Merge commit 'sched-latest/latest'

79 files changed, 4521 insertions, 992 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/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/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7e52b4d8ae13..9ec1f1f34142 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1955,6 +1955,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	snd-ymfpci=	[HW,ALSA]
 
+	softlockup_panic=
+			[KNL] Should the soft-lockup detector generate panics.
+
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/sonypi.txt
 
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt
new file mode 100644
index 000000000000..84246f703875
--- /dev/null
+++ b/Documentation/tracers/mmiotrace.txt
@@ -0,0 +1,153 @@
+		In-kernel memory-mapped I/O tracing
+
+
+Home page and links to optional user space tools:
+
+	http://nouveau.freedesktop.org/wiki/MmioTrace
+
+MMIO tracing was originally developed by Intel around 2003 for their Fault
+Injection Test Harness. In Dec 2006 - Jan 2007, using the code from Intel,
+Jeff Muizelaar created a tool for tracing MMIO accesses with the Nouveau
+project in mind. Since then many people have contributed.
+
+Mmiotrace was built for reverse engineering any memory-mapped IO device with
+the Nouveau project as the first real user. Only x86 and x86_64 architectures
+are supported.
+
+Out-of-tree mmiotrace was originally modified for mainline inclusion and
+ftrace framework by Pekka Paalanen <pq@iki.fi>.
+
+
+Preparation
+-----------
+
+Mmiotrace feature is compiled in by the CONFIG_MMIOTRACE option. Tracing is
+disabled by default, so it is safe to have this set to yes. SMP systems are
+supported, but tracing is unreliable and may miss events if more than one CPU
+is on-line, therefore mmiotrace takes all but one CPU off-line during run-time
+activation [not implemented].
+
+
+Usage Quick Reference
+---------------------
+
+$ mount -t debugfs debugfs /debug
+$ echo mmiotrace > /debug/tracing/current_tracer
+$ cat /debug/tracing/trace_pipe > mydump.txt &
+Start X or whatever.
+$ echo "X is up" > /debug/tracing/marker
+$ echo none > /debug/tracing/current_tracer
+Check kernel log.
+
+
+Usage
+-----
+
+Make sure debugfs is mounted to /debug. If not, (requires root privileges)
+$ mount -t debugfs debugfs /debug
+
+Check that the driver you are about to trace is not loaded.
+
+Activate mmiotrace (requires root privileges):
+$ echo mmiotrace > /debug/tracing/current_tracer
+
+Start storing the trace:
+$ cat /debug/tracing/trace_pipe > mydump.txt &
+The 'cat' process should stay running (sleeping) in the background.
+
+Load the driver you want to trace and use it. Mmiotrace will only catch MMIO
+accesses to areas that are ioremapped while mmiotrace is active.
+
+[Unimplemented feature:]
+During tracing you can place comments (markers) into the trace by
+$ echo "X is up" > /debug/tracing/marker
+This makes it easier to see which part of the (huge) trace corresponds to
+which action. It is recommended to place descriptive markers about what you
+do.
+
+Shut down mmiotrace (requires root privileges):
+$ echo none > /debug/tracing/current_tracer
+The 'cat' process exits. If it does not, kill it by 'fg' and pressing ctrl+c.
+
+[This feature is not implemented yet!]
+Check your kernel log. If there are messages about mmiotrace losing events,
+this is due to buffer overrun, and the trace is incomplete. You should enlarge
+the buffers and try again. [How?]
+
+If you are doing a trace for a driver project, e.g. Nouveau, you should also
+do the following before sending your results:
+$ lspci -vvv > lspci.txt
+$ dmesg > dmesg.txt
+$ tar zcf pciid-nick-mmiotrace.tar.gz mydump.txt lspci.txt dmesg.txt
+and then send the .tar.gz file. The trace compresses considerably. Replace
+"pciid" and "nick" with the PCI ID or model name of your piece of hardware
+under investigation and your nick name.
+
+
+How Mmiotrace Works
+-------------------
+
+Access to hardware IO-memory is gained by mapping addresses from PCI bus by
+calling one of the ioremap_*() functions. Mmiotrace is hooked into the
+__ioremap() function and gets called whenever a mapping is created. Mapping is
+an event that is recorded into the trace log. Note, that ISA range mappings
+are not caught, since the mapping always exists and is returned directly.
+
+MMIO accesses are recorded via page faults. Just before __ioremap() returns,
+the mapped pages are marked as not present. Any access to the pages causes a
+fault. The page fault handler calls mmiotrace to handle the fault. Mmiotrace
+marks the page present, sets TF flag to achieve single stepping and exits the
+fault handler. The instruction that faulted is executed and debug trap is
+entered. Here mmiotrace again marks the page as not present. The instruction
+is decoded to get the type of operation (read/write), data width and the value
+read or written. These are stored to the trace log.
+
+Setting the page present in the page fault handler has a race condition on SMP
+machines. During the single stepping other CPUs may run freely on that page
+and events can be missed without a notice. Re-enabling other CPUs during
+tracing is discouraged.
+
+
+Trace Log Format
+----------------
+
+The raw log is text and easily filtered with e.g. grep and awk. One record is
+one line in the log. A record starts with a keyword, followed by keyword
+dependant arguments. Arguments are separated by a space, or continue until the
+end of line. The format for version 20070824 is as follows:
+
+Explanation	Keyword	Space separated arguments
+---------------------------------------------------------------------------
+
+read event	R	width, timestamp, map id, physical, value, PC, PID
+write event	W	width, timestamp, map id, physical, value, PC, PID
+ioremap event	MAP	timestamp, map id, physical, virtual, length, PC, PID
+iounmap event	UNMAP	timestamp, map id, PC, PID
+marker		MARK	timestamp, text
+version		VERSION	the string "20070824"
+info for reader	LSPCI	one line from lspci -v
+PCI address map	PCIDEV	space separated /proc/bus/pci/devices data
+unk. opcode	UNKNOWN	timestamp, map id, physical, data, PC, PID
+
+Timestamp is in seconds with decimals. Physical is a PCI bus address, virtual
+is a kernel virtual address. Width is the data width in bytes and value is the
+data value. Map id is an arbitrary id number identifying the mapping that was
+used in an operation. PC is the program counter and PID is process id. PC is
+zero if it is not recorded. PID is always zero as tracing MMIO accesses
+originating in user space memory is not yet supported.
+
+For instance, the following awk filter will pass all 32-bit writes that target
+physical addresses in the range [0xfb73ce40, 0xfb800000[
+
+$ awk '/W 4 / { adr=strtonum($5); if (adr >= 0xfb73ce40 &&
+adr < 0xfb800000) print; }'
+
+
+Tools for Developers
+--------------------
+
+The user space tools include utilities for:
+- replacing numeric addresses and values with hardware register names
+- replaying MMIO logs, i.e., re-executing the recorded writes
+
+
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index facf82a5499a..741028c13b11 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -51,7 +51,7 @@ select_smp_affinity(unsigned int irq)
 	if (!irq_desc[irq].chip->set_affinity || irq_user_affinity[irq])
 		return 1;
 
-	while (!cpu_possible(cpu))
+	while (!cpu_possible(cpu) || !cpu_system(cpu))
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
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/Kconfig.debug b/arch/x86/Kconfig.debug
index e51ace61fcc8..30933acb0b50 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -170,6 +170,34 @@ config IOMMU_LEAK
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
+config MMIOTRACE_HOOKS
+	bool
+
+config MMIOTRACE
+	bool "Memory mapped IO tracing"
+	depends on DEBUG_KERNEL && PCI
+	select TRACING
+	select MMIOTRACE_HOOKS
+	default y
+	help
+	  Mmiotrace traces Memory Mapped I/O access and is meant for
+	  debugging and reverse engineering. It is called from the ioremap
+	  implementation and works via page faults. Tracing is disabled by
+	  default and can be enabled at run-time.
+
+	  See Documentation/tracers/mmiotrace.txt.
+	  If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+	tristate "Test module for mmiotrace"
+	depends on MMIOTRACE && m
+	help
+	  This is a dumb module for testing mmiotrace. It is very dangerous
+	  as it will write garbage to IO memory starting at a given address.
+	  However, it should be safe to use on e.g. unused portion of VRAM.
+
+	  Say N, unless you absolutely know what you are doing.
+
 #
 # IO delay types:
 #
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5412fd73fee0..7ce093969541 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1,6 +1,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/kprobes.h>
 #include <linux/mm.h>
@@ -279,7 +279,7 @@ struct smp_alt_module {
 	struct list_head next;
 };
 static LIST_HEAD(smp_alt_modules);
-static DEFINE_SPINLOCK(smp_alt);
+static DEFINE_MUTEX(smp_alt);
 static int smp_mode = 1;	/* protected by smp_alt */
 
 void alternatives_smp_module_add(struct module *mod, char *name,
@@ -312,12 +312,12 @@ void alternatives_smp_module_add(struct module *mod, char *name,
 		__func__, smp->locks, smp->locks_end,
 		smp->text, smp->text_end, smp->name);
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 	list_add_tail(&smp->next, &smp_alt_modules);
 	if (boot_cpu_has(X86_FEATURE_UP))
 		alternatives_smp_unlock(smp->locks, smp->locks_end,
 					smp->text, smp->text_end);
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_module_del(struct module *mod)
@@ -327,17 +327,17 @@ void alternatives_smp_module_del(struct module *mod)
 	if (smp_alt_once || noreplace_smp)
 		return;
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 	list_for_each_entry(item, &smp_alt_modules, next) {
 		if (mod != item->mod)
 			continue;
 		list_del(&item->next);
-		spin_unlock(&smp_alt);
+		mutex_unlock(&smp_alt);
 		DPRINTK("%s: %s\n", __func__, item->name);
 		kfree(item);
 		return;
 	}
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_switch(int smp)
@@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 
 	/*
 	 * Avoid unnecessary switches because it forces JIT based VMs to
@@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp)
 						mod->text, mod->text_end);
 	}
 	smp_mode = smp;
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 #endif
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 9f44623e0072..498608c015fb 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -93,8 +93,8 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		"   movb %b4, 4(%2)\n"
 		"2:\n"
 		".section .fixup, \"ax\"\n"
-		"	movl $1, %0\n"
-		"3:	jmp 2b\n"
+		"3:	movl $1, %0\n"
+		"	jmp 2b\n"
 		".previous\n"
 		_ASM_EXTABLE(1b, 3b)
 		: "=r"(faulted), "=a"(replaced)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 53cfc34a63e7..cdf05ca3474f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -4,6 +4,8 @@
 #include <linux/smp.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/pm.h>
 
 struct kmem_cache *task_xstate_cachep;
 
@@ -42,3 +44,118 @@ void arch_task_cache_init(void)
 				  __alignof__(union thread_xstate),
 				  SLAB_PANIC | SLAB_NOTRACK, NULL);
 }
+
+static void do_nothing(void *unused)
+{
+}
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
+void cpu_idle_wait(void)
+{
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 0, 1);
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
+/*
+ * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
+ * which can obviate IPI to trigger checking of need_resched.
+ * We execute MONITOR against need_resched and enter optimized wait state
+ * through MWAIT. Whenever someone changes need_resched, we would be woken
+ * up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
+ */
+void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
+{
+	if (!need_resched()) {
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		smp_mb();
+		if (!need_resched())
+			__mwait(ax, cx);
+	}
+}
+
+/* Default MONITOR/MWAIT with no hints, used for default C1 state */
+static void mwait_idle(void)
+{
+	if (!need_resched()) {
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		smp_mb();
+		if (!need_resched())
+			__sti_mwait(0, 0);
+		else
+			local_irq_enable();
+	} else
+		local_irq_enable();
+}
+
+
+static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+{
+	if (force_mwait)
+		return 1;
+	/* Any C1 states supported? */
+	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
+}
+
+/*
+ * On SMP it's slightly faster (but much more power-consuming!)
+ * to poll the ->work.need_resched flag instead of waiting for the
+ * cross-CPU IPI to arrive. Use this option with caution.
+ */
+static void poll_idle(void)
+{
+	local_irq_enable();
+	cpu_relax();
+}
+
+void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+{
+	static int selected;
+
+	if (selected)
+		return;
+#ifdef CONFIG_X86_SMP
+	if (pm_idle == poll_idle && smp_num_siblings > 1) {
+		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
+			" performance may degrade.\n");
+	}
+#endif
+	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
+		/*
+		 * Skip, if setup has overridden idle.
+		 * One CPU supports mwait => All CPUs supports mwait
+		 */
+		if (!pm_idle) {
+			printk(KERN_INFO "using mwait in idle threads.\n");
+			pm_idle = mwait_idle;
+		}
+	}
+	selected = 1;
+}
+
+static int __init idle_setup(char *str)
+{
+	if (!strcmp(str, "poll")) {
+		printk("using polling idle threads.\n");
+		pm_idle = poll_idle;
+	} else if (!strcmp(str, "mwait"))
+		force_mwait = 1;
+	else
+		return -1;
+
+	boot_option_idle_override = 1;
+	return 0;
+}
+early_param("idle", idle_setup);
+
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0d848194628f..5124028a5429 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,17 +128,6 @@ void default_idle(void)
 EXPORT_SYMBOL(default_idle);
 #endif
 
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
-	local_irq_enable();
-	cpu_relax();
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <asm/nmi.h>
 /* We don't actually take CPU down, just spin without interrupts. */
@@ -209,104 +198,6 @@ void cpu_idle(void)
 	}
 }
 
