Merge commit 'sched/auto-sched-next'

Conflicts:

	kernel/Makefile
	kernel/sched_rt.c

50 files changed, 2021 insertions, 817 deletions

diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index c64158ecde43..a6d32e65d222 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@@ -93,6 +93,9 @@ Since NMI handlers disable preemption, synchronize_sched() is guaranteed
 not to return until all ongoing NMI handlers exit.  It is therefore safe
 to free up the handler's data as soon as synchronize_sched() returns.
 
+Important note: for this to work, the architecture in question must
+invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
+
 
 Answer to Quick Quiz
 
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 39ad8f56783a..9f711d2df91b 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -52,6 +52,10 @@ of each iteration.  Unfortunately, chaotic relaxation requires highly
 structured data, such as the matrices used in scientific programs, and
 is thus inapplicable to most data structures in operating-system kernels.
 
+In 1992, Henry (now Alexia) Massalin completed a dissertation advising
+parallel programmers to defer processing when feasible to simplify
+synchronization.  RCU makes extremely heavy use of this advice.
+
 In 1993, Jacobson [Jacobson93] verbally described what is perhaps the
 simplest deferred-free technique: simply waiting a fixed amount of time
 before freeing blocks awaiting deferred free.  Jacobson did not describe
@@ -138,6 +142,13 @@ blocking in read-side critical sections appeared [PaulEMcKenney2006c],
 Robert Olsson described an RCU-protected trie-hash combination
 [RobertOlsson2006a].
 
+2007 saw the journal version of the award-winning RCU paper from 2006
+[ThomasEHart2007a], as well as a paper demonstrating use of Promela
+and Spin to mechanically verify an optimization to Oleg Nesterov's
+QRCU [PaulEMcKenney2007QRCUspin], a design document describing
+preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
+LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
+PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
 
 Bibtex Entries
 
@@ -202,6 +213,20 @@ Bibtex Entries
 ,Year="1991"
 }
 
+@phdthesis{HMassalinPhD
+,author="H. Massalin"
+,title="Synthesis: An Efficient Implementation of Fundamental Operating
+System Services"
+,school="Columbia University"
+,address="New York, NY"
+,year="1992"
+,annotation="
+	Mondo optimizing compiler.
+	Wait-free stuff.
+	Good advice: defer work to avoid synchronization.
+"
+}
+
 @unpublished{Jacobson93
 ,author="Van Jacobson"
 ,title="Avoid Read-Side Locking Via Delayed Free"
@@ -635,3 +660,86 @@ Revised:
 "
 }
 
+@unpublished{PaulEMcKenney2007PreemptibleRCU
+,Author="Paul E. McKenney"
+,Title="The design of preemptible read-copy-update"
+,month="October"
+,day="8"
+,year="2007"
+,note="Available:
+\url{http://lwn.net/Articles/253651/}
+[Viewed October 25, 2007]"
+,annotation="
+	LWN article describing the design of preemptible RCU.
+"
+}
+
+########################################################################
+#
+#	"What is RCU?" LWN series.
+#
+
+@unpublished{PaulEMcKenney2007WhatIsRCUFundamentally
+,Author="Paul E. McKenney and Jonathan Walpole"
+,Title="What is {RCU}, Fundamentally?"
+,month="December"
+,day="17"
+,year="2007"
+,note="Available:
+\url{http://lwn.net/Articles/262464/}
+[Viewed December 27, 2007]"
+,annotation="
+	Lays out the three basic components of RCU: (1) publish-subscribe,
+	(2) wait for pre-existing readers to complete, and (2) maintain
+	multiple versions.
+"
+}
+
+@unpublished{PaulEMcKenney2008WhatIsRCUUsage
+,Author="Paul E. McKenney"
+,Title="What is {RCU}? Part 2: Usage"
+,month="January"
+,day="4"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/263130/}
+[Viewed January 4, 2008]"
+,annotation="
+	Lays out six uses of RCU:
+	1. RCU is a Reader-Writer Lock Replacement
+	2. RCU is a Restricted Reference-Counting Mechanism
+	3. RCU is a Bulk Reference-Counting Mechanism
+	4. RCU is a Poor Man's Garbage Collector
+	5. RCU is a Way of Providing Existence Guarantees
+	6. RCU is a Way of Waiting for Things to Finish 
+"
+}
+
+@unpublished{PaulEMcKenney2008WhatIsRCUAPI
+,Author="Paul E. McKenney"
+,Title="{RCU} part 3: the {RCU} {API}"
+,month="January"
+,day="17"
+,year="2008"
+,note="Available:
+\url{http://lwn.net/Articles/264090/}
+[Viewed January 10, 2008]"
+,annotation="
+	Gives an overview of the Linux-kernel RCU API and a brief annotated RCU
+	bibliography.
+"
+}
+
+@article{DinakarGuniguntala2008IBMSysJ
+,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
+,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
+,Year="2008"
+,Month="April"
+,journal="IBM Systems Journal"
+,volume="47"
+,number="2"
+,pages="@@-@@"
+,annotation="
+	RCU, realtime RCU, sleepable RCU, performance.
+"
+}
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 42b01bc2e1b4..cf5562cbe356 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -13,10 +13,13 @@ over a rather long period of time, but improvements are always welcome!
 	detailed performance measurements show that RCU is nonetheless
 	the right tool for the job.
 
-	The other exception would be where performance is not an issue,
-	and RCU provides a simpler implementation.  An example of this
-	situation is the dynamic NMI code in the Linux 2.6 kernel,
-	at least on architectures where NMIs are rare.
+	Another exception is where performance is not an issue, and RCU
+	provides a simpler implementation.  An example of this situation
+	is the dynamic NMI code in the Linux 2.6 kernel, at least on
+	architectures where NMIs are rare.
+
+	Yet another exception is where the low real-time latency of RCU's
+	read-side primitives is critically important.
 
 1.	Does the update code have proper mutual exclusion?
 
@@ -39,9 +42,10 @@ over a rather long period of time, but improvements are always welcome!
 
 2.	Do the RCU read-side critical sections make proper use of
 	rcu_read_lock() and friends?  These primitives are needed
-	to suppress preemption (or bottom halves, in the case of
-	rcu_read_lock_bh()) in the read-side critical sections,
-	and are also an excellent aid to readability.
+	to prevent grace periods from ending prematurely, which
+	could result in data being unceremoniously freed out from
+	under your read-side code, which can greatly increase the
+	actuarial risk of your kernel.
 
 	As a rough rule of thumb, any dereference of an RCU-protected
 	pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
@@ -54,15 +58,30 @@ over a rather long period of time, but improvements are always welcome!
 	be running while updates are in progress.  There are a number
 	of ways to handle this concurrency, depending on the situation:
 
-	a.	Make updates appear atomic to readers.  For example,
+	a.	Use the RCU variants of the list and hlist update
+		primitives to add, remove, and replace elements on an
+		RCU-protected list.  Alternatively, use the RCU-protected
+		trees that have been added to the Linux kernel.
+
+		This is almost always the best approach.
+
+	b.	Proceed as in (a) above, but also maintain per-element
+		locks (that are acquired by both readers and writers)
+		that guard per-element state.  Of course, fields that
+		the readers refrain from accessing can be guarded by the
+		update-side lock.
+
+		This works quite well, also.
+
+	c.	Make updates appear atomic to readers.  For example,
 		pointer updates to properly aligned fields will appear
 		atomic, as will individual atomic primitives.  Operations
 		performed under a lock and sequences of multiple atomic
 		primitives will -not- appear to be atomic.
 
-		This is almost always the best approach.
+		This can work, but is starting to get a bit tricky.
 
-	b.	Carefully order the updates and the reads so that
+	d.	Carefully order the updates and the reads so that
 		readers see valid data at all phases of the update.
 		This is often more difficult than it sounds, especially
 		given modern CPUs' tendency to reorder memory references.
@@ -123,18 +142,22 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
-	is used, the callback function must be written to be called
-	from softirq context.  In particular, it cannot block.
+5.	If call_rcu(), or a related primitive such as call_rcu_bh() or
+	call_rcu_sched(), is used, the callback function must be
+	written to be called from softirq context.  In particular,
+	it cannot block.
 
 6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.
+	any sort of irq context.  Ditto for synchronize_sched() and
+	synchronize_srcu().
 
 7.	If the updater uses call_rcu(), then the corresponding readers
 	must use rcu_read_lock() and rcu_read_unlock().  If the updater
 	uses call_rcu_bh(), then the corresponding readers must use
-	rcu_read_lock_bh() and rcu_read_unlock_bh().  Mixing things up
-	will result in confusion and broken kernels.
+	rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
+	uses call_rcu_sched(), then the corresponding readers must
+	disable preemption.  Mixing things up will result in confusion
+	and broken kernels.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -143,9 +166,9 @@ over a rather long period of time, but improvements are always welcome!
 	such cases is a must, of course!  And the jury is still out on
 	whether the increased speed is worth it.
 
-8.	Although synchronize_rcu() is a bit slower than is call_rcu(),
-	it usually results in simpler code.  So, unless update
-	performance is critically important or the updaters cannot block,
+8.	Although synchronize_rcu() is slower than is call_rcu(), it
+	usually results in simpler code.  So, unless update performance
+	is critically important or the updaters cannot block,
 	synchronize_rcu() should be used in preference to call_rcu().
 
 	An especially important property of the synchronize_rcu()
@@ -187,23 +210,23 @@ over a rather long period of time, but improvements are always welcome!
 		number of updates per grace period.
 
 9.	All RCU list-traversal primitives, which include
-	list_for_each_rcu(), list_for_each_entry_rcu(),
+	rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
-	must be within an RCU read-side critical section.  RCU
+	must be either within an RCU read-side critical section or
+	must be protected by appropriate update-side locks.  RCU
 	read-side critical sections are delimited by rcu_read_lock()
 	and rcu_read_unlock(), or by similar primitives such as
 	rcu_read_lock_bh() and rcu_read_unlock_bh().
 
-	Use of the _rcu() list-traversal primitives outside of an
-	RCU read-side critical section causes no harm other than
-	a slight performance degradation on Alpha CPUs.  It can
-	also be quite helpful in reducing code bloat when common
-	code is shared between readers and updaters.
+	The reason that it is permissible to use RCU list-traversal
+	primitives when the update-side lock is held is that doing so
+	can be quite helpful in reducing code bloat when common code is
+	shared between readers and updaters.
 
 10.	Conversely, if you are in an RCU read-side critical section,
-	you -must- use the "_rcu()" variants of the list macros.
-	Failing to do so will break Alpha and confuse people reading
-	your code.
+	and you don't hold the appropriate update-side lock, you -must-
+	use the "_rcu()" variants of the list macros.  Failing to do so
+	will break Alpha and confuse people reading your code.
 
 11.	Note that synchronize_rcu() -only- guarantees to wait until
 	all currently executing rcu_read_lock()-protected RCU read-side
@@ -230,6 +253,14 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
+	RCU callbacks are -usually- executed on the same CPU that executed
+	the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
+	but are by -no- means guaranteed to be.  For example, if a given
+	CPU goes offline while having an RCU callback pending, then that
+	RCU callback will execute on some surviving CPU.  (If this was
+	not the case, a self-spawning RCU callback would prevent the
+	victim CPU from ever going offline.)
+
 14.	SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
 	may only be invoked from process context.  Unlike other forms of
 	RCU, it -is- permissible to block in an SRCU read-side critical
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 2967a65269d8..516527d4bc55 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -10,13 +10,20 @@ status messages via printk(), which can be examined via the dmesg
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
 
-However, actually setting this config option to "y" results in the system
-running the test immediately upon boot, and ending only when the system
-is taken down.  Normally, one will instead want to build the system
-with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control
-the test, perhaps using a script similar to the one shown at the end of
-this document.  Note that you will need CONFIG_MODULE_UNLOAD in order
-to be able to end the test.
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will
+result in the tests being loaded into the base kernel.  In this case,
+the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify
+whether the RCU torture tests are to be started immediately during
+boot or whether the /proc/sys/kernel/rcutorture_runnable file is used
+to enable them.  This /proc file can be used to repeatedly pause and
+restart the tests, regardless of the initial state specified by the
+CONFIG_RCU_TORTURE_TEST_RUNNABLE config option.
+
+You will normally -not- want to start the RCU torture tests during boot
+(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing
+this can sometimes be useful in finding boot-time bugs.
 
 
 MODULE PARAMETERS
@@ -46,9 +53,15 @@ stat_interval	The number of seconds between output of torture
 
 shuffle_interval
 		The number of seconds to keep the test threads affinitied
-		to a particular subset of the CPUs, defaults to 5 seconds.
+		to a particular subset of the CPUs, defaults to 3 seconds.
 		Used in conjunction with test_no_idle_hz.
 
+stutter		The length of time to run the test before pausing for this
+		same period of time.  Defaults to "stutter=5", so as
+		to run and pause for (roughly) five-second intervals.
+		Specifying "stutter=0" causes the test to run continuously
+		without pausing, which is the old default behavior.
+
 test_no_idle_hz	Whether or not to test the ability of RCU to operate in
 		a kernel that disables the scheduling-clock interrupt to
 		idle CPUs.  Boolean parameter, "1" to test, "0" otherwise.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e0d6d99b8f9b..e04d643a9f57 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -1,3 +1,11 @@
+Please note that the "What is RCU?" LWN series is an excellent place
+to start learning about RCU:
+
+1.	What is RCU, Fundamentally?  http://lwn.net/Articles/262464/
+2.	What is RCU? Part 2: Usage   http://lwn.net/Articles/263130/
+3.	RCU part 3: the RCU API      http://lwn.net/Articles/264090/
+
+
 What is RCU?
 
 RCU is a synchronization mechanism that was added to the Linux kernel
@@ -772,26 +780,18 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-Markers for RCU read-side critical sections:
-
-	rcu_read_lock
-	rcu_read_unlock
-	rcu_read_lock_bh
-	rcu_read_unlock_bh
-	srcu_read_lock
-	srcu_read_unlock
-
 RCU pointer/list traversal:
 
 	rcu_dereference
+	list_for_each_entry_rcu
+	hlist_for_each_entry_rcu
+
 	list_for_each_rcu		(to be deprecated in favor of
 					 list_for_each_entry_rcu)
-	list_for_each_entry_rcu
 	list_for_each_continue_rcu	(to be deprecated in favor of new
 					 list_for_each_entry_continue_rcu)
-	hlist_for_each_entry_rcu
 
-RCU pointer update:
+RCU pointer/list update:
 
 	rcu_assign_pointer
 	list_add_rcu
@@ -799,16 +799,36 @@ RCU pointer update:
 	list_del_rcu
 	list_replace_rcu
 	hlist_del_rcu
+	hlist_add_after_rcu
+	hlist_add_before_rcu
 	hlist_add_head_rcu
+	hlist_replace_rcu
+	list_splice_init_rcu()
 
-RCU grace period:
+RCU:	Critical sections	Grace period		Barrier
+
+	rcu_read_lock		synchronize_net		rcu_barrier
+	rcu_read_unlock		synchronize_rcu
+				call_rcu
+
+
+bh:	Critical sections	Grace period		Barrier
+
+	rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
+	rcu_read_unlock_bh
+
+
+sched:	Critical sections	Grace period		Barrier
+
+	[preempt_disable]	synchronize_sched	rcu_barrier_sched
+	[and friends]		call_rcu_sched
+
+
+SRCU:	Critical sections	Grace period		Barrier
+
+	srcu_read_lock		synchronize_srcu	N/A
+	srcu_read_unlock
 
-	synchronize_net
-	synchronize_sched
-	synchronize_rcu
-	synchronize_srcu
-	call_rcu
-	call_rcu_bh
 
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
diff --git a/Documentation/scheduler/sched-domains.txt b/Documentation/scheduler/sched-domains.txt
index a9e990ab980f..373ceacc367e 100644
--- a/Documentation/scheduler/sched-domains.txt
+++ b/Documentation/scheduler/sched-domains.txt
@@ -61,10 +61,7 @@ builder by #define'ing ARCH_HASH_SCHED_DOMAIN, and exporting your
 arch_init_sched_domains function. This function will attach domains to all
 CPUs using cpu_attach_domain.
 
