12 +62,11 @@ 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_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
+#elif defined(CONFIG_TINY_RCU)
+#include <linux/rcutiny.h>
 #else
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
new file mode 100644
index 00000000000..c4ba9a78721
--- /dev/null
+++ b/include/linux/rcutiny.h
@@ -0,0 +1,104 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
+ *
+ * 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, 2008
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ *		Documentation/RCU
+ */
+#ifndef __LINUX_TINY_H
+#define __LINUX_TINY_H
+
+#include <linux/cache.h>
+
+void rcu_sched_qs(int cpu);
+void rcu_bh_qs(int cpu);
+
+#define __rcu_read_lock()	preempt_disable()
+#define __rcu_read_unlock()	preempt_enable()
+#define __rcu_read_lock_bh()	local_bh_disable()
+#define __rcu_read_unlock_bh()	local_bh_enable()
+#define call_rcu_sched		call_rcu
+
+#define rcu_init_sched()	do { } while (0)
+extern void rcu_check_callbacks(int cpu, int user);
+
+static inline int rcu_needs_cpu(int cpu)
+{
+	return 0;
+}
+
+/*
+ * Return the number of grace periods.
+ */
+static inline long rcu_batches_completed(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of bottom-half grace periods.
+ */
+static inline long rcu_batches_completed_bh(void)
+{
+	return 0;
+}
+
+extern int rcu_expedited_torture_stats(char *page);
+
+#define synchronize_rcu synchronize_sched
+
+static inline void synchronize_rcu_expedited(void)
+{
+	synchronize_sched();
+}
+
+static inline void synchronize_rcu_bh_expedited(void)
+{
+	synchronize_sched();
+}
+
+struct notifier_block;
+
+#ifdef CONFIG_NO_HZ
+
+extern void rcu_enter_nohz(void);
+extern void rcu_exit_nohz(void);
+
+#else /* #ifdef CONFIG_NO_HZ */
+
+static inline void rcu_enter_nohz(void)
+{
+}
+
+static inline void rcu_exit_nohz(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ */
+
+static inline void rcu_scheduler_starting(void)
+{
+}
+
+static inline void exit_rcu(void)
+{
+}
+
+#endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 9642c6bcb39..c93eee5911b 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -34,15 +34,15 @@ struct notifier_block;
 
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
-extern int rcu_cpu_notify(struct notifier_block *self,
-			  unsigned long action, void *hcpu);
 extern int rcu_needs_cpu(int cpu);
+extern void rcu_scheduler_starting(void);
 extern int rcu_expedited_torture_stats(char *page);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 extern void __rcu_read_lock(void);
 extern void __rcu_read_unlock(void);
+extern void synchronize_rcu(void);
 extern void exit_rcu(void);
 
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
@@ -57,7 +57,7 @@ static inline void __rcu_read_unlock(void)
 	preempt_enable();
 }
 
-#define __synchronize_sched() synchronize_rcu()
+#define synchronize_rcu synchronize_sched
 
 static inline void exit_rcu(void)
 {
@@ -83,7 +83,6 @@ static inline void synchronize_rcu_bh_expedited(void)
 	synchronize_sched_expedited();
 }
 
-extern void __rcu_init(void);
 extern void rcu_check_callbacks(int cpu, int user);
 
 extern long rcu_batches_completed(void);
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index aca0eee5393..4765d97dcaf 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -48,6 +48,7 @@ void cleanup_srcu_struct(struct srcu_struct *sp);
 int srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
+void synchronize_srcu_expedited(struct srcu_struct *sp);
 long srcu_batches_completed(struct srcu_struct *sp);
 
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index 2e9a1457132..9ee77829475 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -334,6 +334,15 @@ config TREE_PREEMPT_RCU
 	  is also required.  It also scales down nicely to
 	  smaller systems.
 
+config TINY_RCU
+	bool "UP-only small-memory-footprint RCU"
+	depends on !SMP
+	help
+	  This option selects the RCU implementation that is
+	  designed for UP systems from which real-time response
+	  is not required.  This option greatly reduces the
+	  memory footprint of RCU.
+
 endchoice
 
 config RCU_TRACE
diff --git a/kernel/Makefile b/kernel/Makefile
index d7c13d249b2..dcf6789bf54 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_TINY_RCU) += rcutiny.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 400183346ad..9b7fd472387 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,7 +44,6 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <linux/kernel_stat.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
@@ -53,8 +52,6 @@ struct lockdep_map rcu_lock_map =
 EXPORT_SYMBOL_GPL(rcu_lock_map);
 #endif
 