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
-	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 0, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__sti_mwait(ax, cx);
-		else
-			local_irq_enable();
-	} else
-		local_irq_enable();
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
-	local_irq_enable();
-	mwait_idle_with_hints(0, 0);
-}
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
-	static int selected;
-
-	if (selected)
-		return;
-#ifdef CONFIG_X86_SMP
-	if (pm_idle == poll_idle && smp_num_siblings > 1) {
-		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
-			" performance may degrade.\n");
-	}
-#endif
-	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
-		/*
-		 * Skip, if setup has overridden idle.
-		 * One CPU supports mwait => All CPUs supports mwait
-		 */
-		if (!pm_idle) {
-			printk(KERN_INFO "using mwait in idle threads.\n");
-			pm_idle = mwait_idle;
-		}
-	}
-	selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
-	if (!strcmp(str, "poll")) {
-		printk("using polling idle threads.\n");
-		pm_idle = poll_idle;
-	} else if (!strcmp(str, "mwait"))
-		force_mwait = 1;
-	else
-		return -1;
-
-	boot_option_idle_override = 1;
-	return 0;
-}
-early_param("idle", idle_setup);
-
 void __show_regs(struct pt_regs *regs, int all)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 005fb8172756..bd95a5e433f4 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -116,17 +116,6 @@ void default_idle(void)
 	current_thread_info()->status |= TS_POLLING;
 }
 
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
-	local_irq_enable();
-	cpu_relax();
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 DECLARE_PER_CPU(int, cpu_state);
 
@@ -207,110 +196,6 @@ void cpu_idle(void)
 	}
 }
 
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
-	smp_mb();
-	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 0, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(ax, cx);
-	}
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
-	if (!need_resched()) {
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__sti_mwait(0, 0);
-		else
-			local_irq_enable();
-	} else {
-		local_irq_enable();
-	}
-}
-
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
-	if (force_mwait)
-		return 1;
-	/* Any C1 states supported? */
-	return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
-	static int selected;
-
-	if (selected)
-		return;
-#ifdef CONFIG_X86_SMP
-	if (pm_idle == poll_idle && smp_num_siblings > 1) {
-		printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
-			" performance may degrade.\n");
-	}
-#endif
-	if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
-		/*
-		 * Skip, if setup has overridden idle.
-		 * One CPU supports mwait => All CPUs supports mwait
-		 */
-		if (!pm_idle) {
-			printk(KERN_INFO "using mwait in idle threads.\n");
-			pm_idle = mwait_idle;
-		}
-	}
-	selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
-	if (!strcmp(str, "poll")) {
-		printk("using polling idle threads.\n");
-		pm_idle = poll_idle;
-	} else if (!strcmp(str, "mwait"))
-		force_mwait = 1;
-	else
-		return -1;
-
-	boot_option_idle_override = 1;
-	return 0;
-}
-early_param("idle", idle_setup);
-
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs * regs, int all)
 {
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index b7b3e4c7cfc9..07dab503c9e3 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -8,6 +8,11 @@ obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
+obj-$(CONFIG_MMIOTRACE_HOOKS)	+= kmmio.o
+obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
+mmiotrace-y			:= pf_in.o mmio-mod.o
+obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
+
 ifeq ($(CONFIG_X86_32),y)
 obj-$(CONFIG_NUMA)		+= discontig_32.o
 else
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c6356137c08e..47688dca55ec 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -26,6 +26,7 @@
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
 #include <linux/magic.h>
+#include <linux/mmiotrace.h>
 
 #include <asm/system.h>
 #include <asm/desc.h>
@@ -51,6 +52,16 @@
 #define PF_RSVD		(1<<3)
 #define PF_INSTR	(1<<4)
 
+static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
+{
+#ifdef CONFIG_MMIOTRACE_HOOKS
+	if (unlikely(is_kmmio_active()))
+		if (kmmio_handler(regs, addr) == 1)
+			return -1;
+#endif
+	return 0;
+}
+
 static inline int notify_page_fault(struct pt_regs *regs)
 {
 #ifdef CONFIG_KPROBES
@@ -621,6 +632,8 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
 	if (notify_page_fault(regs))
 		return;
+	if (unlikely(kmmio_fault(regs, address)))
+		return;
 
 	/*
 	 * We fault-in kernel-space virtual memory on-demand. The
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5a921b6bbf2c..325bb54d23fe 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -748,6 +748,8 @@ void mark_rodata_ro(void)
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long size = PFN_ALIGN(_etext) - start;
 
+#ifndef CONFIG_DYNAMIC_FTRACE
+	/* Dynamic tracing modifies the kernel text section */
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
 		size >> 10);
@@ -760,6 +762,8 @@ void mark_rodata_ro(void)
 	printk(KERN_INFO "Testing CPA: write protecting again\n");
 	set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
 #endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
 	start += size;
 	size = (unsigned long)__end_rodata - start;
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 266bee758cc6..14728f3faf35 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -777,6 +777,13 @@ EXPORT_SYMBOL_GPL(rodata_test_data);
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
+	unsigned long rodata_start =
+		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* Dynamic tracing modifies the kernel text section */
+	start = rodata_start;
+#endif
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
@@ -786,8 +793,7 @@ void mark_rodata_ro(void)
 	 * The rodata section (but not the kernel text!) should also be
 	 * not-executable.
 	 */
-	start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
-	set_memory_nx(start, (end - start) >> PAGE_SHIFT);
+	set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d176b23110cc..68b287d52389 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -12,6 +12,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/mmiotrace.h>
 
 #include <asm/cacheflush.h>
 #include <asm/e820.h>
@@ -126,6 +127,7 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
 	unsigned long new_prot_val;
 	pgprot_t prot;
 	int retval;
+	void __iomem *ret_addr;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -229,7 +231,10 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
 		return NULL;
 	}
 
-	return (void __iomem *) (vaddr + offset);
+	ret_addr = (void __iomem *) (vaddr + offset);
+	mmiotrace_ioremap(phys_addr, size, ret_addr);
+
+	return ret_addr;
 }
 
 /**
@@ -306,6 +311,8 @@ void iounmap(volatile void __iomem *addr)
 	    addr < phys_to_virt(ISA_END_ADDRESS))
 		return;
 
+	mmiotrace_iounmap(addr);
+
 	addr = (volatile void __iomem *)
 		(PAGE_MASK & (unsigned long __force)addr);
 