-Implementors should change the line
-#undef SCHED_DOMAIN_DEBUG
-to
-#define SCHED_DOMAIN_DEBUG
-in kernel/sched.c as this enables an error checking parse of the sched domains
+The sched-domains debugging infrastructure can be enabled by enabling
+CONFIG_SCHED_DEBUG. This enables an error checking parse of the sched domains
 which should catch most possible errors (described above). It also prints out
 the domain structure in a visual format.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 14f901f639ee..3ef339f491e0 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -51,9 +51,9 @@ needs only about 3% CPU time to do so, it can do with a 0.03 * 0.005s =
 0.00015s. So this group can be scheduled with a period of 0.005s and a run time
 of 0.00015s.
 
-The remaining CPU time will be used for user input and other tass. Because
+The remaining CPU time will be used for user input and other tasks. Because
 realtime tasks have explicitly allocated the CPU time they need to perform
-their tasks, buffer underruns in the graphocs or audio can be eliminated.
+their tasks, buffer underruns in the graphics or audio can be eliminated.
 
 NOTE: the above example is not fully implemented as of yet (2.6.25). We still
 lack an EDF scheduler to make non-uniform periods usable.
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index 53351c3cd7b1..96c31b4180c3 100644
--- a/arch/ia64/sn/kernel/irq.c
+++ b/arch/ia64/sn/kernel/irq.c
@@ -11,6 +11,7 @@
 #include <linux/irq.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/intr.h>
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index b65871e6bba6..7bfdad7589fa 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -23,6 +23,7 @@
 #include <linux/errno.h>
 #include <asm/debugreg.h>
 #include <linux/mmiotrace.h>
+#include <linux/rculist.h>
 
 #define KMMIO_PAGE_HASH_BITS 4
 #define KMMIO_PAGE_TABLE_SIZE (1 << KMMIO_PAGE_HASH_BITS)
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index c6e772fc5ccd..095c798d3170 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -23,6 +23,7 @@
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  *
  */
+#include <linux/rculist.h>
 #include <linux/kernel.h>
 #include <linux/async_tx.h>
 
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c
index 7779165b2c2c..38c44dec51ca 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs.c
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.c
@@ -35,6 +35,7 @@
 #include <rdma/ib_user_verbs.h>
 #include <linux/io.h>
 #include <linux/utsname.h>
+#include <linux/rculist.h>
 
 #include "ipath_kernel.h"
 #include "ipath_verbs.h"
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c b/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c
index 9e5abf9c309d..d73e32232879 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c
+++ b/drivers/infiniband/hw/ipath/ipath_verbs_mcast.c
@@ -31,8 +31,7 @@
  * SOFTWARE.
  */
 
-#include <linux/list.h>
-#include <linux/rcupdate.h>
+#include <linux/rculist.h>
 
 #include "ipath_verbs.h"
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c36a03ae9bfb..860d75d81f82 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -20,7 +20,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/list.h>
+#include <linux/rculist.h>
 #include <linux/notifier.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 2a6639407c80..1f5cebf10a23 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -3,6 +3,7 @@
 
 #include <asm/atomic.h>
 #include <linux/list.h>
+#include <linux/rculist.h>
 #include <linux/spinlock.h>
 #include <linux/cache.h>
 #include <linux/rcupdate.h>
diff --git a/include/linux/list.h b/include/linux/list.h
index 08cf4f651889..139ec41d9c2e 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -85,65 +85,6 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head)
 }
 
 /*
- * Insert a new entry between two known consecutive entries.
- *
- * This is only for internal list manipulation where we know
- * the prev/next entries already!
- */
-static inline void __list_add_rcu(struct list_head * new,
-		struct list_head * prev, struct list_head * next)
-{
-	new->next = next;
-	new->prev = prev;
-	smp_wmb();
-	next->prev = new;
-	prev->next = new;
-}
-
-/**
- * list_add_rcu - add a new entry to rcu-protected list
- * @new: new entry to be added
- * @head: list head to add it after
- *
- * Insert a new entry after the specified head.
- * This is good for implementing stacks.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as list_add_rcu()
- * or list_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * list_for_each_entry_rcu().
- */
-static inline void list_add_rcu(struct list_head *new, struct list_head *head)
-{
-	__list_add_rcu(new, head, head->next);
-}
-
-/**
- * list_add_tail_rcu - add a new entry to rcu-protected list
- * @new: new entry to be added
- * @head: list head to add it before
- *
- * Insert a new entry before the specified head.
- * This is useful for implementing queues.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as list_add_tail_rcu()
- * or list_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * list_for_each_entry_rcu().
- */
-static inline void list_add_tail_rcu(struct list_head *new,
-					struct list_head *head)
-{
-	__list_add_rcu(new, head->prev, head);
-}
-
-/*
  * Delete a list entry by making the prev/next entries
  * point to each other.
  *
@@ -174,36 +115,6 @@ extern void list_del(struct list_head *entry);
 #endif
 
 /**
- * list_del_rcu - deletes entry from list without re-initialization
- * @entry: the element to delete from the list.
- *
- * Note: list_empty() on entry does not return true after this,
- * the entry is in an undefined state. It is useful for RCU based
- * lockfree traversal.
- *
- * In particular, it means that we can not poison the forward
- * pointers that may still be used for walking the list.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as list_del_rcu()
- * or list_add_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * list_for_each_entry_rcu().
- *
- * Note that the caller is not permitted to immediately free
- * the newly deleted entry.  Instead, either synchronize_rcu()
- * or call_rcu() must be used to defer freeing until an RCU
- * grace period has elapsed.
- */
-static inline void list_del_rcu(struct list_head *entry)
-{
-	__list_del(entry->prev, entry->next);
-	entry->prev = LIST_POISON2;
-}
-
-/**
  * list_replace - replace old entry by new one
  * @old : the element to be replaced
  * @new : the new element to insert
@@ -227,25 +138,6 @@ static inline void list_replace_init(struct list_head *old,
 }
 
 /**
- * list_replace_rcu - replace old entry by new one
- * @old : the element to be replaced
- * @new : the new element to insert
- *
- * The @old entry will be replaced with the @new entry atomically.
- * Note: @old should not be empty.
- */
-static inline void list_replace_rcu(struct list_head *old,
-				struct list_head *new)
-{
-	new->next = old->next;
-	new->prev = old->prev;
-	smp_wmb();
-	new->next->prev = new;
-	new->prev->next = new;
-	old->prev = LIST_POISON2;
-}
-
-/**
  * list_del_init - deletes entry from list and reinitialize it.
  * @entry: the element to delete from the list.
  */
@@ -369,62 +261,6 @@ static inline void list_splice_init(struct list_head *list,
 }
 
 /**
- * list_splice_init_rcu - splice an RCU-protected list into an existing list.
- * @list:	the RCU-protected list to splice
- * @head:	the place in the list to splice the first list into
- * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
- *
- * @head can be RCU-read traversed concurrently with this function.
- *
- * Note that this function blocks.
- *
- * Important note: the caller must take whatever action is necessary to
- *	prevent any other updates to @head.  In principle, it is possible
- *	to modify the list as soon as sync() begins execution.
- *	If this sort of thing becomes necessary, an alternative version
- *	based on call_rcu() could be created.  But only if -really-
- *	needed -- there is no shortage of RCU API members.
- */
-static inline void list_splice_init_rcu(struct list_head *list,
-					struct list_head *head,
-					void (*sync)(void))
-{
-	struct list_head *first = list->next;
-	struct list_head *last = list->prev;
-	struct list_head *at = head->next;
-
-	if (list_empty(head))
-		return;
-
-	/* "first" and "last" tracking list, so initialize it. */
-
-	INIT_LIST_HEAD(list);
-
-	/*
-	 * At this point, the list body still points to the source list.
-	 * Wait for any readers to finish using the list before splicing
-	 * the list body into the new list.  Any new readers will see
-	 * an empty list.
-	 */
-
-	sync();
-
-	/*
-	 * Readers are finished with the source list, so perform splice.
-	 * The order is important if the new list is global and accessible
-	 * to concurrent RCU readers.  Note that RCU readers are not
-	 * permitted to traverse the prev pointers without excluding
-	 * this function.
-	 */
-
-	last->next = at;
-	smp_wmb();
-	head->next = first;
-	first->prev = head;
-	at->prev = last;
-}
-
-/**
  * list_entry - get the struct for this entry
  * @ptr:	the &struct list_head pointer.
  * @type:	the type of the struct this is embedded in.
@@ -629,57 +465,6 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	     &pos->member != (head); 					\
 	     pos = n, n = list_entry(n->member.prev, typeof(*n), member))
 
-/**
- * list_for_each_rcu	-	iterate over an rcu-protected list
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference((head)->next); \
-		prefetch(pos->next), pos != (head); \
-		pos = rcu_dereference(pos->next))
-
-#define __list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference((head)->next); \
-		pos != (head); \
-		pos = rcu_dereference(pos->next))
-
-/**
- * list_for_each_entry_rcu	-	iterate over rcu list of given type
- * @pos:	the type * to use as a loop cursor.
- * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_entry_rcu(pos, head, member) \
-	for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
-		prefetch(pos->member.next), &pos->member != (head); \
-		pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
-
-
-/**
- * list_for_each_continue_rcu
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * Iterate over an rcu-protected list, continuing after current point.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_continue_rcu(pos, head) \
-	for ((pos) = rcu_dereference((pos)->next); \
-		prefetch((pos)->next), (pos) != (head); \
-		(pos) = rcu_dereference((pos)->next))
-
 /*
  * Double linked lists with a single pointer list head.
  * Mostly useful for hash tables where the two pointer list head is
@@ -730,31 +515,6 @@ static inline void hlist_del(struct hlist_node *n)
 	n->pprev = LIST_POISON2;
 }
 
-/**
- * hlist_del_rcu - deletes entry from hash list without re-initialization
- * @n: the element to delete from the hash list.
- *
- * Note: list_unhashed() on entry does not return true after this,
- * the entry is in an undefined state. It is useful for RCU based
- * lockfree traversal.
- *
- * In particular, it means that we can not poison the forward
- * pointers that may still be used for walking the hash list.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry().
- */
-static inline void hlist_del_rcu(struct hlist_node *n)
-{
-	__hlist_del(n);
-	n->pprev = LIST_POISON2;
-}
-
 static inline void hlist_del_init(struct hlist_node *n)
 {
 	if (!hlist_unhashed(n)) {
@@ -763,27 +523,6 @@ static inline void hlist_del_init(struct hlist_node *n)
 	}
 }
 
-/**
- * hlist_replace_rcu - replace old entry by new one
- * @old : the element to be replaced
- * @new : the new element to insert
- *
- * The @old entry will be replaced with the @new entry atomically.
- */
-static inline void hlist_replace_rcu(struct hlist_node *old,
-					struct hlist_node *new)
-{
-	struct hlist_node *next = old->next;
-
-	new->next = next;
-	new->pprev = old->pprev;
-	smp_wmb();
-	if (next)
-		new->next->pprev = &new->next;
-	*new->pprev = new;
-	old->pprev = LIST_POISON2;
-}
-
 static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
 {
 	struct hlist_node *first = h->first;
@@ -794,38 +533,6 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
 	n->pprev = &h->first;
 }
 
-
-/**
- * hlist_add_head_rcu
- * @n: the element to add to the hash list.
- * @h: the list to add to.
- *
- * Description:
- * Adds the specified element to the specified hlist,
- * while permitting racing traversals.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.  Regardless of the type of CPU, the
- * list-traversal primitive must be guarded by rcu_read_lock().
- */
-static inline void hlist_add_head_rcu(struct hlist_node *n,
-					struct hlist_head *h)
-{
-	struct hlist_node *first = h->first;
-	n->next = first;
-	n->pprev = &h->first;
-	smp_wmb();
-	if (first)
-		first->pprev = &n->next;
-	h->first = n;
-}
-
 /* next must be != NULL */
 static inline void hlist_add_before(struct hlist_node *n,
 					struct hlist_node *next)
@@ -847,63 +554,6 @@ static inline void hlist_add_after(struct hlist_node *n,
 		next->next->pprev  = &next->next;
 }
 
-/**
- * hlist_add_before_rcu
- * @n: the new element to add to the hash list.
- * @next: the existing element to add the new element before.
- *
- * Description:
- * Adds the specified element to the specified hlist
- * before the specified node while permitting racing traversals.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.
- */
-static inline void hlist_add_before_rcu(struct hlist_node *n,
-					struct hlist_node *next)
-{
-	n->pprev = next->pprev;
-	n->next = next;
-	smp_wmb();
-	next->pprev = &n->next;
-	*(n->pprev) = n;
-}
-
-/**
- * hlist_add_after_rcu
- * @prev: the existing element to add the new element after.
- * @n: the new element to add to the hash list.
- *
- * Description:
- * Adds the specified element to the specified hlist
- * after the specified node while permitting racing traversals.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.
- */
-static inline void hlist_add_after_rcu(struct hlist_node *prev,
-				       struct hlist_node *n)
-{
-	n->next = prev->next;
-	n->pprev = &prev->next;
-	smp_wmb();
-	prev->next = n;
-	if (n->next)
-		n->next->pprev = &n->next;
-}
-
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
@@ -964,21 +614,4 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
 	     pos = n)
 
-/**
- * hlist_for_each_entry_rcu - iterate over rcu list of given type
- * @tpos:	the type * to use as a loop cursor.
- * @pos:	the &struct hlist_node to use as a loop cursor.
- * @head:	the head for your list.
- * @member:	the name of the hlist_node within the struct.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as hlist_add_head_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define hlist_for_each_entry_rcu(tpos, pos, head, member)		 \
-	for (pos = rcu_dereference((head)->first);			 \
-	        pos && ({ prefetch(pos->next); 1;}) &&			 \
-		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
-	     pos = rcu_dereference(pos->next))
-
 #endif
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index b3aa05baab8a..8c774905dcfe 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -151,7 +151,10 @@ extern struct lockdep_map rcu_lock_map;
 
 #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);
 