-int rcu_scheduler_active __read_mostly;
-
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
@@ -66,122 +63,3 @@ void wakeme_after_rcu(struct rcu_head  *head)
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
-
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-/**
- * synchronize_rcu - wait until a grace period has elapsed.
- *
- * Control will return to the caller some time after a full grace
- * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-void synchronize_rcu(void)
-{
-	struct rcu_synchronize rcu;
-
-	if (!rcu_scheduler_active)
-		return;
-
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	call_rcu(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
-
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-/**
- * synchronize_sched - wait until an rcu-sched grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-sched
- * grace period has elapsed, in other words after all currently executing
- * rcu-sched read-side critical sections have completed.   These read-side
- * critical sections are delimited by rcu_read_lock_sched() and
- * rcu_read_unlock_sched(), and may be nested.  Note that preempt_disable(),
- * local_irq_disable(), and so on may be used in place of
- * rcu_read_lock_sched().
- *
- * This means that all preempt_disable code sequences, including NMI and
- * hardware-interrupt handlers, in progress on entry will have completed
- * before this primitive returns.  However, this does not guarantee that
- * softirq handlers will have completed, since in some kernels, these
- * handlers can run in process context, and can block.
- *
- * This primitive provides the guarantees made by the (now removed)
- * synchronize_kernel() API.  In contrast, synchronize_rcu() only
- * guarantees that rcu_read_lock() sections will have completed.
- * In "classic RCU", these two guarantees happen to be one and
- * the same, but can differ in realtime RCU implementations.
- */
-void synchronize_sched(void)
-{
-	struct rcu_synchronize rcu;
-
-	if (rcu_blocking_is_gp())
-		return;
-
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	call_rcu_sched(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_sched);
-
-/**
- * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu_bh grace
- * period has elapsed, in other words after all currently executing rcu_bh
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(),
- * and may be nested.
- */
-void synchronize_rcu_bh(void)
-{
-	struct rcu_synchronize rcu;
-
-	if (rcu_blocking_is_gp())
-		return;
-
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	call_rcu_bh(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
-
-static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
-		unsigned long action, void *hcpu)
-{
-	return rcu_cpu_notify(self, action, hcpu);
-}
-
-void __init rcu_init(void)
-{
-	int i;
-
-	__rcu_init();
-	cpu_notifier(rcu_barrier_cpu_hotplug, 0);
-
-	/*
-	 * We don't need protection against CPU-hotplug here because
-	 * this is called early in boot, before either interrupts
-	 * or the scheduler are operational.
-	 */
-	for_each_online_cpu(i)
-		rcu_barrier_cpu_hotplug(NULL, CPU_UP_PREPARE, (void *)(long)i);
-}
-
-void rcu_scheduler_starting(void)
-{
-	WARN_ON(num_online_cpus() != 1);
-	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
-}
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
new file mode 100644
index 00000000000..9f6d9ff2572
--- /dev/null
+++ b/kernel/rcutiny.c
@@ -0,0 +1,282 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
+ *
+ * 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, 2008
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ *		Documentation/RCU
+ */
+#include <linux/moduleparam.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/cpu.h>
+
+/* Global control variables for rcupdate callback mechanism. */
+struct rcu_ctrlblk {
+	struct rcu_head *rcucblist;	/* List of pending callbacks (CBs). */
+	struct rcu_head **donetail;	/* ->next pointer of last "done" CB. */
+	struct rcu_head **curtail;	/* ->next pointer of last CB. */
+};
+
+/* Definition for rcupdate control block. */
+static struct rcu_ctrlblk rcu_ctrlblk = {
+	.donetail	= &rcu_ctrlblk.rcucblist,
+	.curtail	= &rcu_ctrlblk.rcucblist,
+};
+
+static struct rcu_ctrlblk rcu_bh_ctrlblk = {
+	.donetail	= &rcu_bh_ctrlblk.rcucblist,
+	.curtail	= &rcu_bh_ctrlblk.rcucblist,
+};
+
+#ifdef CONFIG_NO_HZ
+
+static long rcu_dynticks_nesting = 1;
+
+/*
+ * Enter dynticks-idle mode, which is an extended quiescent state
+ * if we have fully entered that mode (i.e., if the new value of
+ * dynticks_nesting is zero).
+ */
+void rcu_enter_nohz(void)
+{
+	if (--rcu_dynticks_nesting == 0)
+		rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+}
+
+/*