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
new file mode 100644
index 000000000000..b4287b73d21a
--- /dev/null
+++ b/arch/x86/mm/kmmio.c
@@ -0,0 +1,500 @@
+/* Support for MMIO probes.
+ * Benfit many code from kprobes
+ * (C) 2002 Louis Zhuang <louis.zhuang@intel.com>.
+ *     2007 Alexander Eichner
+ *     2008 Pekka Paalanen <pq@iki.fi>
+ */
+
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/percpu.h>
+#include <linux/kdebug.h>
+#include <linux/mutex.h>
+#include <asm/io.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/errno.h>
+#include <asm/debugreg.h>
+#include <linux/mmiotrace.h>
+
+#define KMMIO_PAGE_HASH_BITS 4
+#define KMMIO_PAGE_TABLE_SIZE (1 << KMMIO_PAGE_HASH_BITS)
+
+struct kmmio_fault_page {
+	struct list_head list;
+	struct kmmio_fault_page *release_next;
+	unsigned long page; /* location of the fault page */
+
+	/*
+	 * Number of times this page has been registered as a part
+	 * of a probe. If zero, page is disarmed and this may be freed.
+	 * Used only by writers (RCU).
+	 */
+	int count;
+};
+
+struct kmmio_delayed_release {
+	struct rcu_head rcu;
+	struct kmmio_fault_page *release_list;
+};
+
+struct kmmio_context {
+	struct kmmio_fault_page *fpage;
+	struct kmmio_probe *probe;
+	unsigned long saved_flags;
+	unsigned long addr;
+	int active;
+};
+
+static DEFINE_SPINLOCK(kmmio_lock);
+
+/* Protected by kmmio_lock */
+unsigned int kmmio_count;
+
+/* Read-protected by RCU, write-protected by kmmio_lock. */
+static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE];
+static LIST_HEAD(kmmio_probes);
+
+static struct list_head *kmmio_page_list(unsigned long page)
+{
+	return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)];
+}
+
+/* Accessed per-cpu */
+static DEFINE_PER_CPU(struct kmmio_context, kmmio_ctx);
+
+/*
+ * this is basically a dynamic stabbing problem:
+ * Could use the existing prio tree code or
+ * Possible better implementations:
+ * The Interval Skip List: A Data Structure for Finding All Intervals That
+ * Overlap a Point (might be simple)
+ * Space Efficient Dynamic Stabbing with Fast Queries - Mikkel Thorup
+ */
+/* Get the kmmio at this addr (if any). You must be holding RCU read lock. */
+static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
+{
+	struct kmmio_probe *p;
+	list_for_each_entry_rcu(p, &kmmio_probes, list) {
+		if (addr >= p->addr && addr <= (p->addr + p->len))
+			return p;
+	}
+	return NULL;
+}
+
+/* You must be holding RCU read lock. */
+static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
+{
+	struct list_head *head;
+	struct kmmio_fault_page *p;
+
+	page &= PAGE_MASK;
+	head = kmmio_page_list(page);
+	list_for_each_entry_rcu(p, head, list) {
+		if (p->page == page)
+			return p;
+	}
+	return NULL;
+}
+
+static void set_page_present(unsigned long addr, bool present, int *pglevel)
+{
+	pteval_t pteval;
+	pmdval_t pmdval;
+	int level;
+	pmd_t *pmd;
+	pte_t *pte = lookup_address(addr, &level);
+
+	if (!pte) {
+		pr_err("kmmio: no pte for page 0x%08lx\n", addr);
+		return;
+	}
+
+	if (pglevel)
+		*pglevel = level;
+
+	switch (level) {
+	case PG_LEVEL_2M:
+		pmd = (pmd_t *)pte;
+		pmdval = pmd_val(*pmd) & ~_PAGE_PRESENT;
+		if (present)
+			pmdval |= _PAGE_PRESENT;
+		set_pmd(pmd, __pmd(pmdval));
+		break;
+
+	case PG_LEVEL_4K:
+		pteval = pte_val(*pte) & ~_PAGE_PRESENT;
+		if (present)
+			pteval |= _PAGE_PRESENT;
+		set_pte_atomic(pte, __pte(pteval));
+		break;
+
+	default:
+		pr_err("kmmio: unexpected page level 0x%x.\n", level);
+		return;
+	}
+
+	__flush_tlb_one(addr);
+}
+
+/** Mark the given page as not present. Access to it will trigger a fault. */
+static void arm_kmmio_fault_page(unsigned long page, int *page_level)
+{
+	set_page_present(page & PAGE_MASK, false, page_level);
+}
+
+/** Mark the given page as present. */
+static void disarm_kmmio_fault_page(unsigned long page, int *page_level)
+{
+	set_page_present(page & PAGE_MASK, true, page_level);
+}
+
+/*
+ * This is being called from do_page_fault().
+ *
+ * We may be in an interrupt or a critical section. Also prefecthing may
+ * trigger a page fault. We may be in the middle of process switch.
+ * We cannot take any locks, because we could be executing especially
+ * within a kmmio critical section.
+ *
+ * Local interrupts are disabled, so preemption cannot happen.
+ * Do not enable interrupts, do not sleep, and watch out for other CPUs.
+ */
+/*
+ * Interrupts are disabled on entry as trap3 is an interrupt gate
+ * and they remain disabled thorough out this function.
+ */
+int kmmio_handler(struct pt_regs *regs, unsigned long addr)
+{
+	struct kmmio_context *ctx;
+	struct kmmio_fault_page *faultpage;
+	int ret = 0; /* default to fault not handled */
+
+	/*
+	 * Preemption is now disabled to prevent process switch during
+	 * single stepping. We can only handle one active kmmio trace
+	 * per cpu, so ensure that we finish it before something else
+	 * gets to run. We also hold the RCU read lock over single
+	 * stepping to avoid looking up the probe and kmmio_fault_page
+	 * again.
+	 */
+	preempt_disable();
+	rcu_read_lock();
+
+	faultpage = get_kmmio_fault_page(addr);
+	if (!faultpage) {
+		/*
+		 * Either this page fault is not caused by kmmio, or
+		 * another CPU just pulled the kmmio probe from under
+		 * our feet. The latter case should not be possible.
+		 */
+		goto no_kmmio;
+	}
+
+	ctx = &get_cpu_var(kmmio_ctx);
+	if (ctx->active) {
+		disarm_kmmio_fault_page(faultpage->page, NULL);
+		if (addr == ctx->addr) {
+			/*
+			 * On SMP we sometimes get recursive probe hits on the
+			 * same address. Context is already saved, fall out.
+			 */
+			pr_debug("kmmio: duplicate probe hit on CPU %d, for "
+						"address 0x%08lx.\n",
+						smp_processor_id(), addr);
+			ret = 1;
+			goto no_kmmio_ctx;
+		}
+		/*
+		 * Prevent overwriting already in-flight context.
+		 * This should not happen, let's hope disarming at least
+		 * prevents a panic.
+		 */
+		pr_emerg("kmmio: recursive probe hit on CPU %d, "
+					"for address 0x%08lx. Ignoring.\n",
+					smp_processor_id(), addr);
+		pr_emerg("kmmio: previous hit was at 0x%08lx.\n",
+					ctx->addr);
+		goto no_kmmio_ctx;
+	}
+	ctx->active++;
+
+	ctx->fpage = faultpage;
+	ctx->probe = get_kmmio_probe(addr);
+	ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
+	ctx->addr = addr;
+
+	if (ctx->probe && ctx->probe->pre_handler)
+		ctx->probe->pre_handler(ctx->probe, regs, addr);
+
+	/*
+	 * Enable single-stepping and disable interrupts for the faulting
+	 * context. Local interrupts must not get enabled during stepping.
+	 */
+	regs->flags |= X86_EFLAGS_TF;
+	regs->flags &= ~X86_EFLAGS_IF;
+
+	/* Now we set present bit in PTE and single step. */
+	disarm_kmmio_fault_page(ctx->fpage->page, NULL);
+
+	/*
+	 * If another cpu accesses the same page while we are stepping,
+	 * the access will not be caught. It will simply succeed and the
+	 * only downside is we lose the event. If this becomes a problem,
+	 * the user should drop to single cpu before tracing.
+	 */
+
+	put_cpu_var(kmmio_ctx);
+	return 1; /* fault handled */
+
+no_kmmio_ctx:
+	put_cpu_var(kmmio_ctx);
+no_kmmio:
+	rcu_read_unlock();
+	preempt_enable_no_resched();
+	return ret;
+}
+
+/*
+ * Interrupts are disabled on entry as trap1 is an interrupt gate
+ * and they remain disabled thorough out this function.
+ * This must always get called as the pair to kmmio_handler().
+ */
+static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
+{
+	int ret = 0;
+	struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
+
+	if (!ctx->active) {
+		pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+							smp_processor_id());
+		goto out;
+	}
+
+	if (ctx->probe && ctx->probe->post_handler)
+		ctx->probe->post_handler(ctx->probe, condition, regs);
+
+	arm_kmmio_fault_page(ctx->fpage->page, NULL);
+
+	regs->flags &= ~X86_EFLAGS_TF;
+	regs->flags |= ctx->saved_flags;
+
+	/* These were acquired in kmmio_handler(). */
+	ctx->active--;
+	BUG_ON(ctx->active);
+	rcu_read_unlock();
+	preempt_enable_no_resched();
+
+	/*
+	 * if somebody else is singlestepping across a probe point, flags
+	 * will have TF set, in which case, continue the remaining processing
+	 * of do_debug, as if this is not a probe hit.
+	 */
+	if (!(regs->flags & X86_EFLAGS_TF))
+		ret = 1;
+out:
+	put_cpu_var(kmmio_ctx);
+	return ret;
+}
+
+/* You must be holding kmmio_lock. */
+static int add_kmmio_fault_page(unsigned long page)
+{
+	struct kmmio_fault_page *f;
+
+	page &= PAGE_MASK;
+	f = get_kmmio_fault_page(page);
+	if (f) {
+		if (!f->count)
+			arm_kmmio_fault_page(f->page, NULL);
+		f->count++;
+		return 0;
+	}
+
+	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return -1;
+
+	f->count = 1;
+	f->page = page;
+	list_add_rcu(&f->list, kmmio_page_list(f->page));
+
+	arm_kmmio_fault_page(f->page, NULL);
+
+	return 0;
+}
+
+/* You must be holding kmmio_lock. */
+static void release_kmmio_fault_page(unsigned long page,
+				struct kmmio_fault_page **release_list)
+{
+	struct kmmio_fault_page *f;
+
+	page &= PAGE_MASK;
+	f = get_kmmio_fault_page(page);
+	if (!f)
+		return;
+
+	f->count--;
+	BUG_ON(f->count < 0);
+	if (!f->count) {
+		disarm_kmmio_fault_page(f->page, NULL);
+		f->release_next = *release_list;
+		*release_list = f;
+	}
+}
+
+int register_kmmio_probe(struct kmmio_probe *p)
+{
+	unsigned long flags;
+	int ret = 0;
+	unsigned long size = 0;
+
+	spin_lock_irqsave(&kmmio_lock, flags);
+	if (get_kmmio_probe(p->addr)) {
+		ret = -EEXIST;
+		goto out;
+	}
+	kmmio_count++;
+	list_add_rcu(&p->list, &kmmio_probes);
+	while (size < p->len) {
+		if (add_kmmio_fault_page(p->addr + size))
+			pr_err("kmmio: Unable to set page fault.\n");
+		size += PAGE_SIZE;
+	}
+out:
+	spin_unlock_irqrestore(&kmmio_lock, flags);
+	/*
+	 * XXX: What should I do here?
+	 * Here was a call to global_flush_tlb(), but it does not exist
+	 * anymore. It seems it's not needed after all.
+	 */
+	return ret;
+}
+EXPORT_SYMBOL(register_kmmio_probe);
+
+static void rcu_free_kmmio_fault_pages(struct rcu_head *head)
+{
+	struct kmmio_delayed_release *dr = container_of(
+						head,
+						struct kmmio_delayed_release,
+						rcu);
+	struct kmmio_fault_page *p = dr->release_list;
+	while (p) {
+		struct kmmio_fault_page *next = p->release_next;
+		BUG_ON(p->count);
+		kfree(p);
+		p = next;
+	}
+	kfree(dr);
+}
+
+static void remove_kmmio_fault_pages(struct rcu_head *head)
+{
+	struct kmmio_delayed_release *dr = container_of(
+						head,
+						struct kmmio_delayed_release,
+						rcu);
+	struct kmmio_fault_page *p = dr->release_list;
+	struct kmmio_fault_page **prevp = &dr->release_list;
+	unsigned long flags;
+	spin_lock_irqsave(&kmmio_lock, flags);
+	while (p) {
+		if (!p->count)
+			list_del_rcu(&p->list);
+		else
+			*prevp = p->release_next;
+		prevp = &p->release_next;
+		p = p->release_next;
+	}
+	spin_unlock_irqrestore(&kmmio_lock, flags);
+	/* This is the real RCU destroy call. */
+	call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages);
+}
+
+/*
+ * Remove a kmmio probe. You have to synchronize_rcu() before you can be
+ * sure that the callbacks will not be called anymore. Only after that
+ * you may actually release your struct kmmio_probe.
+ *
+ * Unregistering a kmmio fault page has three steps:
+ * 1. release_kmmio_fault_page()
+ *    Disarm the page, wait a grace period to let all faults finish.
+ * 2. remove_kmmio_fault_pages()
+ *    Remove the pages from kmmio_page_table.
+ * 3. rcu_free_kmmio_fault_pages()
+ *    Actally free the kmmio_fault_page structs as with RCU.
+ */
+void unregister_kmmio_probe(struct kmmio_probe *p)
+{
+	unsigned long flags;
+	unsigned long size = 0;
+	struct kmmio_fault_page *release_list = NULL;
+	struct kmmio_delayed_release *drelease;
+
+	spin_lock_irqsave(&kmmio_lock, flags);
+	while (size < p->len) {
+		release_kmmio_fault_page(p->addr + size, &release_list);
+		size += PAGE_SIZE;
+	}
+	list_del_rcu(&p->list);
+	kmmio_count--;
+	spin_unlock_irqrestore(&kmmio_lock, flags);
+
+	drelease = kmalloc(sizeof(*drelease), GFP_ATOMIC);
+	if (!drelease) {
+		pr_crit("kmmio: leaking kmmio_fault_page objects.\n");
+		return;
+	}
+	drelease->release_list = release_list;
+
+	/*
+	 * This is not really RCU here. We have just disarmed a set of
+	 * pages so that they cannot trigger page faults anymore. However,
+	 * we cannot remove the pages from kmmio_page_table,
+	 * because a probe hit might be in flight on another CPU. The
+	 * pages are collected into a list, and they will be removed from
+	 * kmmio_page_table when it is certain that no probe hit related to
+	 * these pages can be in flight. RCU grace period sounds like a
+	 * good choice.
+	 *
+	 * If we removed the pages too early, kmmio page fault handler might
+	 * not find the respective kmmio_fault_page and determine it's not
+	 * a kmmio fault, when it actually is. This would lead to madness.
+	 */
+	call_rcu(&drelease->rcu, remove_kmmio_fault_pages);
+}
+EXPORT_SYMBOL(unregister_kmmio_probe);
+
+static int kmmio_die_notifier(struct notifier_block *nb, unsigned long val,
+								void *args)
+{
+	struct die_args *arg = args;
+
+	if (val == DIE_DEBUG && (arg->err & DR_STEP))
+		if (post_kmmio_handler(arg->err, arg->regs) == 1)
+			return NOTIFY_STOP;
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nb_die = {
+	.notifier_call = kmmio_die_notifier
+};
+
+static int __init init_kmmio(void)
+{
+	int i;
+	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++)
+		INIT_LIST_HEAD(&kmmio_page_table[i]);
+	return register_die_notifier(&nb_die);
+}
+fs_initcall(init_kmmio); /* should be before device_initcall() */
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
new file mode 100644
index 000000000000..6d6cac84c045
--- /dev/null
+++ b/arch/x86/mm/mmio-mod.c
@@ -0,0 +1,453 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2005
+ *               Jeff Muizelaar, 2006, 2007
+ *               Pekka Paalanen, 2008 <pq@iki.fi>
+ *
+ * Derived from the read-mod example from relay-examples by Tom Zanussi.
+ */
+#define DEBUG 1
+
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <asm/io.h>
+#include <linux/version.h>
+#include <linux/kallsyms.h>
+#include <asm/pgtable.h>
+#include <linux/mmiotrace.h>
+#include <asm/e820.h> /* for ISA_START_ADDRESS */
+#include <asm/atomic.h>
+#include <linux/percpu.h>
+
+#include "pf_in.h"
+
+#define NAME "mmiotrace: "
+
+struct trap_reason {
+	unsigned long addr;
+	unsigned long ip;
+	enum reason_type type;
+	int active_traces;
+};
+
+struct remap_trace {
+	struct list_head list;
+	struct kmmio_probe probe;
+	unsigned long phys;
+	unsigned long id;
+};
+
+/* Accessed per-cpu. */
+static DEFINE_PER_CPU(struct trap_reason, pf_reason);
+static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
+
+#if 0 /* XXX: no way gather this info anymore */
+/* Access to this is not per-cpu. */
+static DEFINE_PER_CPU(atomic_t, dropped);
+#endif
+
+static struct dentry *marker_file;
+
+static DEFINE_MUTEX(mmiotrace_mutex);
+static DEFINE_SPINLOCK(trace_lock);
+static atomic_t mmiotrace_enabled;
+static LIST_HEAD(trace_list);		/* struct remap_trace */
+
+/*
+ * Locking in this file:
+ * - mmiotrace_mutex enforces enable/disable_mmiotrace() critical sections.
+ * - mmiotrace_enabled may be modified only when holding mmiotrace_mutex
+ *   and trace_lock.
+ * - Routines depending on is_enabled() must take trace_lock.
+ * - trace_list users must hold trace_lock.
+ * - is_enabled() guarantees that mmio_trace_record is allowed.
+ * - pre/post callbacks assume the effect of is_enabled() being true.
+ */
+
+/* module parameters */
+static unsigned long	filter_offset;
+static int		nommiotrace;
+static int		trace_pc;
+
+module_param(filter_offset, ulong, 0);
+module_param(nommiotrace, bool, 0);
+module_param(trace_pc, bool, 0);
+
+MODULE_PARM_DESC(filter_offset, "Start address of traced mappings.");
+MODULE_PARM_DESC(nommiotrace, "Disable actual MMIO tracing.");
+MODULE_PARM_DESC(trace_pc, "Record address of faulting instructions.");
+
+static bool is_enabled(void)
+{
+	return atomic_read(&mmiotrace_enabled);
+}
+
+#if 0 /* XXX: needs rewrite */
+/*
+ * Write callback for the debugfs entry:
+ * Read a marker and write it to the mmio trace log
+ */
+static ssize_t write_marker(struct file *file, const char __user *buffer,
+						size_t count, loff_t *ppos)
+{
+	char *event = NULL;
+	struct mm_io_header *headp;
+	ssize_t len = (count > 65535) ? 65535 : count;
+
+	event = kzalloc(sizeof(*headp) + len, GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
+
+	headp = (struct mm_io_header *)event;
+	headp->type = MMIO_MAGIC | (MMIO_MARKER << MMIO_OPCODE_SHIFT);
+	headp->data_len = len;
+
+	if (copy_from_user(event + sizeof(*headp), buffer, len)) {
+		kfree(event);
+		return -EFAULT;
+	}
+
+	spin_lock_irq(&trace_lock);
+#if 0 /* XXX: convert this to use tracing */
+	if (is_enabled())
+		relay_write(chan, event, sizeof(*headp) + len);
+	else
+#endif
+		len = -EINVAL;
+	spin_unlock_irq(&trace_lock);
+	kfree(event);
+	return len;
+}
+#endif
+
+static void print_pte(unsigned long address)
+{
+	int level;
+	pte_t *pte = lookup_address(address, &level);
+
+	if (!pte) {
+		pr_err(NAME "Error in %s: no pte for page 0x%08lx\n",
+							__func__, address);
+		return;
+	}
+
+	if (level == PG_LEVEL_2M) {
+		pr_emerg(NAME "4MB pages are not currently supported: "
+							"0x%08lx\n", address);
+		BUG();
+	}
+	pr_info(NAME "pte for 0x%lx: 0x%llx 0x%llx\n", address,
+		(unsigned long long)pte_val(*pte),
+		(unsigned long long)pte_val(*pte) & _PAGE_PRESENT);
+}
+
+/*
+ * For some reason the pre/post pairs have been called in an
+ * unmatched order. Report and die.
+ */
+static void die_kmmio_nesting_error(struct pt_regs *regs, unsigned long addr)
+{
+	const struct trap_reason *my_reason = &get_cpu_var(pf_reason);
+	pr_emerg(NAME "unexpected fault for address: 0x%08lx, "
+					"last fault for address: 0x%08lx\n",
+					addr, my_reason->addr);
+	print_pte(addr);
+	print_symbol(KERN_EMERG "faulting IP is at %s\n", regs->ip);
+	print_symbol(KERN_EMERG "last faulting IP was at %s\n", my_reason->ip);
+#ifdef __i386__
+	pr_emerg("eax: %08lx   ebx: %08lx   ecx: %08lx   edx: %08lx\n",
+			regs->ax, regs->bx, regs->cx, regs->dx);
+	pr_emerg("esi: %08lx   edi: %08lx   ebp: %08lx   esp: %08lx\n",
+			regs->si, regs->di, regs->bp, regs->sp);
+#else
+	pr_emerg("rax: %016lx   rcx: %016lx   rdx: %016lx\n",
+					regs->ax, regs->cx, regs->dx);
+	pr_emerg("rsi: %016lx   rdi: %016lx   rbp: %016lx   rsp: %016lx\n",
+				regs->si, regs->di, regs->bp, regs->sp);
+#endif
+	put_cpu_var(pf_reason);
+	BUG();
+}
+
+static void pre(struct kmmio_probe *p, struct pt_regs *regs,
+						unsigned long addr)
+{
+	struct trap_reason *my_reason = &get_cpu_var(pf_reason);
+	struct mmiotrace_rw *my_trace = &get_cpu_var(cpu_trace);
+	const unsigned long instptr = instruction_pointer(regs);
+	const enum reason_type type = get_ins_type(instptr);
+	struct remap_trace *trace = p->user_data;
+
+	/* it doesn't make sense to have more than one active trace per cpu */
+	if (my_reason->active_traces)
+		die_kmmio_nesting_error(regs, addr);
+	else
+		my_reason->active_traces++;
+
+	my_reason->type = type;
+	my_reason->addr = addr;
+	my_reason->ip = instptr;
+
+	my_trace->phys = addr - trace->probe.addr + trace->phys;
+	my_trace->map_id = trace->id;
+
+	/*
+	 * Only record the program counter when requested.
+	 * It may taint clean-room reverse engineering.
+	 */
+	if (trace_pc)
+		my_trace->pc = instptr;
+	else
+		my_trace->pc = 0;
+
+	/*
+	 * XXX: the timestamp recorded will be *after* the tracing has been
+	 * done, not at the time we hit the instruction. SMP implications
+	 * on event ordering?
+	 */
+
+	switch (type) {
+	case REG_READ:
+		my_trace->opcode = MMIO_READ;
+		my_trace->width = get_ins_mem_width(instptr);
+		break;
+	case REG_WRITE:
+		my_trace->opcode = MMIO_WRITE;
+		my_trace->width = get_ins_mem_width(instptr);
+		my_trace->value = get_ins_reg_val(instptr, regs);
+		break;
+	case IMM_WRITE:
+		my_trace->opcode = MMIO_WRITE;
+		my_trace->width = get_ins_mem_width(instptr);
+		my_trace->value = get_ins_imm_val(instptr);
+		break;
+	default:
+		{
+			unsigned char *ip = (unsigned char *)instptr;
+			my_trace->opcode = MMIO_UNKNOWN_OP;
+			my_trace->width = 0;
+			my_trace->value = (*ip) << 16 | *(ip + 1) << 8 |
+								*(ip + 2);
+		}
+	}
+	put_cpu_var(cpu_trace);
+	put_cpu_var(pf_reason);
+}
+
+static void post(struct kmmio_probe *p, unsigned long condition,
+							struct pt_regs *regs)
+{
+	struct trap_reason *my_reason = &get_cpu_var(pf_reason);
+	struct mmiotrace_rw *my_trace = &get_cpu_var(cpu_trace);
+
+	/* this should always return the active_trace count to 0 */
+	my_reason->active_traces--;
+	if (my_reason->active_traces) {
+		pr_emerg(NAME "unexpected post handler");
+		BUG();
+	}
+
+	switch (my_reason->type) {
+	case REG_READ:
+		my_trace->value = get_ins_reg_val(my_reason->ip, regs);
+		break;
+	default:
+		break;
+	}
+
+	mmio_trace_rw(my_trace);
+	put_cpu_var(cpu_trace);
+	put_cpu_var(pf_reason);
+}
+
+static void ioremap_trace_core(unsigned long offset, unsigned long size,
+							void __iomem *addr)
+{
+	static atomic_t next_id;
+	struct remap_trace *trace = kmalloc(sizeof(*trace), GFP_KERNEL);
+	struct mmiotrace_map map = {
+		.phys = offset,
+		.virt = (unsigned long)addr,
+		.len = size,
+		.opcode = MMIO_PROBE
+	};
+
+	if (!trace) {
+		pr_err(NAME "kmalloc failed in ioremap\n");
+		return;
+	}
+
+	*trace = (struct remap_trace) {
+		.probe = {
+			.addr = (unsigned long)addr,
+			.len = size,
+			.pre_handler = pre,
+			.post_handler = post,
+			.user_data = trace
+		},
+		.phys = offset,
+		.id = atomic_inc_return(&next_id)
+	};
+	map.map_id = trace->id;
+
+	spin_lock_irq(&trace_lock);
+	if (!is_enabled())
+		goto not_enabled;
+
+	mmio_trace_mapping(&map);
+	list_add_tail(&trace->list, &trace_list);
+	if (!nommiotrace)
+		register_kmmio_probe(&trace->probe);
+
+not_enabled:
+	spin_unlock_irq(&trace_lock);
+}
+
+void
+mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr)
+{
+	if (!is_enabled()) /* recheck and proper locking in *_core() */
+		return;
+
+	pr_debug(NAME "ioremap_*(0x%lx, 0x%lx) = %p\n", offset, size, addr);
+	if ((filter_offset) && (offset != filter_offset))
+		return;
+	ioremap_trace_core(offset, size, addr);
+}
+
+static void iounmap_trace_core(volatile void __iomem *addr)
+{
+	struct mmiotrace_map map = {
+		.phys = 0,
+		.virt = (unsigned long)addr,
+		.len = 0,
+		.opcode = MMIO_UNPROBE
+	};
+	struct remap_trace *trace;
+	struct remap_trace *tmp;
+	struct remap_trace *found_trace = NULL;
+
+	pr_debug(NAME "Unmapping %p.\n", addr);
+
+	spin_lock_irq(&trace_lock);
+	if (!is_enabled())
+		goto not_enabled;
+
+	list_for_each_entry_safe(trace, tmp, &trace_list, list) {
+		if ((unsigned long)addr == trace->probe.addr) {
+			if (!nommiotrace)
+				unregister_kmmio_probe(&trace->probe);
+			list_del(&trace->list);
+			found_trace = trace;
+			break;
+		}
+	}
+	map.map_id = (found_trace) ? found_trace->id : -1;
+	mmio_trace_mapping(&map);
+
+not_enabled:
+	spin_unlock_irq(&trace_lock);
+	if (found_trace) {
+		synchronize_rcu(); /* unregister_kmmio_probe() requirement */
+		kfree(found_trace);
+	}
+}
+
+void mmiotrace_iounmap(volatile void __iomem *addr)
+{
+	might_sleep();
+	if (is_enabled()) /* recheck and proper locking in *_core() */
+		iounmap_trace_core(addr);
+}
+
+static void clear_trace_list(void)
+{
+	struct remap_trace *trace;
+	struct remap_trace *tmp;
+
+	/*
+	 * No locking required, because the caller ensures we are in a
+	 * critical section via mutex, and is_enabled() is false,
+	 * i.e. nothing can traverse or modify this list.
+	 * Caller also ensures is_enabled() cannot change.
+	 */
+	list_for_each_entry(trace, &trace_list, list) {
+		pr_notice(NAME "purging non-iounmapped "
+					"trace @0x%08lx, size 0x%lx.\n",
+					trace->probe.addr, trace->probe.len);
+		if (!nommiotrace)
+			unregister_kmmio_probe(&trace->probe);
+	}
+	synchronize_rcu(); /* unregister_kmmio_probe() requirement */
+
+	list_for_each_entry_safe(trace, tmp, &trace_list, list) {
+		list_del(&trace->list);
+		kfree(trace);
+	}
+}
+
+#if 0 /* XXX: out of order */
+static struct file_operations fops_marker = {
+	.owner =	THIS_MODULE,
+	.write =	write_marker
+};
+#endif
+
+void enable_mmiotrace(void)
+{
+	mutex_lock(&mmiotrace_mutex);
+	if (is_enabled())
+		goto out;
+
+#if 0 /* XXX: tracing does not support text entries */
+	marker_file = debugfs_create_file("marker", 0660, dir, NULL,
+								&fops_marker);
+	if (!marker_file)
+		pr_err(NAME "marker file creation failed.\n");
+#endif
+
+	if (nommiotrace)
+		pr_info(NAME "MMIO tracing disabled.\n");
+	spin_lock_irq(&trace_lock);
+	atomic_inc(&mmiotrace_enabled);
+	spin_unlock_irq(&trace_lock);
+	pr_info(NAME "enabled.\n");
+out:
+	mutex_unlock(&mmiotrace_mutex);
+}
+
+void disable_mmiotrace(void)
+{
+	mutex_lock(&mmiotrace_mutex);
+	if (!is_enabled())
+		goto out;
+
+	spin_lock_irq(&trace_lock);
+	atomic_dec(&mmiotrace_enabled);
+	BUG_ON(is_enabled());
+	spin_unlock_irq(&trace_lock);
+
+	clear_trace_list(); /* guarantees: no more kmmio callbacks */
+	if (marker_file) {
+		debugfs_remove(marker_file);
+		marker_file = NULL;
+	}
+
+	pr_info(NAME "disabled.\n");
+out:
+	mutex_unlock(&mmiotrace_mutex);
+}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bd5e05c654dc..099374bbfed6 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -227,6 +227,7 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 
 	return pte_offset_kernel(pmd, address);
 }
+EXPORT_SYMBOL_GPL(lookup_address);
 