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
new file mode 100644
index 000000000000..b0f39be08b6c
--- /dev/null
+++ b/include/linux/rculist.h
@@ -0,0 +1,373 @@
+#ifndef _LINUX_RCULIST_H
+#define _LINUX_RCULIST_H
+
+#ifdef __KERNEL__
+
+/*
+ * RCU-protected list version
+ */
+#include <linux/list.h>
+#include <linux/rcupdate.h>
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_add_rcu(struct list_head *new,
+		struct list_head *prev, struct list_head *next)
+{
+	new->next = next;
+	new->prev = prev;
+	rcu_assign_pointer(prev->next, new);
+	next->prev = new;
+}
+
+/**
+ * list_add_rcu - add a new entry to rcu-protected list
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as list_add_rcu()
+ * or list_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * list_for_each_entry_rcu().
+ */
+static inline void list_add_rcu(struct list_head *new, struct list_head *head)
+{
+	__list_add_rcu(new, head, head->next);
+}
+
+/**
+ * list_add_tail_rcu - add a new entry to rcu-protected list
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as list_add_tail_rcu()
+ * or list_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * list_for_each_entry_rcu().
+ */
+static inline void list_add_tail_rcu(struct list_head *new,
+					struct list_head *head)
+{
+	__list_add_rcu(new, head->prev, head);
+}
+
+/**
+ * list_del_rcu - deletes entry from list without re-initialization
+ * @entry: the element to delete from the list.
+ *
+ * Note: list_empty() on entry does not return true after this,
+ * the entry is in an undefined state. It is useful for RCU based
+ * lockfree traversal.
+ *
+ * In particular, it means that we can not poison the forward
+ * pointers that may still be used for walking the list.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as list_del_rcu()
+ * or list_add_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * list_for_each_entry_rcu().
+ *
+ * Note that the caller is not permitted to immediately free
+ * the newly deleted entry.  Instead, either synchronize_rcu()
+ * or call_rcu() must be used to defer freeing until an RCU
+ * grace period has elapsed.
+ */
+static inline void list_del_rcu(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+	entry->prev = LIST_POISON2;
+}
+
+/**
+ * list_replace_rcu - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * The @old entry will be replaced with the @new entry atomically.
+ * Note: @old should not be empty.
+ */
+static inline void list_replace_rcu(struct list_head *old,
+				struct list_head *new)
+{
+	new->next = old->next;
+	new->prev = old->prev;
+	rcu_assign_pointer(new->prev->next, new);
+	new->next->prev = new;
+	old->prev = LIST_POISON2;
+}
+
+/**
+ * list_splice_init_rcu - splice an RCU-protected list into an existing list.
+ * @list:	the RCU-protected list to splice
+ * @head:	the place in the list to splice the first list into
+ * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
+ *
+ * @head can be RCU-read traversed concurrently with this function.
+ *
+ * Note that this function blocks.
+ *
+ * Important note: the caller must take whatever action is necessary to
+ *	prevent any other updates to @head.  In principle, it is possible
+ *	to modify the list as soon as sync() begins execution.
+ *	If this sort of thing becomes necessary, an alternative version
+ *	based on call_rcu() could be created.  But only if -really-
+ *	needed -- there is no shortage of RCU API members.
+ */
+static inline void list_splice_init_rcu(struct list_head *list,
+					struct list_head *head,
+					void (*sync)(void))
+{
+	struct list_head *first = list->next;
+	struct list_head *last = list->prev;
+	struct list_head *at = head->next;
+
+	if (list_empty(head))
+		return;
+
+	/* "first" and "last" tracking list, so initialize it. */
+
+	INIT_LIST_HEAD(list);
+
+	/*
+	 * At this point, the list body still points to the source list.
+	 * Wait for any readers to finish using the list before splicing
+	 * the list body into the new list.  Any new readers will see
+	 * an empty list.
+	 */
+
+	sync();
+
+	/*
+	 * Readers are finished with the source list, so perform splice.
+	 * The order is important if the new list is global and accessible
+	 * to concurrent RCU readers.  Note that RCU readers are not
+	 * permitted to traverse the prev pointers without excluding
+	 * this function.
+	 */
+
+	last->next = at;
+	rcu_assign_pointer(head->next, first);
+	first->prev = head;
+	at->prev = last;
+}
+
+/**
+ * list_for_each_rcu	-	iterate over an rcu-protected list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define list_for_each_rcu(pos, head) \
+	for (pos = rcu_dereference((head)->next); \
+		prefetch(pos->next), pos != (head); \
+		pos = rcu_dereference(pos->next))
+
+#define __list_for_each_rcu(pos, head) \
+	for (pos = rcu_dereference((head)->next); \
+		pos != (head); \
+		pos = rcu_dereference(pos->next))
+
+/**
+ * list_for_each_entry_rcu	-	iterate over rcu list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define list_for_each_entry_rcu(pos, head, member) \
+	for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+		prefetch(pos->member.next), &pos->member != (head); \
+		pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+
+
+/**
+ * list_for_each_continue_rcu
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * Iterate over an rcu-protected list, continuing after current point.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define list_for_each_continue_rcu(pos, head) \
+	for ((pos) = rcu_dereference((pos)->next); \
+		prefetch((pos)->next), (pos) != (head); \
+		(pos) = rcu_dereference((pos)->next))
+
+/**
+ * hlist_del_rcu - deletes entry from hash list without re-initialization
+ * @n: the element to delete from the hash list.
+ *
+ * Note: list_unhashed() on entry does not return true after this,
+ * the entry is in an undefined state. It is useful for RCU based
+ * lockfree traversal.
+ *
+ * In particular, it means that we can not poison the forward
+ * pointers that may still be used for walking the hash list.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry().
+ */
+static inline void hlist_del_rcu(struct hlist_node *n)
+{
+	__hlist_del(n);
+	n->pprev = LIST_POISON2;
+}
+
+/**
+ * hlist_replace_rcu - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * The @old entry will be replaced with the @new entry atomically.
+ */
+static inline void hlist_replace_rcu(struct hlist_node *old,
+					struct hlist_node *new)
+{
+	struct hlist_node *next = old->next;
+
+	new->next = next;
+	new->pprev = old->pprev;
+	rcu_assign_pointer(*new->pprev, new);
+	if (next)
+		new->next->pprev = &new->next;
+	old->pprev = LIST_POISON2;
+}
+
+/**
+ * hlist_add_head_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_add_head_rcu(struct hlist_node *n,
+					struct hlist_head *h)
+{
+	struct hlist_node *first = h->first;
+
+	n->next = first;
+	n->pprev = &h->first;
+	rcu_assign_pointer(h->first, n);
+	if (first)
+		first->pprev = &n->next;
+}
+
+/**
+ * hlist_add_before_rcu
+ * @n: the new element to add to the hash list.
+ * @next: the existing element to add the new element before.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist
+ * before the specified node while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.
+ */
+static inline void hlist_add_before_rcu(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	n->pprev = next->pprev;
+	n->next = next;
+	rcu_assign_pointer(*(n->pprev), n);
+	next->pprev = &n->next;
+}
+
+/**
+ * hlist_add_after_rcu
+ * @prev: the existing element to add the new element after.
+ * @n: the new element to add to the hash list.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist
+ * after the specified node while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.
+ */
+static inline void hlist_add_after_rcu(struct hlist_node *prev,
+				       struct hlist_node *n)
+{
+	n->next = prev->next;
+	n->pprev = &prev->next;
+	rcu_assign_pointer(prev->next, n);
+	if (n->next)
+		n->next->pprev = &n->next;
+}
+
+/**
+ * hlist_for_each_entry_rcu - iterate over rcu list of given type
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as hlist_add_head_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define hlist_for_each_entry_rcu(tpos, pos, head, member)		 \
+	for (pos = rcu_dereference((head)->first);			 \
+		pos && ({ prefetch(pos->next); 1; }) &&			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
+		pos = rcu_dereference(pos->next))
+
+#endif	/* __KERNEL__ */
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d42dbec06083..e8b4039cfb2f 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,6 +40,7 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
+#include <linux/completion.h>
 
 /**
  * struct rcu_head - callback structure for use with RCU
@@ -168,6 +169,27 @@ struct rcu_head {
 		(p) = (v); \
 	})
 
+/* Infrastructure to implement the synchronize_() primitives. */
+
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+
+extern void wakeme_after_rcu(struct rcu_head  *head);
+
+#define synchronize_rcu_xxx(name, func) \
+void name(void) \
+{ \
+	struct rcu_synchronize rcu; \
+	\
+	init_completion(&rcu.completion); \
+	/* Will wake me after RCU finished. */ \
+	func(&rcu.head, wakeme_after_rcu); \
+	/* Wait for it. */ \
+	wait_for_completion(&rcu.completion); \
+}
+
 /**
  * synchronize_sched - block until all CPUs have exited any non-preemptive
  * kernel code sequences.
@@ -224,8 +246,8 @@ extern void call_rcu_bh(struct rcu_head *head,
 /* Exported common interfaces */
 extern void synchronize_rcu(void);
 extern void rcu_barrier(void);
-extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index 8a05c7e20bc4..f04b64eca636 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -40,10 +40,39 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 
-#define rcu_qsctr_inc(cpu)
+struct rcu_dyntick_sched {
+	int dynticks;
+	int dynticks_snap;
+	int sched_qs;
+	int sched_qs_snap;
+	int sched_dynticks_snap;
+};
+
+DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
+
+static inline void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->sched_qs++;
+}
 #define rcu_bh_qsctr_inc(cpu)
 #define call_rcu_bh(head, rcu) call_rcu(head, 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);
@@ -55,6 +84,7 @@ extern int rcu_needs_cpu(int cpu);
 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);
@@ -81,20 +111,20 @@ extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu);
 struct softirq_action;
 
 #ifdef CONFIG_NO_HZ
-DECLARE_PER_CPU(long, dynticks_progress_counter);
+DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
 
 static inline void rcu_enter_nohz(void)
 {
 	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	__get_cpu_var(dynticks_progress_counter)++;
-	WARN_ON(__get_cpu_var(dynticks_progress_counter) & 0x1);
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	WARN_ON(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1);
 }
 
 static inline void rcu_exit_nohz(void)
 {
-	__get_cpu_var(dynticks_progress_counter)++;
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
-	WARN_ON(!(__get_cpu_var(dynticks_progress_counter) & 0x1));
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	WARN_ON(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1));
 }
 
 #else /* CONFIG_NO_HZ */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 87e00d199f32..fff888f2827e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -134,7 +134,6 @@ extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
-extern unsigned long weighted_cpuload(const int cpu);
 
 struct seq_file;
 struct cfs_rq;
@@ -826,23 +825,6 @@ extern int arch_reinit_sched_domains(void);
 
 #endif	/* CONFIG_SMP */
 
-/*
- * A runqueue laden with a single nice 0 task scores a weighted_cpuload of
- * SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a
- * task of nice 0 or enough lower priority tasks to bring up the
- * weighted_cpuload
- */
-static inline int above_background_load(void)
-{
-	unsigned long cpu;
-
-	for_each_online_cpu(cpu) {
-		if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)
-			return 1;
-	}
-	return 0;
-}
-
 struct io_context;			/* See blkdev.h */
 #define NGROUPS_SMALL		32
 #define NGROUPS_PER_BLOCK	((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
@@ -924,8 +906,8 @@ struct sched_class {
 	void (*set_cpus_allowed)(struct task_struct *p,
 				 const cpumask_t *newmask);
 
-	void (*join_domain)(struct rq *rq);
-	void (*leave_domain)(struct rq *rq);
+	void (*rq_online)(struct rq *rq);
+	void (*rq_offline)(struct rq *rq);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
 			       int running);
@@ -1042,6 +1024,7 @@ struct task_struct {
 #endif
 
 	int prio, static_prio, normal_prio;
+	unsigned int rt_priority;
 	const struct sched_class *sched_class;
 	struct sched_entity se;
 	struct sched_rt_entity rt;
@@ -1125,7 +1108,6 @@ struct task_struct {
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
 	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
 
-	unsigned int rt_priority;
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
 	cputime_t prev_utime, prev_stime;
@@ -1144,12 +1126,12 @@ struct task_struct {
 	gid_t gid,egid,sgid,fsgid;
 	struct group_info *group_info;
 	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted, cap_bset;
-	unsigned securebits;
 	struct user_struct *user;
+	unsigned securebits;
 #ifdef CONFIG_KEYS
+	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
 	struct key *request_key_auth;	/* assumed request_key authority */
 	struct key *thread_keyring;	/* keyring private to this thread */
-	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
 #endif
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock
@@ -1236,8 +1218,8 @@ struct task_struct {
 # define MAX_LOCK_DEPTH 48UL
 	u64 curr_chain_key;
 	int lockdep_depth;
-	struct held_lock held_locks[MAX_LOCK_DEPTH];
 	unsigned int lockdep_recursion;
+	struct held_lock held_locks[MAX_LOCK_DEPTH];
 #endif
 
 /* journalling filesystem info */
@@ -1265,10 +1247,6 @@ struct task_struct {
 	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
 	cputime_t acct_stimexpd;/* stime since last update */
 #endif
-#ifdef CONFIG_NUMA
-  	struct mempolicy *mempolicy;
-	short il_next;
-#endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;
 	int cpuset_mems_generation;
@@ -1288,6 +1266,10 @@ struct task_struct {
 	struct list_head pi_state_list;
 	struct futex_pi_state *pi_state_cache;
 #endif
+#ifdef CONFIG_NUMA
+	struct mempolicy *mempolicy;
+	short il_next;
+#endif
 	atomic_t fs_excl;	/* holding fs exclusive resources */
 	struct rcu_head rcu;
 
@@ -1507,6 +1489,7 @@ static inline void put_task_struct(struct task_struct *t)
 #define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */
 #define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
+#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
@@ -1658,6 +1641,8 @@ extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
+extern int sched_setscheduler_nocheck(struct task_struct *, int,
+				      struct sched_param *);
 extern struct task_struct *idle_task(int cpu);
 extern struct task_struct *curr_task(int cpu);
 extern void set_curr_task(int cpu, struct task_struct *p);
diff --git a/init/main.c b/init/main.c
index f4f997e7da74..693d68874233 100644
--- a/init/main.c
+++ b/init/main.c
@@ -758,6 +758,7 @@ static void __init do_initcalls(void)
  */
 static void __init do_basic_setup(void)
 {
+	rcu_init_sched(); /* needed by module_init stage. */
 	/* drivers will send hotplug events */
 	init_workqueues();
 	usermodehelper_init();
diff --git a/kernel/Makefile b/kernel/Makefile
index ca2433e84873..e66a541d8cf8 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
-	    exit.o itimer.o time.o softirq.o resource.o \
+	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
@@ -39,7 +39,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
-obj-$(CONFIG_SMP) += cpu.o spinlock.o
+obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
@@ -83,6 +83,7 @@ obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_FTRACE) += trace/
 obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_SMP) += sched_cpupri.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 50ae922c6022..b21ba7e9036d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -15,6 +15,28 @@
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 
+/*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+cpumask_t cpu_present_map __read_mostly;
+EXPORT_SYMBOL(cpu_present_map);
+
+#ifndef CONFIG_SMP
+
+/*
+ * Represents all cpu's that are currently online.
+ */
+cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_online_map);
+
+cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_possible_map);
+
+#else /* CONFIG_SMP */
+
 /* Serializes the updates to cpu_online_map, cpu_present_map */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
@@ -403,3 +425,5 @@ out:
 	cpu_maps_update_done();
 }
 #endif /* CONFIG_PM_SLEEP_SMP */
+
+#endif /* CONFIG_SMP */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9fceb97e989c..64a05da9bc4c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1194,6 +1194,15 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 
 	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
+	if (tsk->flags & PF_THREAD_BOUND) {
+		cpumask_t mask;
+
+		mutex_lock(&callback_mutex);
+		mask = cs->cpus_allowed;
+		mutex_unlock(&callback_mutex);
+		if (!cpus_equal(tsk->cpus_allowed, mask))
+			return -EINVAL;
+	}
 
 	return security_task_setscheduler(tsk, 0, NULL);
 }
@@ -1207,11 +1216,14 @@ static void cpuset_attach(struct cgroup_subsys *ss,
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
+	int err;
 
 	mutex_lock(&callback_mutex);
 	guarantee_online_cpus(cs, &cpus);
-	set_cpus_allowed_ptr(tsk, &cpus);
+	err = set_cpus_allowed_ptr(tsk, &cpus);
 	mutex_unlock(&callback_mutex);
+	if (err)
+		return;
 
 	from = oldcs->mems_allowed;
 	to = cs->mems_allowed;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index bd1b9ea024e1..97747cdd37c9 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -180,6 +180,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
 	set_task_cpu(k, cpu);
 	k->cpus_allowed = cpumask_of_cpu(cpu);
 	k->rt.nr_cpus_allowed = 1;
+	k->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
 
diff --git a/kernel/pid.c b/kernel/pid.c
index 20d59fa2d493..30bd5d4b2ac7 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <linux/bootmem.h>
 #include <linux/hash.h>
 #include <linux/pid_namespace.h>
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index ef39700412e9..b5b90b25e49f 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -502,10 +502,38 @@ void rcu_check_callbacks(int cpu, int user)
 	if (user ||
 	    (idle_cpu(cpu) && !in_softirq() &&
 				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+
+		/*
+		 * Get here if this CPU took its interrupt from user
+		 * mode or from the idle loop, and if this is not a
+		 * nested interrupt.  In this case, the CPU is in
+		 * a quiescent state, so count it.
+		 *
+		 * Also do a memory barrier.  This is needed to handle
+		 * the case where writes from a preempt-disable section
+		 * of code get reordered into schedule() by this CPU's
+		 * write buffer.  The memory barrier makes sure that
+		 * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see
+		 * by other CPUs to happen after any such write.
+		 */
+
+		smp_mb();  /* See above block comment. */
 		rcu_qsctr_inc(cpu);
 		rcu_bh_qsctr_inc(cpu);
-	} else if (!in_softirq())
+
+	} else if (!in_softirq()) {
+
+		/*
+		 * Get here if this CPU did not take its interrupt from
+		 * softirq, in other words, if it is not interrupting
+		 * a rcu_bh read-side critical section.  This is an _bh
+		 * critical section, so count it.  The memory barrier
+		 * is needed for the same reason as is the above one.
+		 */
+
+		smp_mb();  /* See above block comment. */
 		rcu_bh_qsctr_inc(cpu);
+	}
 	raise_rcu_softirq();
 }
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index c09605f8d16c..4a74b8d48d90 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -39,16 +39,16 @@
 #include <linux/sched.h>
 #include <asm/atomic.h>
 #include <linux/bitops.h>
-#include <linux/completion.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
 
-struct rcu_synchronize {
-	struct rcu_head head;
-	struct completion completion;
+enum rcu_barrier {
+	RCU_BARRIER_STD,
+	RCU_BARRIER_BH,
+	RCU_BARRIER_SCHED,
 };
 
 static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
@@ -60,7 +60,7 @@ static struct completion rcu_barrier_completion;
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
  */
-static void wakeme_after_rcu(struct rcu_head  *head)
+void wakeme_after_rcu(struct rcu_head  *head)
 {
 	struct rcu_synchronize *rcu;
 