 /*
  * Set the new pmd in all the pgds we know about:
diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c
new file mode 100644
index 000000000000..efa1911e20ca
--- /dev/null
+++ b/arch/x86/mm/pf_in.c
@@ -0,0 +1,489 @@
+/*
+ *  Fault Injection Test harness (FI)
+ *  Copyright (C) Intel Crop.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version 2
+ *  of the License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307,
+ *  USA.
+ *
+ */
+
+/*  Id: pf_in.c,v 1.1.1.1 2002/11/12 05:56:32 brlock Exp
+ *  Copyright by Intel Crop., 2002
+ *  Louis Zhuang (louis.zhuang@intel.com)
+ *
+ *  Bjorn Steinbrink (B.Steinbrink@gmx.de), 2007
+ */
+
+#include <linux/module.h>
+#include <linux/ptrace.h> /* struct pt_regs */
+#include "pf_in.h"
+
+#ifdef __i386__
+/* IA32 Manual 3, 2-1 */
+static unsigned char prefix_codes[] = {
+	0xF0, 0xF2, 0xF3, 0x2E, 0x36, 0x3E, 0x26, 0x64,
+	0x65, 0x2E, 0x3E, 0x66, 0x67
+};
+/* IA32 Manual 3, 3-432*/
+static unsigned int reg_rop[] = {
+	0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F
+};
+static unsigned int reg_wop[] = { 0x88, 0x89 };
+static unsigned int imm_wop[] = { 0xC6, 0xC7 };
+/* IA32 Manual 3, 3-432*/
+static unsigned int rw8[] = { 0x88, 0x8A, 0xC6 };
+static unsigned int rw32[] = {
+	0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F
+};
+static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F };
+static unsigned int mw16[] = { 0xB70F, 0xBF0F };
+static unsigned int mw32[] = { 0x89, 0x8B, 0xC7 };
+static unsigned int mw64[] = {};
+#else /* not __i386__ */
+static unsigned char prefix_codes[] = {
+	0x66, 0x67, 0x2E, 0x3E, 0x26, 0x64, 0x65, 0x36,
+	0xF0, 0xF3, 0xF2,
+	/* REX Prefixes */
+	0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+	0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f
+};
+/* AMD64 Manual 3, Appendix A*/
+static unsigned int reg_rop[] = {
+	0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F
+};
+static unsigned int reg_wop[] = { 0x88, 0x89 };
+static unsigned int imm_wop[] = { 0xC6, 0xC7 };
+static unsigned int rw8[] = { 0xC6, 0x88, 0x8A };
+static unsigned int rw32[] = {
+	0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F
+};
+/* 8 bit only */
+static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F };
+/* 16 bit only */
+static unsigned int mw16[] = { 0xB70F, 0xBF0F };
+/* 16 or 32 bit */
+static unsigned int mw32[] = { 0xC7 };
+/* 16, 32 or 64 bit */
+static unsigned int mw64[] = { 0x89, 0x8B };
+#endif /* not __i386__ */
+
+static int skip_prefix(unsigned char *addr, int *shorted, int *enlarged,
+								int *rexr)
+{
+	int i;
+	unsigned char *p = addr;
+	*shorted = 0;
+	*enlarged = 0;
+	*rexr = 0;
+
+restart:
+	for (i = 0; i < ARRAY_SIZE(prefix_codes); i++) {
+		if (*p == prefix_codes[i]) {
+			if (*p == 0x66)
+				*shorted = 1;
+#ifdef __amd64__
+			if ((*p & 0xf8) == 0x48)
+				*enlarged = 1;
+			if ((*p & 0xf4) == 0x44)
+				*rexr = 1;
+#endif
+			p++;
+			goto restart;
+		}
+	}
+
+	return (p - addr);
+}
+
+static int get_opcode(unsigned char *addr, unsigned int *opcode)
+{
+	int len;
+
+	if (*addr == 0x0F) {
+		/* 0x0F is extension instruction */
+		*opcode = *(unsigned short *)addr;
+		len = 2;
+	} else {
+		*opcode = *addr;
+		len = 1;
+	}
+
+	return len;
+}
+
+#define CHECK_OP_TYPE(opcode, array, type) \
+	for (i = 0; i < ARRAY_SIZE(array); i++) { \
+		if (array[i] == opcode) { \
+			rv = type; \
+			goto exit; \
+		} \
+	}
+
+enum reason_type get_ins_type(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char *p;
+	int shorted, enlarged, rexr;
+	int i;
+	enum reason_type rv = OTHERS;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += get_opcode(p, &opcode);
+
+	CHECK_OP_TYPE(opcode, reg_rop, REG_READ);
+	CHECK_OP_TYPE(opcode, reg_wop, REG_WRITE);
+	CHECK_OP_TYPE(opcode, imm_wop, IMM_WRITE);
+
+exit:
+	return rv;
+}
+#undef CHECK_OP_TYPE
+
+static unsigned int get_ins_reg_width(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char *p;
+	int i, shorted, enlarged, rexr;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += get_opcode(p, &opcode);
+
+	for (i = 0; i < ARRAY_SIZE(rw8); i++)
+		if (rw8[i] == opcode)
+			return 1;
+
+	for (i = 0; i < ARRAY_SIZE(rw32); i++)
+		if (rw32[i] == opcode)
+			return (shorted ? 2 : (enlarged ? 8 : 4));
+
+	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
+	return 0;
+}
+
+unsigned int get_ins_mem_width(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char *p;
+	int i, shorted, enlarged, rexr;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += get_opcode(p, &opcode);
+
+	for (i = 0; i < ARRAY_SIZE(mw8); i++)
+		if (mw8[i] == opcode)
+			return 1;
+
+	for (i = 0; i < ARRAY_SIZE(mw16); i++)
+		if (mw16[i] == opcode)
+			return 2;
+
+	for (i = 0; i < ARRAY_SIZE(mw32); i++)
+		if (mw32[i] == opcode)
+			return shorted ? 2 : 4;
+
+	for (i = 0; i < ARRAY_SIZE(mw64); i++)
+		if (mw64[i] == opcode)
+			return shorted ? 2 : (enlarged ? 8 : 4);
+
+	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
+	return 0;
+}
+
+/*
+ * Define register ident in mod/rm byte.
+ * Note: these are NOT the same as in ptrace-abi.h.
+ */
+enum {
+	arg_AL = 0,
+	arg_CL = 1,
+	arg_DL = 2,
+	arg_BL = 3,
+	arg_AH = 4,
+	arg_CH = 5,
+	arg_DH = 6,
+	arg_BH = 7,
+
+	arg_AX = 0,
+	arg_CX = 1,
+	arg_DX = 2,
+	arg_BX = 3,
+	arg_SP = 4,
+	arg_BP = 5,
+	arg_SI = 6,
+	arg_DI = 7,
+#ifdef __amd64__
+	arg_R8  = 8,
+	arg_R9  = 9,
+	arg_R10 = 10,
+	arg_R11 = 11,
+	arg_R12 = 12,
+	arg_R13 = 13,
+	arg_R14 = 14,
+	arg_R15 = 15
+#endif
+};
+
+static unsigned char *get_reg_w8(int no, struct pt_regs *regs)
+{
+	unsigned char *rv = NULL;
+
+	switch (no) {
+	case arg_AL:
+		rv = (unsigned char *)&regs->ax;
+		break;
+	case arg_BL:
+		rv = (unsigned char *)&regs->bx;
+		break;
+	case arg_CL:
+		rv = (unsigned char *)&regs->cx;
+		break;
+	case arg_DL:
+		rv = (unsigned char *)&regs->dx;
+		break;
+	case arg_AH:
+		rv = 1 + (unsigned char *)&regs->ax;
+		break;
+	case arg_BH:
+		rv = 1 + (unsigned char *)&regs->bx;
+		break;
+	case arg_CH:
+		rv = 1 + (unsigned char *)&regs->cx;
+		break;
+	case arg_DH:
+		rv = 1 + (unsigned char *)&regs->dx;
+		break;
+#ifdef __amd64__
+	case arg_R8:
+		rv = (unsigned char *)&regs->r8;
+		break;
+	case arg_R9:
+		rv = (unsigned char *)&regs->r9;
+		break;
+	case arg_R10:
+		rv = (unsigned char *)&regs->r10;
+		break;
+	case arg_R11:
+		rv = (unsigned char *)&regs->r11;
+		break;
+	case arg_R12:
+		rv = (unsigned char *)&regs->r12;
+		break;
+	case arg_R13:
+		rv = (unsigned char *)&regs->r13;
+		break;
+	case arg_R14:
+		rv = (unsigned char *)&regs->r14;
+		break;
+	case arg_R15:
+		rv = (unsigned char *)&regs->r15;
+		break;
+#endif
+	default:
+		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
+		break;
+	}
+	return rv;
+}
+
+static unsigned long *get_reg_w32(int no, struct pt_regs *regs)
+{
+	unsigned long *rv = NULL;
+
+	switch (no) {
+	case arg_AX:
+		rv = &regs->ax;
+		break;
+	case arg_BX:
+		rv = &regs->bx;
+		break;
+	case arg_CX:
+		rv = &regs->cx;
+		break;
+	case arg_DX:
+		rv = &regs->dx;
+		break;
+	case arg_SP:
+		rv = &regs->sp;
+		break;
+	case arg_BP:
+		rv = &regs->bp;
+		break;
+	case arg_SI:
+		rv = &regs->si;
+		break;
+	case arg_DI:
+		rv = &regs->di;
+		break;
+#ifdef __amd64__
+	case arg_R8:
+		rv = &regs->r8;
+		break;
+	case arg_R9:
+		rv = &regs->r9;
+		break;
+	case arg_R10:
+		rv = &regs->r10;
+		break;
+	case arg_R11:
+		rv = &regs->r11;
+		break;
+	case arg_R12:
+		rv = &regs->r12;
+		break;
+	case arg_R13:
+		rv = &regs->r13;
+		break;
+	case arg_R14:
+		rv = &regs->r14;
+		break;
+	case arg_R15:
+		rv = &regs->r15;
+		break;
+#endif
+	default:
+		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
+	}
+
+	return rv;
+}
+
+unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs)
+{
+	unsigned int opcode;
+	unsigned char mod_rm;
+	int reg;
+	unsigned char *p;
+	int i, shorted, enlarged, rexr;
+	unsigned long rv;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += get_opcode(p, &opcode);
+	for (i = 0; i < ARRAY_SIZE(reg_rop); i++)
+		if (reg_rop[i] == opcode) {
+			rv = REG_READ;
+			goto do_work;
+		}
+
+	for (i = 0; i < ARRAY_SIZE(reg_wop); i++)
+		if (reg_wop[i] == opcode) {
+			rv = REG_WRITE;
+			goto do_work;
+		}
+
+	printk(KERN_ERR "mmiotrace: Not a register instruction, opcode "
+							"0x%02x\n", opcode);
+	goto err;
+
+do_work:
+	mod_rm = *p;
+	reg = ((mod_rm >> 3) & 0x7) | (rexr << 3);
+	switch (get_ins_reg_width(ins_addr)) {
+	case 1:
+		return *get_reg_w8(reg, regs);
+
+	case 2:
+		return *(unsigned short *)get_reg_w32(reg, regs);
+
+	case 4:
+		return *(unsigned int *)get_reg_w32(reg, regs);
+
+#ifdef __amd64__
+	case 8:
+		return *(unsigned long *)get_reg_w32(reg, regs);
+#endif
+
+	default:
+		printk(KERN_ERR "mmiotrace: Error width# %d\n", reg);
+	}
+
+err:
+	return 0;
+}
+
+unsigned long get_ins_imm_val(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char mod_rm;
+	unsigned char mod;
+	unsigned char *p;
+	int i, shorted, enlarged, rexr;
+	unsigned long rv;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &shorted, &enlarged, &rexr);
+	p += get_opcode(p, &opcode);
+	for (i = 0; i < ARRAY_SIZE(imm_wop); i++)
+		if (imm_wop[i] == opcode) {
+			rv = IMM_WRITE;
+			goto do_work;
+		}
+
+	printk(KERN_ERR "mmiotrace: Not an immediate instruction, opcode "
+							"0x%02x\n", opcode);
+	goto err;
+
+do_work:
+	mod_rm = *p;
+	mod = mod_rm >> 6;
+	p++;
+	switch (mod) {
+	case 0:
+		/* if r/m is 5 we have a 32 disp (IA32 Manual 3, Table 2-2)  */
+		/* AMD64: XXX Check for address size prefix? */
+		if ((mod_rm & 0x7) == 0x5)
+			p += 4;
+		break;
+
+	case 1:
+		p += 1;
+		break;
+
+	case 2:
+		p += 4;
+		break;
+
+	case 3:
+	default:
+		printk(KERN_ERR "mmiotrace: not a memory access instruction "
+						"at 0x%lx, rm_mod=0x%02x\n",
+						ins_addr, mod_rm);
+	}
+
+	switch (get_ins_reg_width(ins_addr)) {
+	case 1:
+		return *(unsigned char *)p;
+
+	case 2:
+		return *(unsigned short *)p;
+
+	case 4:
+		return *(unsigned int *)p;
+
+#ifdef __amd64__
+	case 8:
+		return *(unsigned long *)p;
+#endif
+
+	default:
+		printk(KERN_ERR "mmiotrace: Error: width.\n");
+	}
+
+err:
+	return 0;
+}
diff --git a/arch/x86/mm/pf_in.h b/arch/x86/mm/pf_in.h
new file mode 100644
index 000000000000..e05341a51a27
--- /dev/null
+++ b/arch/x86/mm/pf_in.h
@@ -0,0 +1,39 @@
+/*
+ *  Fault Injection Test harness (FI)
+ *  Copyright (C) Intel Crop.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version 2
+ *  of the License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307,
+ *  USA.
+ *
+ */
+
+#ifndef __PF_H_
+#define __PF_H_
+
+enum reason_type {
+	NOT_ME,	/* page fault is not in regions */
+	NOTHING,	/* access others point in regions */
+	REG_READ,	/* read from addr to reg */
+	REG_WRITE,	/* write from reg to addr */
+	IMM_WRITE,	/* write from imm to addr */
+	OTHERS	/* Other instructions can not intercept */
+};
+
+enum reason_type get_ins_type(unsigned long ins_addr);
+unsigned int get_ins_mem_width(unsigned long ins_addr);
+unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs);
+unsigned long get_ins_imm_val(unsigned long ins_addr);
+
+#endif /* __PF_H_ */
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
new file mode 100644
index 000000000000..cfa60b227c8d
--- /dev/null
+++ b/arch/x86/mm/testmmiotrace.c
@@ -0,0 +1,71 @@
+/*
+ * Written by Pekka Paalanen, 2008 <pq@iki.fi>
+ */
+#include <linux/module.h>
+#include <asm/io.h>
+
+#define MODULE_NAME "testmmiotrace"
+
+static unsigned long mmio_address;
+module_param(mmio_address, ulong, 0);
+MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB.");
+
+static void do_write_test(void __iomem *p)
+{
+	unsigned int i;
+	for (i = 0; i < 256; i++)
+		iowrite8(i, p + i);
+	for (i = 1024; i < (5 * 1024); i += 2)
+		iowrite16(i * 12 + 7, p + i);
+	for (i = (5 * 1024); i < (16 * 1024); i += 4)
+		iowrite32(i * 212371 + 13, p + i);
+}
+
+static void do_read_test(void __iomem *p)
+{
+	unsigned int i;
+	for (i = 0; i < 256; i++)
+		ioread8(p + i);
+	for (i = 1024; i < (5 * 1024); i += 2)
+		ioread16(p + i);
+	for (i = (5 * 1024); i < (16 * 1024); i += 4)
+		ioread32(p + i);
+}
+
+static void do_test(void)
+{
+	void __iomem *p = ioremap_nocache(mmio_address, 0x4000);
+	if (!p) {
+		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
+		return;
+	}
+	do_write_test(p);
+	do_read_test(p);
+	iounmap(p);
+}
+
+static int __init init(void)
+{
+	if (mmio_address == 0) {
+		pr_err(MODULE_NAME ": you have to use the module argument "
+							"mmio_address.\n");
+		pr_err(MODULE_NAME ": DO NOT LOAD THIS MODULE UNLESS"
+				" YOU REALLY KNOW WHAT YOU ARE DOING!\n");
+		return -ENXIO;
+	}
+
+	pr_warning(MODULE_NAME ": WARNING: mapping 16 kB @ 0x%08lx "
+					"in PCI address space, and writing "
+					"rubbish in there.\n", mmio_address);
+	do_test();
+	return 0;
+}
+
+static void __exit cleanup(void)
+{
+	pr_debug(MODULE_NAME ": unloaded.\n");
+}
+
+module_init(init);
+module_exit(cleanup);
+MODULE_LICENSE("GPL");
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/base/cpu.c b/drivers/base/cpu.c
index 6fe417429977..93ff0d881c8e 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -125,11 +125,13 @@ struct sysdev_class_attribute attr_##type##_map = 			\
 print_cpus_func(online);
 print_cpus_func(possible);
 print_cpus_func(present);
+print_cpus_func(system);
 
 struct sysdev_class_attribute *cpu_state_attr[] = {
 	&attr_online_map,
 	&attr_possible_map,
 	&attr_present_map,
+	&attr_system_map,
 };
 
 static int cpu_states_init(void)
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c
index e63927cce5b5..f165f6577ce7 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 2056cfc624dc..4ba75d302827 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/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 9a2da8a6c860..fc2f2462af46 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -181,7 +181,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	   any need to change it. */
 	struct mempolicy *oldpol;
 	cpumask_t oldmask = current->cpus_allowed;
-	int node = pcibus_to_node(dev->bus);
+	int node = dev_to_node(&dev->dev);
 
 	if (node >= 0) {
 		node_to_cpumask_ptr(nodecpumask, node);
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 259c8051155d..57a6c46228fe 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -399,6 +399,7 @@ static inline void __cpus_remap(cpumask_t *dstp, const cpumask_t *srcp,
 extern cpumask_t cpu_possible_map;
 extern cpumask_t cpu_online_map;
 extern cpumask_t cpu_present_map;
+extern cpumask_t cpu_system_map;
 
 #if NR_CPUS > 1
 #define num_online_cpus()	cpus_weight(cpu_online_map)
@@ -407,6 +408,7 @@ extern cpumask_t cpu_present_map;
 #define cpu_online(cpu)		cpu_isset((cpu), cpu_online_map)
 #define cpu_possible(cpu)	cpu_isset((cpu), cpu_possible_map)
 #define cpu_present(cpu)	cpu_isset((cpu), cpu_present_map)
+#define cpu_system(cpu)		cpu_isset((cpu), cpu_system_map)
 #else
 #define num_online_cpus()	1
 #define num_possible_cpus()	1
@@ -414,8 +416,11 @@ extern cpumask_t cpu_present_map;
 #define cpu_online(cpu)		((cpu) == 0)
 #define cpu_possible(cpu)	((cpu) == 0)
 #define cpu_present(cpu)	((cpu) == 0)
+#define cpu_system(cpu)		((cpu) == 0)
 #endif
 