@@ -77,17 +77,7 @@ static void wakeme_after_rcu(struct rcu_head  *head)
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
-void synchronize_rcu(void)
-{
-	struct rcu_synchronize rcu;
-
-	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);
-}
+synchronize_rcu_xxx(synchronize_rcu, call_rcu)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 static void rcu_barrier_callback(struct rcu_head *notused)
@@ -99,19 +89,30 @@ static void rcu_barrier_callback(struct rcu_head *notused)
 /*
  * Called with preemption disabled, and from cross-cpu IRQ context.
  */
-static void rcu_barrier_func(void *notused)
+static void rcu_barrier_func(void *type)
 {
 	int cpu = smp_processor_id();
 	struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu);
 
 	atomic_inc(&rcu_barrier_cpu_count);
-	call_rcu(head, rcu_barrier_callback);
+	switch ((enum rcu_barrier)type) {
+	case RCU_BARRIER_STD:
+		call_rcu(head, rcu_barrier_callback);
+		break;
+	case RCU_BARRIER_BH:
+		call_rcu_bh(head, rcu_barrier_callback);
+		break;
+	case RCU_BARRIER_SCHED:
+		call_rcu_sched(head, rcu_barrier_callback);
+		break;
+	}
 }
 
-/**
- * rcu_barrier - Wait until all the in-flight RCUs are complete.
+/*
+ * Orchestrate the specified type of RCU barrier, waiting for all
+ * RCU callbacks of the specified type to complete.
  */
-void rcu_barrier(void)
+static void _rcu_barrier(enum rcu_barrier type)
 {
 	BUG_ON(in_interrupt());
 	/* Take cpucontrol mutex to protect against CPU hotplug */
@@ -127,13 +128,39 @@ void rcu_barrier(void)
 	 * until all the callbacks are queued.
 	 */
 	rcu_read_lock();
-	on_each_cpu(rcu_barrier_func, NULL, 0, 1);
+	on_each_cpu(rcu_barrier_func, (void *)type, 0, 1);
 	rcu_read_unlock();
 	wait_for_completion(&rcu_barrier_completion);
 	mutex_unlock(&rcu_barrier_mutex);
 }
+
+/**
+ * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
+ */
+void rcu_barrier(void)
+{
+	_rcu_barrier(RCU_BARRIER_STD);
+}
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
+/**
+ * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ */
+void rcu_barrier_bh(void)
+{
+	_rcu_barrier(RCU_BARRIER_BH);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+
+/**
+ * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
+ */
+void rcu_barrier_sched(void)
+{
+	_rcu_barrier(RCU_BARRIER_SCHED);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+
 void __init rcu_init(void)
 {
 	__rcu_init();
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index c69000fd5c3a..797583bd557c 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -46,11 +46,11 @@
 #include <asm/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
+#include <linux/kthread.h>
 #include <linux/completion.h>
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
 #include <linux/cpu.h>
 #include <linux/random.h>
 #include <linux/delay.h>
@@ -82,14 +82,18 @@ struct rcu_data {
 	spinlock_t	lock;		/* Protect rcu_data fields. */
 	long		completed;	/* Number of last completed batch. */
 	int		waitlistcount;
-	struct tasklet_struct rcu_tasklet;
 	struct rcu_head *nextlist;
 	struct rcu_head **nexttail;
 	struct rcu_head *waitlist[GP_STAGES];
 	struct rcu_head **waittail[GP_STAGES];
-	struct rcu_head *donelist;
+	struct rcu_head *donelist;	/* from waitlist & waitschedlist */
 	struct rcu_head **donetail;
 	long rcu_flipctr[2];
+	struct rcu_head *nextschedlist;
+	struct rcu_head **nextschedtail;
+	struct rcu_head *waitschedlist;
+	struct rcu_head **waitschedtail;
+	int rcu_sched_sleeping;
 #ifdef CONFIG_RCU_TRACE
 	struct rcupreempt_trace trace;
 #endif /* #ifdef CONFIG_RCU_TRACE */
@@ -131,11 +135,24 @@ enum rcu_try_flip_states {
 	rcu_try_flip_waitmb_state,
 };
 
+/*
+ * States for rcu_ctrlblk.rcu_sched_sleep.
+ */
+
+enum rcu_sched_sleep_states {
+	rcu_sched_not_sleeping,	/* Not sleeping, callbacks need GP.  */
+	rcu_sched_sleep_prep,	/* Thinking of sleeping, rechecking. */
+	rcu_sched_sleeping,	/* Sleeping, awaken if GP needed. */
+};
+
 struct rcu_ctrlblk {
 	spinlock_t	fliplock;	/* Protect state-machine transitions. */
 	long		completed;	/* Number of last completed batch. */
 	enum rcu_try_flip_states rcu_try_flip_state; /* The current state of
 							the rcu state machine */
+	spinlock_t	schedlock;	/* Protect rcu_sched sleep state. */
+	enum rcu_sched_sleep_states sched_sleep; /* rcu_sched state. */
+	wait_queue_head_t sched_wq;	/* Place for rcu_sched to sleep. */
 };
 
 static DEFINE_PER_CPU(struct rcu_data, rcu_data);
@@ -143,8 +160,12 @@ static struct rcu_ctrlblk rcu_ctrlblk = {
 	.fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock),
 	.completed = 0,
 	.rcu_try_flip_state = rcu_try_flip_idle_state,
+	.schedlock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.schedlock),
+	.sched_sleep = rcu_sched_not_sleeping,
+	.sched_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rcu_ctrlblk.sched_wq),
 };
 
+static struct task_struct *rcu_sched_grace_period_task;
 
 #ifdef CONFIG_RCU_TRACE
 static char *rcu_try_flip_state_names[] =
@@ -207,6 +228,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_mb_flag_values, rcu_mb_flag)
  */
 #define RCU_TRACE_RDP(f, rdp) RCU_TRACE(f, &((rdp)->trace));
 
+#define RCU_SCHED_BATCH_TIME (HZ / 50)
+
 /*
  * Return the number of RCU batches processed thus far.  Useful
  * for debug and statistics.
@@ -411,32 +434,34 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
 	}
 }
 
-#ifdef CONFIG_NO_HZ
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
+	.dynticks = 1,
+};
 
-DEFINE_PER_CPU(long, dynticks_progress_counter) = 1;
-static DEFINE_PER_CPU(long, rcu_dyntick_snapshot);
+#ifdef CONFIG_NO_HZ
 static DEFINE_PER_CPU(int, rcu_update_flag);
 
 /**
  * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
  *
  * If the CPU was idle with dynamic ticks active, this updates the
- * dynticks_progress_counter to let the RCU handling know that the
+ * rcu_dyntick_sched.dynticks to let the RCU handling know that the
  * CPU is active.
  */
 void rcu_irq_enter(void)
 {
 	int cpu = smp_processor_id();
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
 
 	if (per_cpu(rcu_update_flag, cpu))
 		per_cpu(rcu_update_flag, cpu)++;
 
 	/*
 	 * Only update if we are coming from a stopped ticks mode
-	 * (dynticks_progress_counter is even).
+	 * (rcu_dyntick_sched.dynticks is even).
 	 */
 	if (!in_interrupt() &&
-	    (per_cpu(dynticks_progress_counter, cpu) & 0x1) == 0) {
+	    (rdssp->dynticks & 0x1) == 0) {
 		/*
 		 * The following might seem like we could have a race
 		 * with NMI/SMIs. But this really isn't a problem.
@@ -459,12 +484,12 @@ void rcu_irq_enter(void)
 		 * RCU read-side critical sections on this CPU would
 		 * have already completed.
 		 */
-		per_cpu(dynticks_progress_counter, cpu)++;
+		rdssp->dynticks++;
 		/*
 		 * The following memory barrier ensures that any
 		 * rcu_read_lock() primitives in the irq handler
 		 * are seen by other CPUs to follow the above
-		 * increment to dynticks_progress_counter. This is
+		 * increment to rcu_dyntick_sched.dynticks. This is
 		 * required in order for other CPUs to correctly
 		 * determine when it is safe to advance the RCU
 		 * grace-period state machine.
@@ -472,7 +497,7 @@ void rcu_irq_enter(void)
 		smp_mb(); /* see above block comment. */
 		/*
 		 * Since we can't determine the dynamic tick mode from
-		 * the dynticks_progress_counter after this routine,
+		 * the rcu_dyntick_sched.dynticks after this routine,
 		 * we use a second flag to acknowledge that we came
 		 * from an idle state with ticks stopped.
 		 */
@@ -480,7 +505,7 @@ void rcu_irq_enter(void)
 		/*
 		 * If we take an NMI/SMI now, they will also increment
 		 * the rcu_update_flag, and will not update the
-		 * dynticks_progress_counter on exit. That is for
+		 * rcu_dyntick_sched.dynticks on exit. That is for
 		 * this IRQ to do.
 		 */
 	}
@@ -490,12 +515,13 @@ void rcu_irq_enter(void)
  * rcu_irq_exit - Called from exiting Hard irq context.
  *
  * If the CPU was idle with dynamic ticks active, update the
- * dynticks_progress_counter to put let the RCU handling be
+ * rcu_dyntick_sched.dynticks to put let the RCU handling be
  * aware that the CPU is going back to idle with no ticks.
  */
 void rcu_irq_exit(void)
 {
 	int cpu = smp_processor_id();
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
 
 	/*
 	 * rcu_update_flag is set if we interrupted the CPU
@@ -503,7 +529,7 @@ void rcu_irq_exit(void)
 	 * Once this occurs, we keep track of interrupt nesting
 	 * because a NMI/SMI could also come in, and we still
 	 * only want the IRQ that started the increment of the
-	 * dynticks_progress_counter to be the one that modifies
+	 * rcu_dyntick_sched.dynticks to be the one that modifies
 	 * it on exit.
 	 */
 	if (per_cpu(rcu_update_flag, cpu)) {
@@ -515,28 +541,29 @@ void rcu_irq_exit(void)
 
 		/*
 		 * If an NMI/SMI happens now we are still
-		 * protected by the dynticks_progress_counter being odd.
+		 * protected by the rcu_dyntick_sched.dynticks being odd.
 		 */
 
 		/*
 		 * The following memory barrier ensures that any
 		 * rcu_read_unlock() primitives in the irq handler
 		 * are seen by other CPUs to preceed the following
-		 * increment to dynticks_progress_counter. This
+		 * increment to rcu_dyntick_sched.dynticks. This
 		 * is required in order for other CPUs to determine
 		 * when it is safe to advance the RCU grace-period
 		 * state machine.
 		 */
 		smp_mb(); /* see above block comment. */
-		per_cpu(dynticks_progress_counter, cpu)++;
-		WARN_ON(per_cpu(dynticks_progress_counter, cpu) & 0x1);
+		rdssp->dynticks++;
+		WARN_ON(rdssp->dynticks & 0x1);
 	}
 }
 
 static void dyntick_save_progress_counter(int cpu)
 {
-	per_cpu(rcu_dyntick_snapshot, cpu) =
-		per_cpu(dynticks_progress_counter, cpu);
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->dynticks_snap = rdssp->dynticks;
 }
 
 static inline int
@@ -544,9 +571,10 @@ rcu_try_flip_waitack_needed(int cpu)
 {
 	long curr;
 	long snap;
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
 
-	curr = per_cpu(dynticks_progress_counter, cpu);
-	snap = per_cpu(rcu_dyntick_snapshot, cpu);
+	curr = rdssp->dynticks;
+	snap = rdssp->dynticks_snap;
 	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
 
 	/*
@@ -567,7 +595,7 @@ rcu_try_flip_waitack_needed(int cpu)
 	 * that this CPU already acknowledged the counter.
 	 */
 
-	if ((curr - snap) > 2 || (snap & 0x1) == 0)
+	if ((curr - snap) > 2 || (curr & 0x1) == 0)
 		return 0;
 
 	/* We need this CPU to explicitly acknowledge the counter flip. */
@@ -580,9 +608,10 @@ rcu_try_flip_waitmb_needed(int cpu)
 {
 	long curr;
 	long snap;
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
 
-	curr = per_cpu(dynticks_progress_counter, cpu);
-	snap = per_cpu(rcu_dyntick_snapshot, cpu);
+	curr = rdssp->dynticks;
+	snap = rdssp->dynticks_snap;
 	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
 
 	/*
@@ -609,14 +638,86 @@ rcu_try_flip_waitmb_needed(int cpu)
 	return 1;
 }
 
+static void dyntick_save_progress_counter_sched(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->sched_dynticks_snap = rdssp->dynticks;
+}
+
+static int rcu_qsctr_inc_needed_dyntick(int cpu)
+{
+	long curr;
+	long snap;
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	curr = rdssp->dynticks;
+	snap = rdssp->sched_dynticks_snap;
+	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+	/*
+	 * If the CPU remained in dynticks mode for the entire time
+	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
+	 * then it cannot be in the middle of an rcu_read_lock(), so
+	 * the next rcu_read_lock() it executes must use the new value
+	 * of the counter.  Therefore, this CPU has been in a quiescent
+	 * state the entire time, and we don't need to wait for it.
+	 */
+
+	if ((curr == snap) && ((curr & 0x1) == 0))
+		return 0;
+
+	/*
+	 * If the CPU passed through or entered a dynticks idle phase with
+	 * no active irq handlers, then, as above, this CPU has already
+	 * passed through a quiescent state.
+	 */
+
+	if ((curr - snap) > 2 || (snap & 0x1) == 0)
+		return 0;
+
+	/* We need this CPU to go through a quiescent state. */
+
+	return 1;
+}
+
 #else /* !CONFIG_NO_HZ */
 
-# define dyntick_save_progress_counter(cpu)	do { } while (0)
-# define rcu_try_flip_waitack_needed(cpu)	(1)
-# define rcu_try_flip_waitmb_needed(cpu)	(1)
+# define dyntick_save_progress_counter(cpu)		do { } while (0)
+# define rcu_try_flip_waitack_needed(cpu)		(1)
+# define rcu_try_flip_waitmb_needed(cpu)		(1)
+
+# define dyntick_save_progress_counter_sched(cpu)	do { } while (0)
+# define rcu_qsctr_inc_needed_dyntick(cpu)		(1)
 
 #endif /* CONFIG_NO_HZ */
 
+static void save_qsctr_sched(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->sched_qs_snap = rdssp->sched_qs;
+}
+
+static inline int rcu_qsctr_inc_needed(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	/*
+	 * If there has been a quiescent state, no more need to wait
+	 * on this CPU.
+	 */
+
+	if (rdssp->sched_qs != rdssp->sched_qs_snap) {
+		smp_mb(); /* force ordering with cpu entering schedule(). */
+		return 0;
+	}
+
+	/* We need this CPU to go through a quiescent state. */
+
+	return 1;
+}
+
 /*
  * Get here when RCU is idle.  Decide whether we need to
  * move out of idle state, and return non-zero if so.
@@ -819,6 +920,26 @@ void rcu_check_callbacks(int cpu, int user)
 	unsigned long flags;
 	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
 
+	/*
+	 * If this CPU took its interrupt from user mode or from the
+	 * idle loop, and this is not a nested interrupt, then
+	 * this CPU has to have exited all prior preept-disable
+	 * sections of code.  So increment the counter to note this.
+	 *
+	 * The memory barrier is needed to handle the case where
+	 * writes from a preempt-disable section of code get reordered
+	 * into schedule() by this CPU's write buffer.  So the memory
+	 * barrier makes sure that the rcu_qsctr_inc() is seen by other
+	 * CPUs to happen after any such write.
+	 */
+
+	if (user ||
+	    (idle_cpu(cpu) && !in_softirq() &&
+	     hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+		smp_mb();	/* Guard against aggressive schedule(). */
+	     	rcu_qsctr_inc(cpu);
+	}
+
 	rcu_check_mb(cpu);
 	if (rcu_ctrlblk.completed == rdp->completed)
 		rcu_try_flip();
@@ -869,6 +990,8 @@ void rcu_offline_cpu(int cpu)
 	struct rcu_head *list = NULL;
 	unsigned long flags;
 	struct rcu_data *rdp = RCU_DATA_CPU(cpu);
+	struct rcu_head *schedlist = NULL;
+	struct rcu_head **schedtail = &schedlist;
 	struct rcu_head **tail = &list;
 