+extern int cpus_match_system(cpumask_t mask);
+
 #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 726761e24003..b5c116b200c5 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -78,6 +78,8 @@ extern void cpuset_track_online_nodes(void);
 
 extern int current_cpuset_is_being_rebound(void);
 
+extern struct blocking_notifier_head system_map_notifier;
+
 #else /* !CONFIG_CPUSETS */
 
 static inline int cpuset_init_early(void) { return 0; }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index cfb1627ac51c..f350cc36c689 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -5,6 +5,7 @@
 
 #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/irq.h b/include/linux/irq.h
index 1883a85625dd..2d9520fd8132 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -243,14 +243,7 @@ static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
 }
 #endif
 
-#ifdef CONFIG_AUTO_IRQ_AFFINITY
 extern int select_smp_affinity(unsigned int irq);
-#else
-static inline int select_smp_affinity(unsigned int irq)
-{
-	return 1;
-}
-#endif
 
 extern int no_irq_affinity;
 
diff --git a/include/linux/list.h b/include/linux/list.h
index dac16f99c701..2d870fce3532 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -87,65 +87,6 @@ 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.
  *
@@ -176,36 +117,6 @@ 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
@@ -229,25 +140,6 @@ 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.
  */
@@ -361,62 +253,6 @@ 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.
@@ -621,57 +457,6 @@ 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
@@ -722,31 +507,6 @@ 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)) {
@@ -755,27 +515,6 @@ 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;
@@ -786,38 +525,6 @@ 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)
@@ -839,63 +546,6 @@ 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) \
@@ -956,23 +606,6 @@ 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))
-
 #else
 #warning "don't include kernel headers in userspace"
 #endif /* __KERNEL__ */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
new file mode 100644
index 000000000000..dd6b64b160fc
--- /dev/null
+++ b/include/linux/mmiotrace.h
@@ -0,0 +1,89 @@
+#ifndef MMIOTRACE_H
+#define MMIOTRACE_H
+
+#include <asm/types.h>
+
+#ifdef __KERNEL__
+
+#include <linux/list.h>
+
+struct kmmio_probe;
+struct pt_regs;
+
+typedef void (*kmmio_pre_handler_t)(struct kmmio_probe *,
+				struct pt_regs *, unsigned long addr);
+typedef void (*kmmio_post_handler_t)(struct kmmio_probe *,
+				unsigned long condition, struct pt_regs *);
+
+struct kmmio_probe {
+	struct list_head list; /* kmmio internal list */
+	unsigned long addr; /* start location of the probe point */
+	unsigned long len; /* length of the probe region */
+	kmmio_pre_handler_t pre_handler; /* Called before addr is executed. */
+	kmmio_post_handler_t post_handler; /* Called after addr is executed */
+	void *user_data;
+};
+
+/* kmmio is active by some kmmio_probes? */
+static inline int is_kmmio_active(void)
+{
+	extern unsigned int kmmio_count;
+	return kmmio_count;
+}
+
+extern int register_kmmio_probe(struct kmmio_probe *p);
+extern void unregister_kmmio_probe(struct kmmio_probe *p);
+
+/* Called from page fault handler. */
+extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
+
+/* Called from ioremap.c */
+#ifdef CONFIG_MMIOTRACE
+extern void
+mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr);
+extern void mmiotrace_iounmap(volatile void __iomem *addr);
+#else
+static inline void
+mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr)
+{
+}
+static inline void mmiotrace_iounmap(volatile void __iomem *addr)
+{
+}
+#endif /* CONFIG_MMIOTRACE_HOOKS */
+
+enum mm_io_opcode {
+	MMIO_READ = 0x1,     /* struct mmiotrace_rw */
+	MMIO_WRITE = 0x2,    /* struct mmiotrace_rw */
+	MMIO_PROBE = 0x3,    /* struct mmiotrace_map */
+	MMIO_UNPROBE = 0x4,  /* struct mmiotrace_map */
+	MMIO_MARKER = 0x5,   /* raw char data */
+	MMIO_UNKNOWN_OP = 0x6, /* struct mmiotrace_rw */
+};
+
+struct mmiotrace_rw {
+	unsigned long phys;	/* PCI address of register */
+	unsigned long value;
+	unsigned long pc;	/* optional program counter */
+	int map_id;
+	unsigned char opcode;	/* one of MMIO_{READ,WRITE,UNKNOWN_OP} */
+	unsigned char width;	/* size of register access in bytes */
+};
+
+struct mmiotrace_map {
+	unsigned long phys;	/* base address in PCI space */
+	unsigned long virt;	/* base virtual address */
+	unsigned long len;	/* mapping size */
+	int map_id;
+	unsigned char opcode;	/* MMIO_PROBE or MMIO_UNPROBE */
+};
+
+/* in kernel/trace/trace_mmiotrace.c */
+extern void enable_mmiotrace(void);
+extern void disable_mmiotrace(void);
+extern void mmio_trace_rw(struct mmiotrace_rw *rw);
+extern void mmio_trace_mapping(struct mmiotrace_map *map);
+
+#endif /* __KERNEL__ */
+
+#endif /* MMIOTRACE_H */
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index b3dccd68629e..f7b4782d1382 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -153,7 +153,10 @@ 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 ae5ba4e46d76..a83f5faf84d8 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -42,6 +42,7 @@
 #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
@@ -182,6 +183,27 @@ 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.
@@ -238,6 +260,8 @@ extern void call_rcu_bh(struct rcu_head *head,
 /* Exported common interfaces */
 extern void synchronize_rcu(void);
 extern void rcu_barrier(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index d038aa6e5ee1..0e45c91f41c1 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -42,10 +42,39 @@
 #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);
@@ -57,6 +86,7 @@ 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);
@@ -83,20 +113,20 @@ 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 5fd87a52f6d3..209979e3b6d6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -159,6 +159,8 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 }
 #endif
 
+extern unsigned long long time_sync_thresh;
+
 /*
  * Task state bitmask. NOTE! These bits are also
  * encoded in fs/proc/array.c: get_task_state().
@@ -295,7 +297,8 @@ extern void softlockup_tick(void);
 extern void spawn_softlockup_task(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern unsigned long  softlockup_thresh;
+extern unsigned int  softlockup_panic;
+extern unsigned long softlockup_thresh;
 extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
 extern unsigned long sysctl_hung_task_warnings;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b7b3362f7717..608395606a95 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -105,6 +105,8 @@ extern int vm_highmem_is_dirtyable;
 extern int block_dump;
 extern int laptop_mode;
 
+extern unsigned long determine_dirtyable_memory(void);
+
 extern int dirty_ratio_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
 		loff_t *ppos);
diff --git a/init/main.c b/init/main.c
index eaf2ef1c8caf..eba1eea17696 100644
--- a/init/main.c
+++ b/init/main.c
@@ -760,6 +760,7 @@ 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 ddd6d1830c38..6c87f32be2f7 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -75,6 +75,7 @@ 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/cpuset.c b/kernel/cpuset.c
index 8b35fbd8292f..1d792262c144 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -64,6 +64,7 @@
  * short circuit some hooks.
  */
 int number_of_cpusets __read_mostly;
+int number_of_system_sets __read_mostly;
 
 /* Forward declare cgroup structures */
 struct cgroup_subsys cpuset_subsys;
@@ -131,6 +132,7 @@ typedef enum {
 	CS_SCHED_LOAD_BALANCE,
 	CS_SPREAD_PAGE,
 	CS_SPREAD_SLAB,
+	CS_SYSTEM,
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
@@ -164,6 +166,11 @@ static inline int is_spread_slab(const struct cpuset *cs)
 	return test_bit(CS_SPREAD_SLAB, &cs->flags);
 }
 
+static inline int is_system(const struct cpuset *cs)
+{
+	return test_bit(CS_SYSTEM, &cs->flags);
+}
+
 /*
  * Increment this integer everytime any cpuset changes its
  * mems_allowed value.  Users of cpusets can track this generation
@@ -186,7 +193,9 @@ static inline int is_spread_slab(const struct cpuset *cs)
 static int cpuset_mems_generation;
 
 static struct cpuset top_cpuset = {
-	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
+	.flags = ((1 << CS_CPU_EXCLUSIVE) |
+		  (1 << CS_MEM_EXCLUSIVE) |
+		  (1 << CS_SYSTEM)),
 	.cpus_allowed = CPU_MASK_ALL,
 	.mems_allowed = NODE_MASK_ALL,
 };
@@ -468,6 +477,9 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 		}
 	}
 
+	if (number_of_system_sets == 1 && is_system(cur) && !is_system(trial))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1051,6 +1063,74 @@ static int update_relax_domain_level(struct cpuset *cs, char *buf)
 	return 0;
 }
 
+BLOCKING_NOTIFIER_HEAD(system_map_notifier);
+EXPORT_SYMBOL_GPL(system_map_notifier);
+
+int cpus_match_system(cpumask_t mask)
+{
+	cpumask_t online_system, online_mask;
+
+	cpus_and(online_system, cpu_system_map, cpu_online_map);
+	cpus_and(online_mask, mask, cpu_online_map);
+
+	return cpus_equal(online_system, online_mask);
+}
+
+static void rebuild_system_map(void)
+{
+	cpumask_t *new_system_map;
+	struct kfifo *q = NULL;
+	struct cpuset *cp;
+
+	new_system_map = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+	if (!new_system_map)
+		return;
+
+	if (is_system(&top_cpuset)) {
+		cpus_setall(*new_system_map);
+		goto notify;
+	}
+
+	cpus_clear(*new_system_map);
+
+	q = kfifo_alloc(number_of_cpusets * sizeof(cp), GFP_KERNEL, NULL);
+	if (IS_ERR(q))
+		goto done;
+
+	cp = &top_cpuset;
+	__kfifo_put(q, (void *)&cp, sizeof(cp));
+	while (__kfifo_get(q, (void *)&cp, sizeof(cp))) {
+		struct cgroup *cont;
+		struct cpuset *child;
+
+		if (is_system(cp)) {
+			cpus_or(*new_system_map,
+					*new_system_map, cp->cpus_allowed);
+			continue;
+		}
+
+		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+			child = cgroup_cs(cont);
+			__kfifo_put(q, (void *)&child, sizeof(cp));
+		}
+	}
+
+	if (cpus_empty(*new_system_map))
+		BUG();
+
+notify:
+	if (!cpus_match_system(*new_system_map)) {
+		blocking_notifier_call_chain(&system_map_notifier, 0,
+				new_system_map);
+	}
+	cpu_system_map = *new_system_map;
+
+done:
+	kfree(new_system_map);
+	if (q && !IS_ERR(q))
+		kfifo_free(q);
+}
+
 /*
  * update_flag - read a 0 or a 1 in a file and update associated flag
  * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
@@ -1069,6 +1149,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
 	struct cpuset trialcs;
 	int err;
 	int cpus_nonempty, balance_flag_changed;
+	int system_flag_changed;
 
 	turning_on = (simple_strtoul(buf, NULL, 10) != 0);
 
@@ -1085,6 +1166,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
 	cpus_nonempty = !cpus_empty(trialcs.cpus_allowed);
 	balance_flag_changed = (is_sched_load_balance(cs) !=
 		 			is_sched_load_balance(&trialcs));
+	system_flag_changed = (is_system(cs) != is_system(&trialcs));
 
 	mutex_lock(&callback_mutex);
 	cs->flags = trialcs.flags;
@@ -1093,6 +1175,15 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
 	if (cpus_nonempty && balance_flag_changed)
 		rebuild_sched_domains();
 
+	if (system_flag_changed) {
+		rebuild_system_map();
+
+		if (is_system(cs))
+			number_of_system_sets++;
+		else
+			number_of_system_sets--;
+	}
+
 	return 0;
 }
 
@@ -1247,6 +1338,7 @@ typedef enum {
 	FILE_MEMORY_PRESSURE,
 	FILE_SPREAD_PAGE,
 	FILE_SPREAD_SLAB,
+	FILE_SYSTEM,
 } cpuset_filetype_t;
 
 static ssize_t cpuset_common_file_write(struct cgroup *cont,
@@ -1317,6 +1409,9 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
 		retval = update_flag(CS_SPREAD_SLAB, cs, buffer);
 		cs->mems_generation = cpuset_mems_generation++;
 		break;
+	case FILE_SYSTEM:
+		retval = update_flag(CS_SYSTEM, cs, buffer);
+		break;
 	default:
 		retval = -EINVAL;
 		goto out2;
@@ -1416,6 +1511,9 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
 	case FILE_SPREAD_SLAB:
 		*s++ = is_spread_slab(cs) ? '1' : '0';
 		break;
+	case FILE_SYSTEM:
+		*s++ = is_system(cs) ? '1' : '0';
+		break;
 	default:
 		retval = -EINVAL;
 		goto out;
@@ -1513,6 +1611,13 @@ static struct cftype cft_spread_slab = {
 	.private = FILE_SPREAD_SLAB,
 };
 
+static struct cftype cft_system = {
+	.name = "system",
+	.read = cpuset_common_file_read,
+	.write = cpuset_common_file_write,
+	.private = FILE_SYSTEM,
+};
+
 static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	int err;
@@ -1538,6 +1643,8 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
 		return err;
 	if ((err = cgroup_add_file(cont, ss, &cft_spread_slab)) < 0)
 		return err;
+	if ((err = cgroup_add_file(cont, ss, &cft_system)) < 0)
+		return err;
 	/* memory_pressure_enabled is in root cpuset only */
 	if (err == 0 && !cont->parent)
 		err = cgroup_add_file(cont, ss,
@@ -1612,6 +1719,7 @@ static struct cgroup_subsys_state *cpuset_create(
 	if (is_spread_slab(parent))
 		set_bit(CS_SPREAD_SLAB, &cs->flags);
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+	set_bit(CS_SYSTEM, &cs->flags);
 	cpus_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
 	cs->mems_generation = cpuset_mems_generation++;
@@ -1620,6 +1728,7 @@ static struct cgroup_subsys_state *cpuset_create(
 
 	cs->parent = parent;
 	number_of_cpusets++;
+	number_of_system_sets++;
 	return &cs->css ;
 }
 