 	/*
@@ -882,6 +1005,11 @@ void rcu_offline_cpu(int cpu)
 		rcu_offline_cpu_enqueue(rdp->waitlist[i], rdp->waittail[i],
 						list, tail);
 	rcu_offline_cpu_enqueue(rdp->nextlist, rdp->nexttail, list, tail);
+	rcu_offline_cpu_enqueue(rdp->waitschedlist, rdp->waitschedtail,
+				schedlist, schedtail);
+	rcu_offline_cpu_enqueue(rdp->nextschedlist, rdp->nextschedtail,
+				schedlist, schedtail);
+	rdp->rcu_sched_sleeping = 0;
 	spin_unlock_irqrestore(&rdp->lock, flags);
 	rdp->waitlistcount = 0;
 
@@ -916,22 +1044,40 @@ void rcu_offline_cpu(int cpu)
 	 * fix.
 	 */
 
-	local_irq_save(flags);
+	local_irq_save(flags);  /* disable preempt till we know what lock. */
 	rdp = RCU_DATA_ME();
 	spin_lock(&rdp->lock);
 	*rdp->nexttail = list;
 	if (list)
 		rdp->nexttail = tail;
+	*rdp->nextschedtail = schedlist;
+	if (schedlist)
+		rdp->nextschedtail = schedtail;
 	spin_unlock_irqrestore(&rdp->lock, flags);
 }
 
 void __devinit rcu_online_cpu(int cpu)
 {
 	unsigned long flags;
+	struct rcu_data *rdp;
 
 	spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
 	cpu_set(cpu, rcu_cpu_online_map);
 	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
+
+	/*
+	 * The rcu_sched grace-period processing might have bypassed
+	 * this CPU, given that it was not in the rcu_cpu_online_map
+	 * when the grace-period scan started.  This means that the
+	 * grace-period task might sleep.  So make sure that if this
+	 * should happen, the first callback posted to this CPU will
+	 * wake up the grace-period task if need be.
+	 */
+
+	rdp = RCU_DATA_CPU(cpu);
+	spin_lock_irqsave(&rdp->lock, flags);
+	rdp->rcu_sched_sleeping = 1;
+	spin_unlock_irqrestore(&rdp->lock, flags);
 }
 
 #else /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -986,31 +1132,196 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 	*rdp->nexttail = head;
 	rdp->nexttail = &head->next;
 	RCU_TRACE_RDP(rcupreempt_trace_next_add, rdp);
-	spin_unlock(&rdp->lock);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&rdp->lock, flags);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
+void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	int wake_gp = 0;
+
+	head->func = func;
+	head->next = NULL;
+	local_irq_save(flags);
+	rdp = RCU_DATA_ME();
+	spin_lock(&rdp->lock);
+	*rdp->nextschedtail = head;
+	rdp->nextschedtail = &head->next;
+	if (rdp->rcu_sched_sleeping) {
+
+		/* Grace-period processing might be sleeping... */
+
+		rdp->rcu_sched_sleeping = 0;
+		wake_gp = 1;
+	}
+	spin_unlock_irqrestore(&rdp->lock, flags);
+	if (wake_gp) {
+
+		/* Wake up grace-period processing, unless someone beat us. */
+
+		spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
+		if (rcu_ctrlblk.sched_sleep != rcu_sched_sleeping)
+			wake_gp = 0;
+		rcu_ctrlblk.sched_sleep = rcu_sched_not_sleeping;
+		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+		if (wake_gp)
+			wake_up_interruptible(&rcu_ctrlblk.sched_wq);
+	}
+}
+EXPORT_SYMBOL_GPL(call_rcu_sched);
+
 /*
  * Wait until all currently running preempt_disable() code segments
  * (including hardware-irq-disable segments) complete.  Note that
  * in -rt this does -not- necessarily result in all currently executing
  * interrupt -handlers- having completed.
  */
-void __synchronize_sched(void)
+synchronize_rcu_xxx(__synchronize_sched, call_rcu_sched)
+EXPORT_SYMBOL_GPL(__synchronize_sched);
+
+/*
+ * kthread function that manages call_rcu_sched grace periods.
+ */
+static int rcu_sched_grace_period(void *arg)
 {
-	cpumask_t oldmask;
+	int couldsleep;		/* might sleep after current pass. */
+	int couldsleepnext = 0; /* might sleep after next pass. */
 	int cpu;
+	unsigned long flags;
+	struct rcu_data *rdp;
+	int ret;
 
-	if (sched_getaffinity(0, &oldmask) < 0)
-		oldmask = cpu_possible_map;
-	for_each_online_cpu(cpu) {
-		sched_setaffinity(0, &cpumask_of_cpu(cpu));
-		schedule();
-	}
-	sched_setaffinity(0, &oldmask);
+	/*
+	 * Each pass through the following loop handles one
+	 * rcu_sched grace period cycle.
+	 */
+	do {
+		/* Save each CPU's current state. */
+
+		for_each_online_cpu(cpu) {
+			dyntick_save_progress_counter_sched(cpu);
+			save_qsctr_sched(cpu);
+		}
+
+		/*
+		 * Sleep for about an RCU grace-period's worth to
+		 * allow better batching and to consume less CPU.
+		 */
+		schedule_timeout_interruptible(RCU_SCHED_BATCH_TIME);
+
+		/*
+		 * If there was nothing to do last time, prepare to
+		 * sleep at the end of the current grace period cycle.
+		 */
+		couldsleep = couldsleepnext;
+		couldsleepnext = 1;
+		if (couldsleep) {
+			spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
+			rcu_ctrlblk.sched_sleep = rcu_sched_sleep_prep;
+			spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+		}
+
+		/*
+		 * Wait on each CPU in turn to have either visited
+		 * a quiescent state or been in dynticks-idle mode.
+		 */
+		for_each_online_cpu(cpu) {
+			while (rcu_qsctr_inc_needed(cpu) &&
+			       rcu_qsctr_inc_needed_dyntick(cpu)) {
+				/* resched_cpu(cpu); @@@ */
+				schedule_timeout_interruptible(1);
+			}
+		}
+
+		/* Advance callbacks for each CPU.  */
+
+		for_each_online_cpu(cpu) {
+
+			rdp = RCU_DATA_CPU(cpu);
+			spin_lock_irqsave(&rdp->lock, flags);
+
+			/*
+			 * We are running on this CPU irq-disabled, so no
+			 * CPU can go offline until we re-enable irqs.
+			 * The current CPU might have already gone
+			 * offline (between the for_each_offline_cpu and
+			 * the spin_lock_irqsave), but in that case all its
+			 * callback lists will be empty, so no harm done.
+			 *
+			 * Advance the callbacks!  We share normal RCU's
+			 * donelist, since callbacks are invoked the
+			 * same way in either case.
+			 */
+			if (rdp->waitschedlist != NULL) {
+				*rdp->donetail = rdp->waitschedlist;
+				rdp->donetail = rdp->waitschedtail;
+
+				/*
+				 * Next rcu_check_callbacks() will
+				 * do the required raise_softirq().
+				 */
+			}
+			if (rdp->nextschedlist != NULL) {
+				rdp->waitschedlist = rdp->nextschedlist;
+				rdp->waitschedtail = rdp->nextschedtail;
+				couldsleep = 0;
+				couldsleepnext = 0;
+			} else {
+				rdp->waitschedlist = NULL;
+				rdp->waitschedtail = &rdp->waitschedlist;
+			}
+			rdp->nextschedlist = NULL;
+			rdp->nextschedtail = &rdp->nextschedlist;
+
+			/* Mark sleep intention. */
+
+			rdp->rcu_sched_sleeping = couldsleep;
+
+			spin_unlock_irqrestore(&rdp->lock, flags);
+		}
+
+		/* If we saw callbacks on the last scan, go deal with them. */
+
+		if (!couldsleep)
+			continue;
+
+		/* Attempt to block... */
+
+		spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags);
+		if (rcu_ctrlblk.sched_sleep != rcu_sched_sleep_prep) {
+
+			/*
+			 * Someone posted a callback after we scanned.
+			 * Go take care of it.
+			 */
+			spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+			couldsleepnext = 0;
+			continue;
+		}
+
+		/* Block until the next person posts a callback. */
+
+		rcu_ctrlblk.sched_sleep = rcu_sched_sleeping;
+		spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags);
+		ret = 0;
+		__wait_event_interruptible(rcu_ctrlblk.sched_wq,
+			rcu_ctrlblk.sched_sleep != rcu_sched_sleeping,
+			ret);
+
+		/*
+		 * Signals would prevent us from sleeping, and we cannot
+		 * do much with them in any case.  So flush them.
+		 */
+		if (ret)
+			flush_signals(current);
+		couldsleepnext = 0;
+
+	} while (!kthread_should_stop());
+
+	return (0);
 }
-EXPORT_SYMBOL_GPL(__synchronize_sched);
 
 /*
  * Check to see if any future RCU-related work will need to be done
@@ -1027,7 +1338,9 @@ int rcu_needs_cpu(int cpu)
 
 	return (rdp->donelist != NULL ||
 		!!rdp->waitlistcount ||
-		rdp->nextlist != NULL);
+		rdp->nextlist != NULL ||
+		rdp->nextschedlist != NULL ||
+		rdp->waitschedlist != NULL);
 }
 
 int rcu_pending(int cpu)
@@ -1038,7 +1351,9 @@ int rcu_pending(int cpu)
 
 	if (rdp->donelist != NULL ||
 	    !!rdp->waitlistcount ||
-	    rdp->nextlist != NULL)
+	    rdp->nextlist != NULL ||
+	    rdp->nextschedlist != NULL ||
+	    rdp->waitschedlist != NULL)
 		return 1;
 
 	/* The RCU core needs an acknowledgement from this CPU. */
@@ -1105,6 +1420,11 @@ void __init __rcu_init(void)
 		rdp->donetail = &rdp->donelist;
 		rdp->rcu_flipctr[0] = 0;
 		rdp->rcu_flipctr[1] = 0;
+		rdp->nextschedlist = NULL;
+		rdp->nextschedtail = &rdp->nextschedlist;
+		rdp->waitschedlist = NULL;
+		rdp->waitschedtail = &rdp->waitschedlist;
+		rdp->rcu_sched_sleeping = 0;
 	}
 	register_cpu_notifier(&rcu_nb);
 
@@ -1127,11 +1447,15 @@ void __init __rcu_init(void)
 }
 
 /*
- * Deprecated, use synchronize_rcu() or synchronize_sched() instead.
+ * Late-boot-time RCU initialization that must wait until after scheduler
+ * has been initialized.
  */
-void synchronize_kernel(void)
+void __init rcu_init_sched(void)
 {
-	synchronize_rcu();
+	rcu_sched_grace_period_task = kthread_run(rcu_sched_grace_period,
+						  NULL,
+						  "rcu_sched_grace_period");
+	WARN_ON(IS_ERR(rcu_sched_grace_period_task));
 }
 
 #ifdef CONFIG_RCU_TRACE
diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c
index 49ac4947af24..5edf82c34bbc 100644
--- a/kernel/rcupreempt_trace.c
+++ b/kernel/rcupreempt_trace.c
@@ -38,7 +38,6 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
-#include <linux/rcupdate.h>
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/rcupreempt_trace.h>
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 33acc424667e..5e954edf0ed5 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -57,7 +57,8 @@ static int stat_interval;	/* Interval between stats, in seconds. */
 				/*  Defaults to "only at end of test". */
 static int verbose;		/* Print more debug info. */
 static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
-static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/
+static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
+static int stutter = 5;		/* Start/stop testing interval (in sec) */
 static char *torture_type = "rcu"; /* What RCU implementation to torture. */
 
 module_param(nreaders, int, 0444);
@@ -72,6 +73,8 @@ module_param(test_no_idle_hz, bool, 0444);
 MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
 module_param(shuffle_interval, int, 0444);
 MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
+module_param(stutter, int, 0444);
+MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
 
@@ -91,6 +94,7 @@ static struct task_struct **fakewriter_tasks;
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
 static struct task_struct *shuffler_task;
+static struct task_struct *stutter_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -119,6 +123,15 @@ static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
 static struct list_head rcu_torture_removed;
 
+static int stutter_pause_test = 0;
+
+#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
+#define RCUTORTURE_RUNNABLE_INIT 1
+#else
+#define RCUTORTURE_RUNNABLE_INIT 0
+#endif
+int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -179,6 +192,16 @@ rcu_random(struct rcu_random_state *rrsp)
 	return swahw32(rrsp->rrs_state);
 }
 
+static void
+rcu_stutter_wait(void)
+{
+	while (stutter_pause_test || !rcutorture_runnable)
+		if (rcutorture_runnable)
+			schedule_timeout_interruptible(1);
+		else
+			schedule_timeout_interruptible(round_jiffies_relative(HZ));
+}
+
 /*
  * Operations vector for selecting different types of tests.
  */
@@ -192,6 +215,7 @@ struct rcu_torture_ops {
 	int (*completed)(void);
 	void (*deferredfree)(struct rcu_torture *p);
 	void (*sync)(void);
+	void (*cb_barrier)(void);
 	int (*stats)(char *page);
 	char *name;
 };
@@ -265,6 +289,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.completed = rcu_torture_completed,
 	.deferredfree = rcu_torture_deferred_free,
 	.sync = synchronize_rcu,
+	.cb_barrier = rcu_barrier,
 	.stats = NULL,
 	.name = "rcu"
 };
@@ -304,6 +329,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
 	.completed = rcu_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = synchronize_rcu,
+	.cb_barrier = NULL,
 	.stats = NULL,
 	.name = "rcu_sync"
 };
@@ -364,6 +390,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.completed = rcu_bh_torture_completed,
 	.deferredfree = rcu_bh_torture_deferred_free,
 	.sync = rcu_bh_torture_synchronize,
+	.cb_barrier = rcu_barrier_bh,
 	.stats = NULL,
 	.name = "rcu_bh"
 };
@@ -377,6 +404,7 @@ static struct rcu_torture_ops rcu_bh_sync_ops = {
 	.completed = rcu_bh_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = rcu_bh_torture_synchronize,
+	.cb_barrier = NULL,
 	.stats = NULL,
 	.name = "rcu_bh_sync"
 };
@@ -458,6 +486,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.completed = srcu_torture_completed,
 	.deferredfree = rcu_sync_torture_deferred_free,
 	.sync = srcu_torture_synchronize,
+	.cb_barrier = NULL,
 	.stats = srcu_torture_stats,
 	.name = "srcu"
 };
@@ -482,6 +511,11 @@ static int sched_torture_completed(void)
 	return 0;
 }
 
+static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
+}
+
 static void sched_torture_synchronize(void)
 {
 	synchronize_sched();
@@ -494,12 +528,27 @@ static struct rcu_torture_ops sched_ops = {
 	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock = sched_torture_read_unlock,
 	.completed = sched_torture_completed,
-	.deferredfree = rcu_sync_torture_deferred_free,
+	.deferredfree = rcu_sched_torture_deferred_free,
 	.sync = sched_torture_synchronize,
+	.cb_barrier = rcu_barrier_sched,
 	.stats = NULL,
 	.name = "sched"
 };
 
+static struct rcu_torture_ops sched_ops_sync = {
+	.init = rcu_sync_torture_init,
+	.cleanup = NULL,
+	.readlock = sched_torture_read_lock,
+	.readdelay = rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock = sched_torture_read_unlock,
+	.completed = sched_torture_completed,
+	.deferredfree = rcu_sync_torture_deferred_free,
+	.sync = sched_torture_synchronize,
+	.cb_barrier = NULL,
+	.stats = NULL,
+	.name = "sched_sync"
+};
+
 /*
  * RCU torture writer kthread.  Repeatedly substitutes a new structure
  * for that pointed to by rcu_torture_current, freeing the old structure
@@ -537,6 +586,7 @@ rcu_torture_writer(void *arg)
 		}
 		rcu_torture_current_version++;
 		oldbatch = cur_ops->completed();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
 	while (!kthread_should_stop())
@@ -560,6 +610,7 @@ rcu_torture_fakewriter(void *arg)
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		cur_ops->sync();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
@@ -615,6 +666,7 @@ rcu_torture_reader(void *arg)
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
+		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
 	while (!kthread_should_stop())
@@ -661,6 +713,7 @@ rcu_torture_printk(char *page)
 	if (i > 1) {
 		cnt += sprintf(&page[cnt], "!!! ");
 		atomic_inc(&n_rcu_torture_error);
+		WARN_ON_ONCE(1);
 	}
 	cnt += sprintf(&page[cnt], "Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -785,15 +838,34 @@ rcu_torture_shuffle(void *arg)
 	return 0;
 }
 
+/* Cause the rcutorture test to "stutter", starting and stopping all
+ * threads periodically.
+ */
+static int
+rcu_torture_stutter(void *arg)
+{
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task started");
+	do {
+		schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 1;
+		if (!kthread_should_stop())
+			schedule_timeout_interruptible(stutter * HZ);
+		stutter_pause_test = 0;
+	} while (!kthread_should_stop());
+	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
+	return 0;
+}
+
 static inline void
 rcu_torture_print_module_parms(char *tag)
 {
 	printk(KERN_ALERT "%s" TORTURE_FLAG
 		"--- %s: nreaders=%d nfakewriters=%d "
 		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval = %d\n",
+		"shuffle_interval=%d stutter=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
-		stat_interval, verbose, test_no_idle_hz, shuffle_interval);
+		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+		stutter);
 }
 
 static void
@@ -802,6 +874,11 @@ rcu_torture_cleanup(void)
 	int i;
 
 	fullstop = 1;
+	if (stutter_task) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
+		kthread_stop(stutter_task);
+	}
+	stutter_task = NULL;
 	if (shuffler_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
 		kthread_stop(shuffler_task);
@@ -848,7 +925,9 @@ rcu_torture_cleanup(void)
 	stats_task = NULL;
 
 	/* Wait for all RCU callbacks to fire.  */
-	rcu_barrier();
+
+	if (cur_ops->cb_barrier != NULL)
+		cur_ops->cb_barrier();
 
 	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
 
@@ -868,7 +947,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
-		  &srcu_ops, &sched_ops, };
+		  &srcu_ops, &sched_ops, &sched_ops_sync, };
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
@@ -988,6 +1067,19 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
+	if (stutter < 0)
+		stutter = 0;
+	if (stutter) {
+		/* Create the stutter thread */
+		stutter_task = kthread_run(rcu_torture_stutter, NULL,
+					  "rcu_torture_stutter");
+		if (IS_ERR(stutter_task)) {
+			firsterr = PTR_ERR(stutter_task);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create stutter");
+			stutter_task = NULL;
+			goto unwind;
+		}
+	}
 	return 0;
 
 unwind:
diff --git a/kernel/sched.c b/kernel/sched.c
index f7e6938a4f35..8970124e027f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,6 +75,8 @@
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 
+#include "sched_cpupri.h"
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
@@ -290,15 +292,15 @@ struct task_group root_task_group;
 static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
 /* Default task group's cfs_rq on each cpu */
 static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
-#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
 static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
-#endif
-#else
+#endif /* CONFIG_RT_GROUP_SCHED */
+#else /* !CONFIG_FAIR_GROUP_SCHED */
 #define root_task_group init_task_group
-#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 /* task_group_lock serializes add/remove of task groups and also changes to
  * a task group's cpu shares.
@@ -308,9 +310,9 @@ static DEFINE_SPINLOCK(task_group_lock);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
-#else
+#else /* !CONFIG_USER_SCHED */
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
-#endif
+#endif /* CONFIG_USER_SCHED */
 
 /*
  * A weight of 0 or 1 can cause arithmetics problems.
@@ -453,6 +455,9 @@ struct root_domain {
 	 */
 	cpumask_t rto_mask;
 	atomic_t rto_count;
+#ifdef CONFIG_SMP
+	struct cpupri cpupri;
+#endif
 };
 
 /*
@@ -527,6 +532,7 @@ struct rq {
 	int push_cpu;
 	/* cpu of this runqueue: */
 	int cpu;
+	int online;
 
 	struct task_struct *migration_thread;
 	struct list_head migration_queue;
@@ -1332,15 +1338,15 @@ void wake_up_idle_cpu(int cpu)
 	if (!tsk_is_polling(rq->idle))
 		smp_send_reschedule(cpu);
 }
-#endif
+#endif /* CONFIG_NO_HZ */
 
-#else
+#else /* !CONFIG_SMP */
 static void __resched_task(struct task_struct *p, int tif_bit)
 {
 	assert_spin_locked(&task_rq(p)->lock);
 	set_tsk_thread_flag(p, tif_bit);
 }
-#endif
+#endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
 # define WMULT_CONST	(~0UL)
@@ -1500,16 +1506,8 @@ static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
 static unsigned long cpu_avg_load_per_task(int cpu);
 static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
-#else /* CONFIG_SMP */
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
-{
-}
 #endif
 
-#endif /* CONFIG_SMP */
-
 #include "sched_stats.h"
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -1519,6 +1517,8 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 #endif
 
 #define sched_class_highest (&rt_sched_class)
+#define for_each_class(class) \
+   for (class = sched_class_highest; class; class = class->next)
 
 static inline void inc_load(struct rq *rq, const struct task_struct *p)
 {
@@ -1655,12 +1655,6 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
-/* Used instead of source_load when we know the type == 0 */
-unsigned long weighted_cpuload(const int cpu)
-{
-	return cpu_rq(cpu)->load.weight;
-}
-
 static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 {
 	set_task_rq(p, cpu);
@@ -1689,6 +1683,12 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 
 #ifdef CONFIG_SMP
 
+/* Used instead of source_load when we know the type == 0 */
+static unsigned long weighted_cpuload(const int cpu)
+{
+	return cpu_rq(cpu)->load.weight;
+}
+
 /*
  * Is this task likely cache-hot:
  */
@@ -2150,7 +2150,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 			}
 		}
 	}
-#endif
+#endif /* CONFIG_SCHEDSTATS */
 
 out_activate:
 #endif /* CONFIG_SMP */
@@ -2356,7 +2356,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 		notifier->ops->sched_out(notifier, next);
 }
 
-#else
+#else /* !CONFIG_PREEMPT_NOTIFIERS */
 
 static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
@@ -2368,7 +2368,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 {
 }
 
-#endif
+#endif /* CONFIG_PREEMPT_NOTIFIERS */
 
 /**
  * prepare_task_switch - prepare to switch tasks
@@ -3702,6 +3702,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	/* Earliest time when we have to do rebalance again */
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
+	int need_serialize;
 	cpumask_t tmp;
 
 	for_each_domain(cpu, sd) {
@@ -3719,8 +3720,9 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		if (interval > HZ*NR_CPUS/10)
 			interval = HZ*NR_CPUS/10;
 
+		need_serialize = sd->flags & SD_SERIALIZE;
 
-		if (sd->flags & SD_SERIALIZE) {
+		if (need_serialize) {
 			if (!spin_trylock(&balancing))
 				goto out;
 		}
@@ -3736,7 +3738,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 			}
 			sd->last_balance = jiffies;
 		}
-		if (sd->flags & SD_SERIALIZE)
+		if (need_serialize)
 			spin_unlock(&balancing);
 out:
 		if (time_after(next_balance, sd->last_balance + interval)) {
@@ -4121,6 +4123,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 		prev->comm, prev->pid, preempt_count());
 
 	debug_show_held_locks(prev);
+	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
 
@@ -4194,7 +4197,7 @@ asmlinkage void __sched schedule(void)
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;
-	int cpu;
+	int cpu, hrtick = sched_feat(HRTICK);
 
 need_resched:
 	preempt_disable();
@@ -4209,7 +4212,8 @@ need_resched_nonpreemptible:
 
 	schedule_debug(prev);
 
-	hrtick_clear(rq);
+	if (hrtick)
+		hrtick_clear(rq);
 
 	/*
 	 * Do the rq-clock update outside the rq lock:
@@ -4255,7 +4259,8 @@ need_resched_nonpreemptible:
 	} else
 		spin_unlock_irq(&rq->lock);
 
-	hrtick_set(rq);
+	if (hrtick)
+		hrtick_set(rq);
 
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
@@ -4795,16 +4800,8 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
 	set_load_weight(p);
 }
 
-/**
- * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
- * @p: the task in question.
- * @policy: new policy.
- * @param: structure containing the new RT priority.
- *
- * NOTE that the task may be already dead.
- */
-int sched_setscheduler(struct task_struct *p, int policy,
-		       struct sched_param *param)
+static int __sched_setscheduler(struct task_struct *p, int policy,
+				struct sched_param *param, bool user)
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	unsigned long flags;
@@ -4836,7 +4833,7 @@ recheck:
 	/*
 	 * Allow unprivileged RT tasks to decrease priority:
 	 */
-	if (!capable(CAP_SYS_NICE)) {
+	if (user && !capable(CAP_SYS_NICE)) {
 		if (rt_policy(policy)) {
 			unsigned long rlim_rtprio;
 
@@ -4872,7 +4869,8 @@ recheck:
 	 * Do not allow realtime tasks into groups that have no runtime
 	 * assigned.
 	 */
-	if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+	if (user
+	    && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
 		return -EPERM;
 #endif
 
@@ -4921,8 +4919,39 @@ recheck:
 
 	return 0;
 }
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+		       struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, true);
+}
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
+/**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission.  For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+			       struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, false);
+}
+
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
@@ -5121,24 +5150,6 @@ asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 	return sched_setaffinity(pid, &new_mask);
 }
 
-/*
- * Represents all cpu's present in the system
- * In systems capable of hotplug, this map could dynamically grow
- * as new cpu's are detected in the system via any platform specific
- * method, such as ACPI for e.g.
- */
-
-cpumask_t cpu_present_map __read_mostly;
-EXPORT_SYMBOL(cpu_present_map);
-
-#ifndef CONFIG_SMP
-cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_online_map);
-
-cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_possible_map);
-#endif
-
 long sched_getaffinity(pid_t pid, cpumask_t *mask)
 {
 	struct task_struct *p;
@@ -5622,6 +5633,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
 		goto out;
 	}
 
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
+		     !cpus_equal(p->cpus_allowed, *new_mask))) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (p->sched_class->set_cpus_allowed)
 		p->sched_class->set_cpus_allowed(p, new_mask);
 	else {
@@ -6109,6 +6126,36 @@ static void unregister_sched_domain_sysctl(void)
 }
 #endif
 
+static void set_rq_online(struct rq *rq)
+{
+	if (!rq->online) {
+		const struct sched_class *class;
+
+		cpu_set(rq->cpu, rq->rd->online);
+		rq->online = 1;
+
+		for_each_class(class) {
+			if (class->rq_online)
+				class->rq_online(rq);
+		}
+	}
+}
+
+static void set_rq_offline(struct rq *rq)
+{
+	if (rq->online) {
+		const struct sched_class *class;
+
+		for_each_class(class) {
+			if (class->rq_offline)
+				class->rq_offline(rq);
+		}
+
+		cpu_clear(rq->cpu, rq->rd->online);
+		rq->online = 0;
+	}
+}
+
 /*
  * migration_call - callback that gets triggered when a CPU is added.
  * Here we can start up the necessary migration thread for the new CPU.
@@ -6146,7 +6193,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpu_isset(cpu, rq->rd->span));
-			cpu_set(cpu, rq->rd->online);
+
+			set_rq_online(rq);
 		}
 		spin_unlock_irqrestore(&rq->lock, flags);
 		break;
@@ -6207,7 +6255,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpu_isset(cpu, rq->rd->span));
-			cpu_clear(cpu, rq->rd->online);
+			set_rq_offline(rq);
 		}
 		spin_unlock_irqrestore(&rq->lock, flags);
 		break;
@@ -6241,6 +6289,28 @@ void __init migration_init(void)
 
 #ifdef CONFIG_SCHED_DEBUG
 
+static inline const char *sd_level_to_string(enum sched_domain_level lvl)
+{
+	switch (lvl) {
+	case SD_LV_NONE:
+			return "NONE";
+	case SD_LV_SIBLING:
+			return "SIBLING";
+	case SD_LV_MC:
+			return "MC";
+	case SD_LV_CPU:
+			return "CPU";
+	case SD_LV_NODE:
+			return "NODE";
+	case SD_LV_ALLNODES:
+			return "ALLNODES";
+	case SD_LV_MAX:
+			return "MAX";
+
+	}
+	return "MAX";
+}
+
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  cpumask_t *groupmask)
 {
@@ -6260,7 +6330,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %s\n", str);
+	printk(KERN_CONT "span %s level %s\n",
+		str, sd_level_to_string(sd->level));
 
 	if (!cpu_isset(cpu, sd->span)) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
@@ -6344,9 +6415,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 	}
 	kfree(groupmask);
 }
-#else
+#else /* !CONFIG_SCHED_DEBUG */
 # define sched_domain_debug(sd, cpu) do { } while (0)
-#endif
+#endif /* CONFIG_SCHED_DEBUG */
 
 static int sd_degenerate(struct sched_domain *sd)
 {
@@ -6406,20 +6477,16 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
 	unsigned long flags;
-	const struct sched_class *class;
 
 	spin_lock_irqsave(&rq->lock, flags);
 
 	if (rq->rd) {
 		struct root_domain *old_rd = rq->rd;
 
-		for (class = sched_class_highest; class; class = class->next) {
-			if (class->leave_domain)
-				class->leave_domain(rq);
-		}
+		if (cpu_isset(rq->cpu, old_rd->online))
+			set_rq_offline(rq);
 
 		cpu_clear(rq->cpu, old_rd->span);
-		cpu_clear(rq->cpu, old_rd->online);
 
 		if (atomic_dec_and_test(&old_rd->refcount))
 			kfree(old_rd);
@@ -6430,12 +6497,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 
 	cpu_set(rq->cpu, rd->span);
 	if (cpu_isset(rq->cpu, cpu_online_map))
-		cpu_set(rq->cpu, rd->online);
-
-	for (class = sched_class_highest; class; class = class->next) {
-		if (class->join_domain)
-			class->join_domain(rq);
-	}
+		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
 }
@@ -6446,6 +6508,8 @@ static void init_rootdomain(struct root_domain *rd)
 
 	cpus_clear(rd->span);
 	cpus_clear(rd->online);
+
+	cpupri_init(&rd->cpupri);
 }
 
 static void init_defrootdomain(void)
@@ -6640,7 +6704,7 @@ static void sched_domain_node_span(int node, cpumask_t *span)
 		cpus_or(*span, *span, *nodemask);
 	}
 }
-#endif
+#endif /* CONFIG_NUMA */
 
 int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
@@ -6659,7 +6723,7 @@ cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
 		*sg = &per_cpu(sched_group_cpus, cpu);
 	return cpu;
 }
-#endif
+#endif /* CONFIG_SCHED_SMT */
 
 /*
  * multi-core sched-domains:
@@ -6667,7 +6731,7 @@ cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct sched_domain, core_domains);
 static DEFINE_PER_CPU(struct sched_group, sched_group_core);
-#endif
+#endif /* CONFIG_SCHED_MC */
 
 #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
@@ -6769,7 +6833,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 		sg = sg->next;
 	} while (sg != group_head);
 }
-#endif
+#endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_NUMA
 /* Free memory allocated for various sched_group structures */
@@ -6806,11 +6870,11 @@ next_sg:
 		sched_group_nodes_bycpu[cpu] = NULL;
 	}
 }
-#else
+#else /* !CONFIG_NUMA */
 static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
 {
 }
-#endif
+#endif /* CONFIG_NUMA */
 
 /*
  * Initialize sched groups cpu_power.
@@ -7519,7 +7583,7 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 #endif
 	return err;
 }
-#endif
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
 /*
  * Force a reinitialization of the sched domains hierarchy. The domains
@@ -7530,21 +7594,28 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 static int update_sched_domains(struct notifier_block *nfb,
 				unsigned long action, void *hcpu)
 {
+	int cpu = (int)(long)hcpu;
+
 	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
+		disable_runtime(cpu_rq(cpu));
+		/* fall-through */
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		detach_destroy_domains(&cpu_online_map);
 		free_sched_domains();
 		return NOTIFY_OK;
 
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
+
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
+		enable_runtime(cpu_rq(cpu));
+		/* fall-through */
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		/*
@@ -7744,8 +7815,8 @@ void __init sched_init(void)
 
 		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
-#endif
-#endif
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		init_task_group.rt_se = (struct sched_rt_entity **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
@@ -7759,8 +7830,8 @@ void __init sched_init(void)
 
 		root_task_group.rt_rq = (struct rt_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
-#endif
-#endif
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_RT_GROUP_SCHED */
 	}
 