@@ -1643,8 +1752,11 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 
 	if (is_sched_load_balance(cs))
 		update_flag(CS_SCHED_LOAD_BALANCE, cs, "0");
+	if (!is_system(cs))
+		update_flag(CS_SYSTEM, cs, "1");
 
 	number_of_cpusets--;
+	number_of_system_sets--;
 	kfree(cs);
 }
 
@@ -1696,6 +1808,7 @@ int __init cpuset_init(void)
 		return err;
 
 	number_of_cpusets = 1;
+	number_of_system_sets = 1;
 	return 0;
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 438a01464287..631a3563c4d4 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -11,6 +11,8 @@
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
 
 #include "internals.h"
 
@@ -488,6 +490,24 @@ void free_irq(unsigned int irq, void *dev_id)
 }
 EXPORT_SYMBOL(free_irq);
 
+#if !defined(CONFIG_AUTO_IRQ_AFFINITY) && defined(CONFIG_SMP)
+int select_smp_affinity(unsigned int irq)
+{
+	cpumask_t online_system;
+
+	if (!irq_can_set_affinity(irq))
+		return 0;
+
+	cpus_and(online_system, cpu_system_map, cpu_online_map);
+
+	set_balance_irq_affinity(irq, online_system);
+
+	irq_desc[irq].affinity = online_system;
+	irq_desc[irq].chip->set_affinity(irq, online_system);
+	return 0;
+}
+#endif
+
 /**
  *	request_irq - allocate an interrupt line
  *	@irq: Interrupt line to allocate
@@ -555,7 +575,9 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	action->next = NULL;
 	action->dev_id = dev_id;
 
+#if !defined(CONFIG_AUTO_IRQ_AFFINITY) && defined(CONFIG_SMP)
 	select_smp_affinity(irq);
+#endif
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	if (irqflags & IRQF_SHARED) {
@@ -580,3 +602,46 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	return retval;
 }
 EXPORT_SYMBOL(request_irq);
+
+#ifdef CONFIG_CPUSETS
+static int system_irq_notifier(struct notifier_block *nb,
+		unsigned long action, void *cpus)
+{
+	cpumask_t *new_system_map = (cpumask_t *)cpus;
+	int i;
+
+	for (i = 0; i < NR_IRQS; i++) {
+		struct irq_desc *desc = &irq_desc[i];
+
+		if (desc->chip == &no_irq_chip || !irq_can_set_affinity(i))
+			continue;
+
+		if (cpus_match_system(desc->affinity)) {
+			cpumask_t online_system;
+
+			cpus_and(online_system, *new_system_map,
+				 cpu_online_map);
+
+			set_balance_irq_affinity(i, online_system);
+
+			desc->affinity = online_system;
+			desc->chip->set_affinity(i, online_system);
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fn_system_irq_notifier = {
+	.notifier_call = system_irq_notifier,
+};
+
+static int __init init_irq(void)
+{
+	blocking_notifier_chain_register(&system_map_notifier,
+			&fn_system_irq_notifier);
+	return 0;
+}
+
+module_init(init_irq);
+#endif
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 92cf6930ab51..faf273548366 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -13,6 +13,8 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -106,7 +108,7 @@ static void create_kthread(struct kthread_create_info *create)
 		 */
 		sched_setscheduler(create->result, SCHED_NORMAL, &param);
 		set_user_nice(create->result, KTHREAD_NICE_LEVEL);
-		set_cpus_allowed(create->result, CPU_MASK_ALL);
+		set_cpus_allowed_ptr(create->result, &cpu_system_map);
 	}
 	complete(&create->done);
 }
@@ -232,7 +234,7 @@ int kthreadd(void *unused)
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
 	set_user_nice(tsk, KTHREAD_NICE_LEVEL);
-	set_cpus_allowed(tsk, CPU_MASK_ALL);
+	set_cpus_allowed_ptr(tsk, &cpu_system_map);
 
 	current->flags |= PF_NOFREEZE;
 
@@ -260,3 +262,47 @@ int kthreadd(void *unused)
 
 	return 0;
 }
+
+#ifdef CONFIG_CPUSETS
+static int system_kthread_notifier(struct notifier_block *nb,
+		unsigned long action, void *cpus)
+{
+	cpumask_t *new_system_map = (cpumask_t *)cpus;
+	struct task_struct *g, *t;
+
+again:
+	rcu_read_lock();
+	do_each_thread(g, t) {
+		if (t->parent != kthreadd_task && t != kthreadd_task)
+			continue;
+
+		if (cpus_match_system(t->cpus_allowed) &&
+		    !cpus_equal(t->cpus_allowed, *new_system_map)) {
+			/*
+			 * What is holding a ref on t->usage here?!
+			 */
+			get_task_struct(t);
+			rcu_read_unlock();
+			set_cpus_allowed_ptr(t, new_system_map);
+			put_task_struct(t);
+			goto again;
+		}
+	} while_each_thread(g, t);
+	rcu_read_unlock();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fn_system_kthread_notifier = {
+	.notifier_call = system_kthread_notifier,
+};
+
+static int __init init_kthread(void)
+{
+	blocking_notifier_chain_register(&system_map_notifier,
+			&fn_system_kthread_notifier);
+	return 0;
+}
+
+module_init(init_kthread);
+#endif
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 90a440cbd6de..65548eff029e 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -82,6 +82,8 @@ static int graph_lock(void)
 		__raw_spin_unlock(&lockdep_lock);
 		return 0;
 	}
+	/* prevent any recursions within lockdep from causing deadlocks */
+	current->lockdep_recursion++;
 	return 1;
 }
 
@@ -90,6 +92,7 @@ static inline int graph_unlock(void)
 	if (debug_locks && !__raw_spin_is_locked(&lockdep_lock))
 		return DEBUG_LOCKS_WARN_ON(1);
 
+	current->lockdep_recursion--;
 	__raw_spin_unlock(&lockdep_lock);
 	return 0;
 }
diff --git a/kernel/pid.c b/kernel/pid.c
index 477691576b33..d62e3f7efb37 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/printk.c b/kernel/printk.c
index 5e31cf8cc731..0ee8bb7f7aae 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -665,13 +665,14 @@ static int acquire_console_semaphore_for_printk(unsigned int cpu)
 static const char recursion_bug_msg [] =
 		KERN_CRIT "BUG: recent printk recursion!\n";
 static int recursion_bug;
-static int log_level_unknown = 1;
+	static int new_text_line = 1;
 static char printk_buf[1024];
 
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
-	unsigned long flags;
 	int printed_len = 0;
+	int current_log_level = default_message_loglevel;
+	unsigned long flags;
 	int this_cpu;
 	char *p;
 
@@ -713,61 +714,53 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	printed_len += vscnprintf(printk_buf + printed_len,
 				  sizeof(printk_buf) - printed_len, fmt, args);
 
+
 	/*
 	 * Copy the output into log_buf.  If the caller didn't provide
 	 * appropriate log level tags, we insert them here
 	 */
 	for (p = printk_buf; *p; p++) {
-		if (log_level_unknown) {
-                        /* log_level_unknown signals the start of a new line */
+		if (new_text_line) {
+			/* If a token, set current_log_level and skip over */
+			if (p[0] == '<' && p[1] >= '0' && p[1] <= '7' &&
+			    p[2] == '>') {
+				current_log_level = p[1] - '0';
+				p += 3;
+				printed_len -= 3;
+			}
+
+			/* Always output the token */
+			emit_log_char('<');
+			emit_log_char(current_log_level + '0');
+			emit_log_char('>');
+			printed_len += 3;
+			new_text_line = 0;
+
 			if (printk_time) {
-				int loglev_char;
+				/* Follow the token with the time */
 				char tbuf[50], *tp;
 				unsigned tlen;
 				unsigned long long t;
 				unsigned long nanosec_rem;
 
-				/*
-				 * force the log level token to be
-				 * before the time output.
-				 */
-				if (p[0] == '<' && p[1] >='0' &&
-				   p[1] <= '7' && p[2] == '>') {
-					loglev_char = p[1];
-					p += 3;
-					printed_len -= 3;
-				} else {
-					loglev_char = default_message_loglevel
-						+ '0';
-				}
 				t = cpu_clock(printk_cpu);
 				nanosec_rem = do_div(t, 1000000000);
-				tlen = sprintf(tbuf,
-						"<%c>[%5lu.%06lu] ",
-						loglev_char,
-						(unsigned long)t,
-						nanosec_rem/1000);
+				tlen = sprintf(tbuf, "[%5lu.%06lu] ",
+						(unsigned long) t,
+						nanosec_rem / 1000);
 
 				for (tp = tbuf; tp < tbuf + tlen; tp++)
 					emit_log_char(*tp);
 				printed_len += tlen;
-			} else {
-				if (p[0] != '<' || p[1] < '0' ||
-				   p[1] > '7' || p[2] != '>') {
-					emit_log_char('<');
-					emit_log_char(default_message_loglevel
-						+ '0');
-					emit_log_char('>');
-					printed_len += 3;
-				}
 			}
-			log_level_unknown = 0;
+
 			if (!*p)
 				break;
 		}
+
 		emit_log_char(*p);
 		if (*p == '\n')
-			log_level_unknown = 1;
+			new_text_line = 1;
 	}
 
 	/*
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index f4ffbd0f306f..d8348792f9f5 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 5e02b7740702..27d0748d8d32 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -46,6 +46,7 @@
 #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>
@@ -87,9 +88,14 @@ struct rcu_data {
 	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 +137,24 @@ 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 +162,12 @@ 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 +230,8 @@ 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 +436,34 @@ 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 +486,12 @@ 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 +499,7 @@ 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 +507,7 @@ 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 +517,13 @@ 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 +531,7 @@ 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 +543,29 @@ 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 +573,10 @@ 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 +597,7 @@ 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 +610,10 @@ 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 +640,86 @@ 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 +922,26 @@ 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 +992,8 @@ 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 +1007,11 @@ 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 +1046,40 @@ 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 +1134,196 @@ 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 +1340,9 @@ 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 +1353,9 @@ 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 +1422,11 @@ 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 +1449,15 @@ 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/sched.c b/kernel/sched.c
index 79e75fd4b78f..4a378bc47d91 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"
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  * This is default implementation.
@@ -462,6 +464,7 @@ struct rt_rq {
 #ifdef CONFIG_SMP
 	unsigned long rt_nr_migratory;
 	int overloaded;
+	int pushed;
 #endif
 	int rt_throttled;
 	u64 rt_time;
@@ -500,6 +503,9 @@ struct root_domain {
 	 */
 	cpumask_t rto_mask;
 	atomic_t rto_count;
+#ifdef CONFIG_SMP
+	struct cpupri cpupri;
+#endif
 };
 
 /*
@@ -918,7 +924,7 @@ static inline u64 global_rt_runtime(void)
 	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
-static const unsigned long long time_sync_thresh = 100000;
+unsigned long long time_sync_thresh = 100000;
 
 static DEFINE_PER_CPU(unsigned long long, time_offset);
 static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
@@ -995,6 +1001,8 @@ unsigned long long notrace cpu_clock(int cpu)
 	if (unlikely(delta_time > time_sync_thresh))
 		time = __sync_cpu_clock(time, cpu);
 
+	per_cpu(prev_cpu_time, cpu) = time;
+
 	return time;
 }
 EXPORT_SYMBOL_GPL(cpu_clock);
@@ -5605,6 +5613,9 @@ asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 cpumask_t cpu_present_map __read_mostly;
 EXPORT_SYMBOL(cpu_present_map);
 
+cpumask_t cpu_system_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_system_map);
+
 #ifndef CONFIG_SMP
 cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
 EXPORT_SYMBOL(cpu_online_map);
@@ -6919,6 +6930,8 @@ 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)
@@ -6974,24 +6987,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	rcu_assign_pointer(rq->sd, sd);
 }
 
-/* cpus with isolated domains */
-static cpumask_t cpu_isolated_map = CPU_MASK_NONE;
-
-/* Setup the mask of cpus configured for isolated domains */
-static int __init isolated_cpu_setup(char *str)
-{
-	int ints[NR_CPUS], i;
-
-	str = get_options(str, ARRAY_SIZE(ints), ints);
-	cpus_clear(cpu_isolated_map);
-	for (i = 1; i <= ints[0]; i++)
-		if (ints[i] < NR_CPUS)
-			cpu_set(ints[i], cpu_isolated_map);
-	return 1;
-}
-
-__setup("isolcpus=", isolated_cpu_setup);
-
 /*
  * init_sched_build_groups takes the cpumask we wish to span, and a pointer
  * to a function which identifies what group(along with sched group) a CPU
@@ -7778,7 +7773,7 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map)
 	doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
-	cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
+	*doms_cur = *cpu_map;
 	dattr_cur = NULL;
 	err = build_sched_domains(doms_cur);
 	register_sched_domain_sysctl();
@@ -7859,7 +7854,7 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
 	if (doms_new == NULL) {
 		ndoms_new = 1;
 		doms_new = &fallback_doms;
-		cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+		doms_new[0] = cpu_online_map;
 		dattr_new = NULL;
 	}
 