 #ifdef CONFIG_SMP
@@ -7776,8 +7847,8 @@ void __init sched_init(void)
 #ifdef CONFIG_USER_SCHED
 	init_rt_bandwidth(&root_task_group.rt_bandwidth,
 			global_rt_period(), RUNTIME_INF);
-#endif
-#endif
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_GROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
@@ -7787,8 +7858,8 @@ void __init sched_init(void)
 	INIT_LIST_HEAD(&root_task_group.children);
 	init_task_group.parent = &root_task_group;
 	list_add(&init_task_group.siblings, &root_task_group.children);
-#endif
-#endif
+#endif /* CONFIG_USER_SCHED */
+#endif /* CONFIG_GROUP_SCHED */
 
 	for_each_possible_cpu(i) {
 		struct rq *rq;
@@ -7868,6 +7939,7 @@ void __init sched_init(void)
 		rq->next_balance = jiffies;
 		rq->push_cpu = 0;
 		rq->cpu = i;
+		rq->online = 0;
 		rq->migration_thread = NULL;
 		INIT_LIST_HEAD(&rq->migration_queue);
 		rq_attach_root(rq, &def_root_domain);
@@ -8107,7 +8179,7 @@ static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 {
 	list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
 }
-#else
+#else /* !CONFG_FAIR_GROUP_SCHED */
 static inline void free_fair_sched_group(struct task_group *tg)
 {
 }
@@ -8125,7 +8197,7 @@ static inline void register_fair_sched_group(struct task_group *tg, int cpu)
 static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 {
 }
-#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static void free_rt_sched_group(struct task_group *tg)
@@ -8196,7 +8268,7 @@ static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
 {
 	list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
 }
-#else
+#else /* !CONFIG_RT_GROUP_SCHED */
 static inline void free_rt_sched_group(struct task_group *tg)
 {
 }
@@ -8214,7 +8286,7 @@ static inline void register_rt_sched_group(struct task_group *tg, int cpu)
 static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
 {
 }
-#endif
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_GROUP_SCHED
 static void free_sched_group(struct task_group *tg)
@@ -8325,7 +8397,7 @@ void sched_move_task(struct task_struct *tsk)
 
 	task_rq_unlock(rq, &flags);
 }
-#endif
+#endif /* CONFIG_GROUP_SCHED */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void set_se_shares(struct sched_entity *se, unsigned long shares)
@@ -8425,7 +8497,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_CGROUP_SCHED
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-	struct task_group *tgi, *parent = tg ? tg->parent : NULL;
+	struct task_group *tgi, *parent = tg->parent;
 	unsigned long total = 0;
 
 	if (!parent) {
@@ -8449,7 +8521,7 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 	}
 	rcu_read_unlock();
 
-	return total + to_ratio(period, runtime) <
+	return total + to_ratio(period, runtime) <=
 		to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period),
 				parent->rt_bandwidth.rt_runtime);
 }
@@ -8566,16 +8638,21 @@ long sched_group_rt_period(struct task_group *tg)
 
 static int sched_rt_global_constraints(void)
 {
+	struct task_group *tg = &root_task_group;
+	u64 rt_runtime, rt_period;
 	int ret = 0;
 
+	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	rt_runtime = tg->rt_bandwidth.rt_runtime;
+
 	mutex_lock(&rt_constraints_mutex);
-	if (!__rt_schedulable(NULL, 1, 0))
+	if (!__rt_schedulable(tg, rt_period, rt_runtime))
 		ret = -EINVAL;
 	mutex_unlock(&rt_constraints_mutex);
 
 	return ret;
 }
-#else
+#else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
 	unsigned long flags;
@@ -8593,7 +8670,7 @@ static int sched_rt_global_constraints(void)
 
 	return 0;
 }
-#endif
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 int sched_rt_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
@@ -8701,7 +8778,7 @@ static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
 
 	return (u64) tg->shares;
 }
-#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
@@ -8725,7 +8802,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft)
 {
 	return sched_group_rt_period(cgroup_tg(cgrp));
 }
-#endif
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 static struct cftype cpu_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
new file mode 100644
index 000000000000..52154fefab7e
--- /dev/null
+++ b/kernel/sched_cpupri.c
@@ -0,0 +1,174 @@
+/*
+ *  kernel/sched_cpupri.c
+ *
+ *  CPU priority management
+ *
+ *  Copyright (C) 2007-2008 Novell
+ *
+ *  Author: Gregory Haskins <ghaskins@novell.com>
+ *
+ *  This code tracks the priority of each CPU so that global migration
+ *  decisions are easy to calculate.  Each CPU can be in a state as follows:
+ *
+ *                 (INVALID), IDLE, NORMAL, RT1, ... RT99
+ *
+ *  going from the lowest priority to the highest.  CPUs in the INVALID state
+ *  are not eligible for routing.  The system maintains this state with
+ *  a 2 dimensional bitmap (the first for priority class, the second for cpus
+ *  in that class).  Therefore a typical application without affinity
+ *  restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
+ *  searches).  For tasks with affinity restrictions, the algorithm has a
+ *  worst case complexity of O(min(102, nr_domcpus)), though the scenario that
+ *  yields the worst case search is fairly contrived.
+ *
+ *  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; version 2
+ *  of the License.
+ */
+
+#include "sched_cpupri.h"
+
+/* Convert between a 140 based task->prio, and our 102 based cpupri */
+static int convert_prio(int prio)
+{
+	int cpupri;
+
+	if (prio == CPUPRI_INVALID)
+		cpupri = CPUPRI_INVALID;
+	else if (prio == MAX_PRIO)
+		cpupri = CPUPRI_IDLE;
+	else if (prio >= MAX_RT_PRIO)
+		cpupri = CPUPRI_NORMAL;
+	else
+		cpupri = MAX_RT_PRIO - prio + 1;
+
+	return cpupri;
+}
+
+#define for_each_cpupri_active(array, idx)                    \
+  for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES);     \
+       idx < CPUPRI_NR_PRIORITIES;                            \
+       idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1))
+
+/**
+ * cpupri_find - find the best (lowest-pri) CPU in the system
+ * @cp: The cpupri context
+ * @p: The task
+ * @lowest_mask: A mask to fill in with selected CPUs
+ *
+ * Note: This function returns the recommended CPUs as calculated during the
+ * current invokation.  By the time the call returns, the CPUs may have in
+ * fact changed priorities any number of times.  While not ideal, it is not
+ * an issue of correctness since the normal rebalancer logic will correct
+ * any discrepancies created by racing against the uncertainty of the current
+ * priority configuration.
+ *
+ * Returns: (int)bool - CPUs were found
+ */
+int cpupri_find(struct cpupri *cp, struct task_struct *p,
+		cpumask_t *lowest_mask)
+{
+	int                  idx      = 0;
+	int                  task_pri = convert_prio(p->prio);
+
+	for_each_cpupri_active(cp->pri_active, idx) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
+		cpumask_t mask;
+
+		if (idx >= task_pri)
+			break;
+
+		cpus_and(mask, p->cpus_allowed, vec->mask);
+
+		if (cpus_empty(mask))
+			continue;
+
+		*lowest_mask = mask;
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * cpupri_set - update the cpu priority setting
+ * @cp: The cpupri context
+ * @cpu: The target cpu
+ * @pri: The priority (INVALID-RT99) to assign to this CPU
+ *
+ * Note: Assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpupri_set(struct cpupri *cp, int cpu, int newpri)
+{
+	int                 *currpri = &cp->cpu_to_pri[cpu];
+	int                  oldpri  = *currpri;
+	unsigned long        flags;
+
+	newpri = convert_prio(newpri);
+
+	BUG_ON(newpri >= CPUPRI_NR_PRIORITIES);
+
+	if (newpri == oldpri)
+		return;
+
+	/*
+	 * If the cpu was currently mapped to a different value, we
+	 * first need to unmap the old value
+	 */
+	if (likely(oldpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
+
+		spin_lock_irqsave(&vec->lock, flags);
+
+		vec->count--;
+		if (!vec->count)
+			clear_bit(oldpri, cp->pri_active);
+		cpu_clear(cpu, vec->mask);
+
+		spin_unlock_irqrestore(&vec->lock, flags);
+	}
+
+	if (likely(newpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
+
+		spin_lock_irqsave(&vec->lock, flags);
+
+		cpu_set(cpu, vec->mask);
+		vec->count++;
+		if (vec->count == 1)
+			set_bit(newpri, cp->pri_active);
+
+		spin_unlock_irqrestore(&vec->lock, flags);
+	}
+
+	*currpri = newpri;
+}
+
+/**
+ * cpupri_init - initialize the cpupri structure
+ * @cp: The cpupri context
+ *
+ * Returns: (void)
+ */
+void cpupri_init(struct cpupri *cp)
+{
+	int i;
+
+	memset(cp, 0, sizeof(*cp));
+
+	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
+		struct cpupri_vec *vec = &cp->pri_to_cpu[i];
+
+		spin_lock_init(&vec->lock);
+		vec->count = 0;
+		cpus_clear(vec->mask);
+	}
+
+	for_each_possible_cpu(i)
+		cp->cpu_to_pri[i] = CPUPRI_INVALID;
+}
+
+
diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h
new file mode 100644
index 000000000000..f25811b0f931
--- /dev/null
+++ b/kernel/sched_cpupri.h
@@ -0,0 +1,36 @@
+#ifndef _LINUX_CPUPRI_H
+#define _LINUX_CPUPRI_H
+
+#include <linux/sched.h>
+
+#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO + 2)
+#define CPUPRI_NR_PRI_WORDS	BITS_TO_LONGS(CPUPRI_NR_PRIORITIES)
+
+#define CPUPRI_INVALID -1
+#define CPUPRI_IDLE     0
+#define CPUPRI_NORMAL   1
+/* values 2-101 are RT priorities 0-99 */
+
+struct cpupri_vec {
+	spinlock_t lock;
+	int        count;
+	cpumask_t  mask;
+};
+
+struct cpupri {
+	struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
+	long              pri_active[CPUPRI_NR_PRI_WORDS];
+	int               cpu_to_pri[NR_CPUS];
+};
+
+#ifdef CONFIG_SMP
+int  cpupri_find(struct cpupri *cp,
+		 struct task_struct *p, cpumask_t *lowest_mask);
+void cpupri_set(struct cpupri *cp, int cpu, int pri);
+void cpupri_init(struct cpupri *cp);
+#else
+#define cpupri_set(cp, cpu, pri) do { } while (0)
+#define cpupri_init() do { } while (0)
+#endif
+
+#endif /* _LINUX_CPUPRI_H */
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 8bb713040ac9..8e077b9c91cb 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -119,9 +119,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	struct sched_entity *last;
 	unsigned long flags;
 
-#if !defined(CONFIG_CGROUP_SCHED) || !defined(CONFIG_USER_SCHED)
-	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
-#else
+#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
 	char path[128] = "";
 	struct cgroup *cgroup = NULL;
 	struct task_group *tg = cfs_rq->tg;
@@ -133,6 +131,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 		cgroup_path(cgroup, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
+#else
+	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
 
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
@@ -169,6 +169,39 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->nr_spread_over);
 }
 
+void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
+{
+#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
+	char path[128] = "";
+	struct cgroup *cgroup = NULL;
+	struct task_group *tg = rt_rq->tg;
+
+	if (tg)
+		cgroup = tg->css.cgroup;
+
+	if (cgroup)
+		cgroup_path(cgroup, path, sizeof(path));
+
+	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
+#else
+	SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
+#endif
+
+
+#define P(x) \
+	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
+#define PN(x) \
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
+
+	P(rt_nr_running);
+	P(rt_throttled);
+	PN(rt_time);
+	PN(rt_runtime);
+
+#undef PN
+#undef P
+}
+
 static void print_cpu(struct seq_file *m, int cpu)
 {
 	struct rq *rq = &per_cpu(runqueues, cpu);
@@ -208,6 +241,7 @@ static void print_cpu(struct seq_file *m, int cpu)
 #undef PN
 
 	print_cfs_stats(m, cpu);
+	print_rt_stats(m, cpu);
 
 	print_rq(m, rq, cpu);
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 74774bde5264..0152dbd0b77a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1275,23 +1275,18 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
 	struct task_struct *p = NULL;
 	struct sched_entity *se;
 
-	if (next == &cfs_rq->tasks)
-		return NULL;
-
-	/* Skip over entities that are not tasks */
-	do {
+	while (next != &cfs_rq->tasks) {
 		se = list_entry(next, struct sched_entity, group_node);
 		next = next->next;
-	} while (next != &cfs_rq->tasks && !entity_is_task(se));
 
-	if (next == &cfs_rq->tasks)
-		return NULL;
+		/* Skip over entities that are not tasks */
+		if (entity_is_task(se)) {
+			p = task_of(se);
+			break;
+		}
+	}
 
 	cfs_rq->balance_iterator = next;
-
-	if (entity_is_task(se))
-		p = task_of(se);
-
 	return p;
 }
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 1c7283cb9581..62b39ca92ebd 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -6,5 +6,3 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 SCHED_FEAT(SYNC_WAKEUPS, 1)
 SCHED_FEAT(HRTICK, 1)
 SCHED_FEAT(DOUBLE_TICK, 0)
-SCHED_FEAT(NORMALIZED_SLEEPER, 1)
-SCHED_FEAT(DEADLINE, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index e757f370eb1b..405f8c6226a9 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -12,6 +12,9 @@ static inline int rt_overloaded(struct rq *rq)
 
 static inline void rt_set_overload(struct rq *rq)
 {
+	if (!rq->online)
+		return;
+
 	cpu_set(rq->cpu, rq->rd->rto_mask);
 	/*
 	 * Make sure the mask is visible before we set
@@ -26,6 +29,9 @@ static inline void rt_set_overload(struct rq *rq)
 
 static inline void rt_clear_overload(struct rq *rq)
 {
+	if (!rq->online)
+		return;
+
 	/* the order here really doesn't matter */
 	atomic_dec(&rq->rd->rto_count);
 	cpu_clear(rq->cpu, rq->rd->rto_mask);
@@ -222,47 +228,8 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 
 #endif
 
-static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
-{
-	int i, idle = 1;
-	cpumask_t span;
-
-	if (rt_b->rt_runtime == RUNTIME_INF)
-		return 1;
-
-	span = sched_rt_period_mask();
-	for_each_cpu_mask_nr(i, span) {
-		int enqueue = 0;
-		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
-		struct rq *rq = rq_of_rt_rq(rt_rq);
-
-		spin_lock(&rq->lock);
-		if (rt_rq->rt_time) {
-			u64 runtime;
-
-			spin_lock(&rt_rq->rt_runtime_lock);
-			runtime = rt_rq->rt_runtime;
-			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
-			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
-				rt_rq->rt_throttled = 0;
-				enqueue = 1;
-			}
-			if (rt_rq->rt_time || rt_rq->rt_nr_running)
-				idle = 0;
-			spin_unlock(&rt_rq->rt_runtime_lock);
-		} else if (rt_rq->rt_nr_running)
-			idle = 0;
-
-		if (enqueue)
-			sched_rt_rq_enqueue(rt_rq);
-		spin_unlock(&rq->lock);
-	}
-
-	return idle;
-}
-
 #ifdef CONFIG_SMP
-static int balance_runtime(struct rt_rq *rt_rq)
+static int do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
@@ -281,6 +248,9 @@ static int balance_runtime(struct rt_rq *rt_rq)
 			continue;
 
 		spin_lock(&iter->rt_runtime_lock);
+		if (iter->rt_runtime == RUNTIME_INF)
+			goto next;
+
 		diff = iter->rt_runtime - iter->rt_time;
 		if (diff > 0) {
 			do_div(diff, weight);
@@ -294,14 +264,165 @@ static int balance_runtime(struct rt_rq *rt_rq)
 				break;
 			}
 		}
+next:
 		spin_unlock(&iter->rt_runtime_lock);
 	}
 	spin_unlock(&rt_b->rt_runtime_lock);
 
 	return more;
 }
+
+static void __disable_runtime(struct rq *rq)
+{
+	struct root_domain *rd = rq->rd;
+	struct rt_rq *rt_rq;
+
+	if (unlikely(!scheduler_running))
+		return;
+
+	for_each_leaf_rt_rq(rt_rq, rq) {
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+		s64 want;
+		int i;
+
+		spin_lock(&rt_b->rt_runtime_lock);
+		spin_lock(&rt_rq->rt_runtime_lock);
+		if (rt_rq->rt_runtime == RUNTIME_INF ||
+				rt_rq->rt_runtime == rt_b->rt_runtime)
+			goto balanced;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+
+		want = rt_b->rt_runtime - rt_rq->rt_runtime;
+
+		for_each_cpu_mask(i, rd->span) {
+			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
+			s64 diff;
+
+			if (iter == rt_rq)
+				continue;
+
+			spin_lock(&iter->rt_runtime_lock);
+			if (want > 0) {
+				diff = min_t(s64, iter->rt_runtime, want);
+				iter->rt_runtime -= diff;
+				want -= diff;
+			} else {
+				iter->rt_runtime -= want;
+				want -= want;
+			}
+			spin_unlock(&iter->rt_runtime_lock);
+
+			if (!want)
+				break;
+		}
+
+		spin_lock(&rt_rq->rt_runtime_lock);
+		BUG_ON(want);
+balanced:
+		rt_rq->rt_runtime = RUNTIME_INF;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+		spin_unlock(&rt_b->rt_runtime_lock);
+	}
+}
+
+static void disable_runtime(struct rq *rq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+	__disable_runtime(rq);
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static void __enable_runtime(struct rq *rq)
+{
+	struct root_domain *rd = rq->rd;
+	struct rt_rq *rt_rq;
+
+	if (unlikely(!scheduler_running))
+		return;
+
+	for_each_leaf_rt_rq(rt_rq, rq) {
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+		spin_lock(&rt_b->rt_runtime_lock);
+		spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = rt_b->rt_runtime;
+		rt_rq->rt_time = 0;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+		spin_unlock(&rt_b->rt_runtime_lock);
+	}
+}
+
+static void enable_runtime(struct rq *rq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+	__enable_runtime(rq);
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static int balance_runtime(struct rt_rq *rt_rq)
+{
+	int more = 0;
+
+	if (rt_rq->rt_time > rt_rq->rt_runtime) {
+		spin_unlock(&rt_rq->rt_runtime_lock);
+		more = do_balance_runtime(rt_rq);
+		spin_lock(&rt_rq->rt_runtime_lock);
+	}
+
+	return more;
+}
+#else
+static inline int balance_runtime(struct rt_rq *rt_rq)
+{
+	return 0;
+}
 #endif
 
+static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
+{
+	int i, idle = 1;
+	cpumask_t span;
+
+	if (rt_b->rt_runtime == RUNTIME_INF)
+		return 1;
+
+	span = sched_rt_period_mask();
+	for_each_cpu_mask(i, span) {
+		int enqueue = 0;
+		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
+		struct rq *rq = rq_of_rt_rq(rt_rq);
+
+		spin_lock(&rq->lock);
+		if (rt_rq->rt_time) {
+			u64 runtime;
+
+			spin_lock(&rt_rq->rt_runtime_lock);
+			if (rt_rq->rt_throttled)
+				balance_runtime(rt_rq);
+			runtime = rt_rq->rt_runtime;
+			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
+			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
+				rt_rq->rt_throttled = 0;
+				enqueue = 1;
+			}
+			if (rt_rq->rt_time || rt_rq->rt_nr_running)
+				idle = 0;
+			spin_unlock(&rt_rq->rt_runtime_lock);
+		} else if (rt_rq->rt_nr_running)
+			idle = 0;
+
+		if (enqueue)
+			sched_rt_rq_enqueue(rt_rq);
+		spin_unlock(&rq->lock);
+	}
+
+	return idle;
+}
+
 static inline int rt_se_prio(struct sched_rt_entity *rt_se)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -327,18 +448,10 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 	if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq))
 		return 0;
 
-#ifdef CONFIG_SMP
-	if (rt_rq->rt_time > runtime) {
-		int more;
-
-		spin_unlock(&rt_rq->rt_runtime_lock);
-		more = balance_runtime(rt_rq);
-		spin_lock(&rt_rq->rt_runtime_lock);
-
-		if (more)
-			runtime = sched_rt_runtime(rt_rq);
-	}
-#endif
+	balance_runtime(rt_rq);
+	runtime = sched_rt_runtime(rt_rq);
+	if (runtime == RUNTIME_INF)
+		return 0;
 
 	if (rt_rq->rt_time > runtime) {
 		rt_rq->rt_throttled = 1;
@@ -392,12 +505,21 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
 	rt_rq->rt_nr_running++;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	if (rt_se_prio(rt_se) < rt_rq->highest_prio)
+	if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+		struct rq *rq = rq_of_rt_rq(rt_rq);
+
 		rt_rq->highest_prio = rt_se_prio(rt_se);
+#ifdef CONFIG_SMP
+		if (rq->online)
+			cpupri_set(&rq->rd->cpupri, rq->cpu,
+				   rt_se_prio(rt_se));
+#endif
+	}
 #endif
 #ifdef CONFIG_SMP
 	if (rt_se->nr_cpus_allowed > 1) {
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+
 		rq->rt.rt_nr_migratory++;
 	}
 
@@ -417,6 +539,10 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 static inline
 void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+#ifdef CONFIG_SMP
+	int highest_prio = rt_rq->highest_prio;
+#endif
+
 	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
 	WARN_ON(!rt_rq->rt_nr_running);
 	rt_rq->rt_nr_running--;
@@ -440,6 +566,14 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 		rq->rt.rt_nr_migratory--;
 	}
 
+	if (rt_rq->highest_prio != highest_prio) {
+		struct rq *rq = rq_of_rt_rq(rt_rq);
+
+		if (rq->online)
+			cpupri_set(&rq->rd->cpupri, rq->cpu,
+				   rt_rq->highest_prio);
+	}
+
 	update_rt_migration(rq_of_rt_rq(rt_rq));
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -455,6 +589,7 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
 	struct rt_rq *group_rq = group_rt_rq(rt_se);
+	struct list_head *queue = array->queue + rt_se_prio(rt_se);
 
 	/*
 	 * Don't enqueue the group if its throttled, or when empty.
@@ -465,7 +600,11 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
-	list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
+	if (rt_se->nr_cpus_allowed == 1)
+		list_add(&rt_se->run_list, queue);
+	else
+		list_add_tail(&rt_se->run_list, queue);
+
 	__set_bit(rt_se_prio(rt_se), array->bitmap);
 
 	inc_rt_tasks(rt_se, rt_rq);
@@ -552,8 +691,11 @@ void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
 	struct rt_prio_array *array = &rt_rq->active;
 	struct list_head *queue = array->queue + rt_se_prio(rt_se);
 
-	if (on_rt_rq(rt_se))
-		list_move_tail(&rt_se->run_list, queue);
+	if (on_rt_rq(rt_se)) {
+		list_del_init(&rt_se->run_list);
+		list_add_tail(&rt_se->run_list,
+			      array->queue + rt_se_prio(rt_se));
+	}
 }
 
 static void requeue_task_rt(struct rq *rq, struct task_struct *p)
@@ -616,8 +758,37 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
  */
 static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
 {
-	if (p->prio < rq->curr->prio)
+	if (p->prio < rq->curr->prio) {
 		resched_task(rq->curr);
+		return;
+	}
+
+#ifdef CONFIG_SMP
+	/*
+	 * If:
+	 *
+	 * - the newly woken task is of equal priority to the current task
+	 * - the newly woken task is non-migratable while current is migratable
+	 * - current will be preempted on the next reschedule
+	 *
+	 * we should check to see if current can readily move to a different
+	 * cpu.  If so, we will reschedule to allow the push logic to try
+	 * to move current somewhere else, making room for our non-migratable
+	 * task.
+	 */
+	if((p->prio == rq->curr->prio)
+	   && p->rt.nr_cpus_allowed == 1
+	   && rq->curr->rt.nr_cpus_allowed != 1) {
+		cpumask_t mask;
+
+		if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+			/*
+			 * There appears to be other cpus that can accept
+			 * current, so lets reschedule to try and push it away
+			 */
+			resched_task(rq->curr);
+	}
+#endif
 }
 
 static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
@@ -720,73 +891,6 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_t, local_cpu_mask);
 
-static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask)
-{
-	int       lowest_prio = -1;
-	int       lowest_cpu  = -1;
-	int       count       = 0;
-	int       cpu;
-
-	cpus_and(*lowest_mask, task_rq(task)->rd->online, task->cpus_allowed);
-
-	/*
-	 * Scan each rq for the lowest prio.
-	 */
-	for_each_cpu_mask(cpu, *lowest_mask) {
-		struct rq *rq = cpu_rq(cpu);
-
-		/* We look for lowest RT prio or non-rt CPU */
-		if (rq->rt.highest_prio >= MAX_RT_PRIO) {
-			/*
-			 * if we already found a low RT queue
-			 * and now we found this non-rt queue
-			 * clear the mask and set our bit.
-			 * Otherwise just return the queue as is
-			 * and the count==1 will cause the algorithm
-			 * to use the first bit found.
-			 */
-			if (lowest_cpu != -1) {
-				cpus_clear(*lowest_mask);
-				cpu_set(rq->cpu, *lowest_mask);
-			}
-			return 1;
-		}
-
-		/* no locking for now */
-		if ((rq->rt.highest_prio > task->prio)
-		    && (rq->rt.highest_prio >= lowest_prio)) {
-			if (rq->rt.highest_prio > lowest_prio) {
-				/* new low - clear old data */
-				lowest_prio = rq->rt.highest_prio;
-				lowest_cpu = cpu;
-				count = 0;
-			}
-			count++;
-		} else
-			cpu_clear(cpu, *lowest_mask);
-	}
-
-	/*
-	 * Clear out all the set bits that represent
-	 * runqueues that were of higher prio than
-	 * the lowest_prio.
-	 */
-	if (lowest_cpu > 0) {
-		/*
-		 * Perhaps we could add another cpumask op to
-		 * zero out bits. Like cpu_zero_bits(cpumask, nrbits);
-		 * Then that could be optimized to use memset and such.
-		 */
-		for_each_cpu_mask(cpu, *lowest_mask) {
-			if (cpu >= lowest_cpu)
-				break;
-			cpu_clear(cpu, *lowest_mask);
-		}
-	}
-
-	return count;
-}
-
 static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 {
 	int first;
@@ -808,17 +912,12 @@ static int find_lowest_rq(struct task_struct *task)
 	cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
-	int count    = find_lowest_cpus(task, lowest_mask);
 
-	if (!count)
-		return -1; /* No targets found */
+	if (task->rt.nr_cpus_allowed == 1)
+		return -1; /* No other targets possible */
 
-	/*
-	 * There is no sense in performing an optimal search if only one
-	 * target is found.
-	 */
-	if (count == 1)
-		return first_cpu(*lowest_mask);
+	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
+		return -1; /* No targets found */
 
 	/*
 	 * At this point we have built a mask of cpus representing the
@@ -1163,17 +1262,25 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 }
 
 /* Assumes rq->lock is held */
-static void join_domain_rt(struct rq *rq)
+static void rq_online_rt(struct rq *rq)
 {
 	if (rq->rt.overloaded)
 		rt_set_overload(rq);
+
+	__enable_runtime(rq);
+
+	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
 }
 
 /* Assumes rq->lock is held */
-static void leave_domain_rt(struct rq *rq)
+static void rq_offline_rt(struct rq *rq)
 {
 	if (rq->rt.overloaded)
 		rt_clear_overload(rq);
+
+	__disable_runtime(rq);
+
+	cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
 }
 
 /*
@@ -1336,8 +1443,8 @@ static const struct sched_class rt_sched_class = {
 	.load_balance		= load_balance_rt,
 	.move_one_task		= move_one_task_rt,
 	.set_cpus_allowed       = set_cpus_allowed_rt,
-	.join_domain            = join_domain_rt,
-	.leave_domain           = leave_domain_rt,
+	.rq_online              = rq_online_rt,
+	.rq_offline             = rq_offline_rt,
 	.pre_schedule		= pre_schedule_rt,
 	.post_schedule		= post_schedule_rt,
 	.task_wake_up		= task_wake_up_rt,
@@ -1350,3 +1457,17 @@ static const struct sched_class rt_sched_class = {
 	.prio_changed		= prio_changed_rt,
 	.switched_to		= switched_to_rt,
 };
+
+#ifdef CONFIG_SCHED_DEBUG
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+
+static void print_rt_stats(struct seq_file *m, int cpu)
+{
+	struct rt_rq *rt_rq;
+
+	rcu_read_lock();
+	for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
+		print_rt_rq(m, cpu, rt_rq);
+	rcu_read_unlock();
+}
+#endif
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 1eb09bf17c29..5e85e53734c8 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -629,7 +629,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 
 		p = per_cpu(ksoftirqd, hotcpu);
 		per_cpu(ksoftirqd, hotcpu) = NULL;
-		sched_setscheduler(p, SCHED_FIFO, &param);
+		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
 		kthread_stop(p);
 		takeover_tasklets(hotcpu);
 		break;
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b7350bbfb076..ba9b2054ecbd 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -187,7 +187,7 @@ struct task_struct *__stop_machine_run(int (*fn)(void *), void *data,
 		struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 
 		/* One high-prio thread per cpu.  We'll do this one. */
-		sched_setscheduler(p, SCHED_FIFO, &param);
+		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
 		kthread_bind(p, cpu);
 		wake_up_process(p);
 		wait_for_completion(&smdata.done);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2f3fcdac325b..135cc6840bd8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -83,6 +83,9 @@ extern int maps_protect;
 extern int sysctl_stat_interval;
 extern int latencytop_enabled;
 extern int sysctl_nr_open_min, sysctl_nr_open_max;
+#ifdef CONFIG_RCU_TORTURE_TEST
+extern int rcutorture_runnable;
+#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP)
@@ -836,6 +839,16 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
+#ifdef CONFIG_RCU_TORTURE_TEST
+	{
+		.ctl_name       = CTL_UNNUMBERED,
+		.procname       = "rcutorture_runnable",
+		.data           = &rcutorture_runnable,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = &proc_dointvec,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 98471f7b00ec..6d66631d63c7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -567,16 +567,34 @@ config BOOT_PRINTK_DELAY
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
-	depends on m
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
 	  on the RCU infrastructure.  The kernel module may be built
 	  after the fact on the running kernel to be tested, if desired.
 
+	  Say Y here if you want RCU torture tests to be built into
+	  the kernel.
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config RCU_TORTURE_TEST_RUNNABLE
+	bool "torture tests for RCU runnable by default"
+	depends on RCU_TORTURE_TEST = y
+	default n
+	help
+	  This option provides a way to build the RCU torture tests
+	  directly into the kernel without them starting up at boot
+	  time.  You can use /proc/sys/kernel/rcutorture_runnable
+	  to manually override this setting.  This /proc file is
+	  available only when the RCU torture tests have been built
+	  into the kernel.
+
+	  Say Y here if you want the RCU torture tests to start during
+	  boot (you probably don't).
+	  Say N here if you want the RCU torture tests to start only
+	  after being manually enabled via /proc.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
diff --git a/lib/textsearch.c b/lib/textsearch.c
index be8bda3862f5..a3e500ad51d7 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -97,6 +97,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/err.h>
 #include <linux/textsearch.h>
diff --git a/net/802/psnap.c b/net/802/psnap.c
index 31128cb92a23..ea4643931446 100644
--- a/net/802/psnap.c
+++ b/net/802/psnap.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/in.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 
 static LIST_HEAD(snap_list);
 static DEFINE_SPINLOCK(snap_lock);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ab2225da0ee2..08f14f6c5fd6 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -27,6 +27,7 @@
 #include <linux/mm.h>
 #include <linux/in.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <net/p8022.h>
 #include <net/arp.h>
 #include <linux/rtnetlink.h>
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 72c5976a5ce3..142060f02054 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -15,6 +15,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/rculist.h>
 #include <linux/spinlock.h>
 #include <linux/times.h>
 #include <linux/netdevice.h>
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index e38034aa56f5..9e96ffcd29a3 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -13,6 +13,7 @@
  *	2 of the License, or (at your option) any later version.
  */
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 
 #include "br_private.h"
 #include "br_private_stp.h"
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 7d1b11703741..8e0b4c8f62a8 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
+#include <linux/rculist.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 0edefcfc5949..077bcd228799 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 #include <linux/types.h>
 #include <linux/timer.h>
 #include <linux/skbuff.h>
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index 02c2f7c0b255..643c032a3a57 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -30,8 +30,7 @@
  */
 
 #include <linux/types.h>
-#include <linux/rcupdate.h>
-#include <linux/list.h>
+#include <linux/rculist.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>