@@ -8029,7 +8024,7 @@ void __init sched_init_smp(void)
 #endif
 	get_online_cpus();
 	arch_init_sched_domains(&cpu_online_map);
-	cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
+	non_isolated_cpus = cpu_possible_map;
 	if (cpus_empty(non_isolated_cpus))
 		cpu_set(smp_processor_id(), non_isolated_cpus);
 	put_online_cpus();
@@ -8089,6 +8084,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 #ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
+	rt_rq->pushed = 0;
 #endif
 
 	rt_rq->rt_time = 0;
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..0b6a3d110fac
--- /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 2+MAX_RT_PRIO
+#define CPUPRI_NR_PRI_WORDS CPUPRI_NR_PRIORITIES/BITS_PER_LONG
+
+#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_rt.c b/kernel/sched_rt.c
index c2730a5a4f05..79e5ad51b1d2 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -391,8 +391,11 @@ 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);
+		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_se_prio(rt_se));
+	}
 #endif
 #ifdef CONFIG_SMP
 	if (rt_se->nr_cpus_allowed > 1) {
@@ -416,6 +419,10 @@ 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--;
@@ -439,6 +446,11 @@ 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);
+		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
@@ -515,6 +527,15 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 		enqueue_rt_entity(rt_se);
 
 	inc_cpu_load(rq, p->se.load.weight);
+
+#ifdef CONFIG_SMP
+	/*
+	 * Clear the "pushed" state since we have changed the run-queue and
+	 * may need to migrate some of these tasks (see push_rt_tasks() for
+	 * details)
+	 */
+	rq->rt.pushed = 0;
+#endif
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -714,73 +735,6 @@ 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;
@@ -802,17 +756,12 @@ 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
@@ -913,7 +862,7 @@ static int push_rt_task(struct rq *rq)
 	int ret = 0;
 	int paranoid = RT_MAX_TRIES;
 
-	if (!rq->rt.overloaded)
+	if (!rq->rt.overloaded || rq->rt.pushed)
 		return 0;
 
 	next_task = pick_next_highest_task_rt(rq, -1);
@@ -973,6 +922,15 @@ out:
 }
 
 /*
+ * push_rt_tasks()
+ *
+ * Push as many tasks away as possible.  We only need to try once whenever
+ * one or more new tasks are added to our runqueue.  After an inital attempt,
+ * further changes in remote runqueue state will be accounted for with pull
+ * operations.  Therefore, we mark the run-queue as "pushed" here, and clear it
+ * during enqueue.  This primarily helps SCHED_RR tasks which will tend to
+ * have a higher context-switch to enqueue ratio.
+ *
  * TODO: Currently we just use the second highest prio task on
  *       the queue, and stop when it can't migrate (or there's
  *       no more RT tasks).  There may be a case where a lower
@@ -987,6 +945,8 @@ static void push_rt_tasks(struct rq *rq)
 	/* push_rt_task will return true if it moved an RT */
 	while (push_rt_task(rq))
 		;
+
+	rq->rt.pushed = 1;
 }
 
 static int pull_rt_task(struct rq *this_rq)
@@ -1091,7 +1051,7 @@ static void post_schedule_rt(struct rq *rq)
 	 * the lock was owned by prev, we need to release it
 	 * first via finish_lock_switch and then reaquire it here.
 	 */
-	if (unlikely(rq->rt.overloaded)) {
+	if (unlikely(rq->rt.overloaded && !rq->rt.pushed)) {
 		spin_lock_irq(&rq->lock);
 		push_rt_tasks(rq);
 		spin_unlock_irq(&rq->lock);
@@ -1158,6 +1118,8 @@ static void join_domain_rt(struct rq *rq)
 {
 	if (rq->rt.overloaded)
 		rt_set_overload(rq);
+
+	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
 }
 
 /* Assumes rq->lock is held */
@@ -1165,6 +1127,8 @@ static void leave_domain_rt(struct rq *rq)
 {
 	if (rq->rt.overloaded)
 		rt_clear_overload(rq);
+
+	cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
 }
 
 /*
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index d19117e4a602..cc7797936a17 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -27,6 +27,21 @@ static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
 static int __read_mostly did_panic;
 unsigned long __read_mostly softlockup_thresh = 60;
 
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * soft-lockup occurs:
+ */
+unsigned int __read_mostly softlockup_panic =
+				CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
+
+static int __init softlockup_panic_setup(char *str)
+{
+	softlockup_panic = simple_strtoul(str, NULL, 0);
+
+	return 1;
+}
+__setup("softlockup_panic=", softlockup_panic_setup);
+
 static int
 softlock_panic(struct notifier_block *this, unsigned long event, void *ptr)
 {
@@ -120,6 +135,9 @@ void softlockup_tick(void)
 	else
 		dump_stack();
 	spin_unlock(&print_lock);
+
+	if (softlockup_panic)
+		panic("softlockup: hung tasks");
 }
 
 /*
@@ -172,6 +190,9 @@ static void check_hung_task(struct task_struct *t, unsigned long now)
 
 	t->last_switch_timestamp = now;
 	touch_nmi_watchdog();
+
+	if (softlockup_panic)
+		panic("softlockup: blocked tasks");
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e69b65634b52..36f2939d558c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -745,6 +745,17 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "softlockup_panic",
+		.data		= &softlockup_panic,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "softlockup_thresh",
 		.data		= &softlockup_thresh,
 		.maxlen		= sizeof(unsigned long),
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b854a895591e..76050c9fb6af 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -48,6 +48,13 @@ static void tick_do_update_jiffies64(ktime_t now)
 	unsigned long ticks = 0;
 	ktime_t delta;
 
+	/*
+	 * Do a quick check without holding xtime_lock:
+	 */
+	delta = ktime_sub(now, last_jiffies_update);
+	if (delta.tv64 < tick_period.tv64)
+		return;
+
 	/* Reevalute with xtime_lock held */
 	write_seqlock(&xtime_lock);
 
@@ -133,8 +140,6 @@ void tick_nohz_update_jiffies(void)
 	if (!ts->tick_stopped)
 		return;
 
-	touch_softlockup_watchdog();
-
 	cpu_clear(cpu, nohz_cpu_mask);
 	now = ktime_get();
 	ts->idle_waketime = now;
@@ -142,6 +147,8 @@ void tick_nohz_update_jiffies(void)
 	local_irq_save(flags);
 	tick_do_update_jiffies64(now);
 	local_irq_restore(flags);
+
+	touch_softlockup_watchdog();
 }
 
 void tick_nohz_stop_idle(int cpu)
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 7aec123ec1d8..71d17de17288 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -19,5 +19,6 @@ obj-$(CONFIG_FTRACE) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f8040fa195fe..86d72ce6241b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -630,10 +630,10 @@ static int ftraced(void *ignore)
 {
 	unsigned long usecs;
 
-	set_current_state(TASK_INTERRUPTIBLE);
-
 	while (!kthread_should_stop()) {
 
+		set_current_state(TASK_INTERRUPTIBLE);
+
 		/* check once a second */
 		schedule_timeout(HZ);
 
@@ -667,8 +667,6 @@ static int ftraced(void *ignore)
 		wake_up_interruptible(&ftraced_waiters);
 
 		ftrace_shutdown_replenish();
-
-		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);
 	return 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a8d1377b33cb..92e18aefba50 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -27,6 +27,7 @@
 #include <linux/poll.h>
 #include <linux/gfp.h>
 #include <linux/fs.h>
+#include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
 
@@ -35,9 +36,25 @@
 unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly	tracing_thresh;
 
+static unsigned long __read_mostly	tracing_nr_buffers;
+static cpumask_t __read_mostly		tracing_buffer_mask;
+
+#define for_each_tracing_cpu(cpu)	\
+	for_each_cpu_mask(cpu, tracing_buffer_mask)
+
+/* dummy trace to disable tracing */
+static struct tracer no_tracer __read_mostly = {
+	.name		= "none",
+};
+
+static int trace_alloc_page(void);
+static int trace_free_page(void);
+
 static int tracing_disabled = 1;
 
-static long
+static unsigned long tracing_pages_allocated;
+
+long
 ns2usecs(cycle_t nsec)
 {
 	nsec += 500;
@@ -50,26 +67,79 @@ cycle_t ftrace_now(int cpu)
 	return cpu_clock(cpu);
 }
 
+/*
+ * The global_trace is the descriptor that holds the tracing
+ * buffers for the live tracing. For each CPU, it contains
+ * a link list of pages that will store trace entries. The
+ * page descriptor of the pages in the memory is used to hold
+ * the link list by linking the lru item in the page descriptor
+ * to each of the pages in the buffer per CPU.
+ *
+ * For each active CPU there is a data field that holds the
+ * pages for the buffer for that CPU. Each CPU has the same number
+ * of pages allocated for its buffer.
+ */
 static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
+/*
+ * The max_tr is used to snapshot the global_trace when a maximum
+ * latency is reached. Some tracers will use this to store a maximum
+ * trace while it continues examining live traces.
+ *
+ * The buffers for the max_tr are set up the same as the global_trace.
+ * When a snapshot is taken, the link list of the max_tr is swapped
+ * with the link list of the global_trace and the buffers are reset for
+ * the global_trace so the tracing can continue.
+ */
 static struct trace_array	max_tr;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
 
+/* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;
+
+/*
+ * trace_nr_entries is the number of entries that is allocated
+ * for a buffer. Note, the number of entries is always rounded
+ * to ENTRIES_PER_PAGE.
+ */
 static unsigned long		trace_nr_entries = 65536UL;
 
+/* trace_types holds a link list of available tracers. */
 static struct tracer		*trace_types __read_mostly;
+
+/* current_trace points to the tracer that is currently active */
 static struct tracer		*current_trace __read_mostly;
+
+/*
+ * max_tracer_type_len is used to simplify the allocating of
+ * buffers to read userspace tracer names. We keep track of
+ * the longest tracer name registered.
+ */
 static int			max_tracer_type_len;
 
+/*
+ * trace_types_lock is used to protect the trace_types list.
+ * This lock is also used to keep user access serialized.
+ * Accesses from userspace will grab this lock while userspace
+ * activities happen inside the kernel.
+ */
 static DEFINE_MUTEX(trace_types_lock);
+
+/* trace_wait is a waitqueue for tasks blocked on trace_poll */
 static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
+/* trace_flags holds iter_ctrl options */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
 
+/**
+ * trace_wake_up - wake up tasks waiting for trace input
+ *
+ * Simply wakes up any task that is blocked on the trace_wait
+ * queue. These is used with trace_poll for tasks polling the trace.
+ */
 void trace_wake_up(void)
 {
 	/*
@@ -84,9 +154,16 @@ void trace_wake_up(void)
 
 static int __init set_nr_entries(char *str)
 {
+	unsigned long nr_entries;
+	int ret;
+
 	if (!str)
 		return 0;
-	trace_nr_entries = simple_strtoul(str, &str, 0);
+	ret = strict_strtoul(str, 0, &nr_entries);
+	/* nr_entries can not be zero */
+	if (ret < 0 || nr_entries == 0)
+		return 0;
+	trace_nr_entries = nr_entries;
 	return 1;
 }
 __setup("trace_entries=", set_nr_entries);
@@ -96,18 +173,14 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
 	return nsecs / 1000;
 }
 
-enum trace_type {
-	__TRACE_FIRST_TYPE = 0,
-
-	TRACE_FN,
-	TRACE_CTX,
-	TRACE_WAKE,
-	TRACE_STACK,
-	TRACE_SPECIAL,
-
-	__TRACE_LAST_TYPE
-};
-
+/*
+ * trace_flag_type is an enumeration that holds different
+ * states when a trace occurs. These are:
+ *  IRQS_OFF	- interrupts were disabled
+ *  NEED_RESCED - reschedule is requested
+ *  HARDIRQ	- inside an interrupt handler
+ *  SOFTIRQ	- inside a softirq handler
+ */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
 	TRACE_FLAG_NEED_RESCHED		= 0x02,
@@ -115,10 +188,14 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x08,
 };
 
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
 #define TRACE_ITER_SYM_MASK \
 	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
 
-/* These must match the bit postions above */
+/* These must match the bit postions in trace_iterator_flags */
 static const char *trace_options[] = {
 	"print-parent",
 	"sym-offset",
@@ -133,6 +210,15 @@ static const char *trace_options[] = {
 	NULL
 };
 
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a raw_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ */
 static raw_spinlock_t ftrace_max_lock =
 	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 
@@ -163,6 +249,13 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	tracing_record_cmdline(current);
 }
 
+/**
+ * check_pages - integrity check of trace buffers
+ *
+ * As a safty measure we check to make sure the data pages have not
+ * been corrupted. TODO: configure to disable this because it adds
+ * a bit of overhead.
+ */
 void check_pages(struct trace_array_cpu *data)
 {
 	struct page *page, *tmp;
@@ -176,6 +269,13 @@ void check_pages(struct trace_array_cpu *data)
 	}
 }
 
+/**
+ * head_page - page address of the first page in per_cpu buffer.
+ *
+ * head_page returns the page address of the first page in
+ * a per_cpu buffer. This also preforms various consistency
+ * checks to make sure the buffer has not been corrupted.
+ */
 void *head_page(struct trace_array_cpu *data)
 {
 	struct page *page;
@@ -190,7 +290,18 @@ void *head_page(struct trace_array_cpu *data)
 	return page_address(page);
 }
 
-static int
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
 trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
 	int len = (PAGE_SIZE - 1) - s->len;
@@ -205,7 +316,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	va_end(ap);
 
 	/* If we can't write it all, don't bother writing anything */
-	if (ret > len)
+	if (ret >= len)
 		return 0;
 
 	s->len += ret;
@@ -213,6 +324,16 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	return len;
 }
 
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
 static int
 trace_seq_puts(struct trace_seq *s, const char *str)
 {
@@ -251,19 +372,18 @@ trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
 }
 
 #define HEX_CHARS 17
+static const char hex2asc[] = "0123456789abcdef";
 
 static int
 trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 {
 	unsigned char hex[HEX_CHARS];
-	unsigned char *data;
+	unsigned char *data = mem;
 	unsigned char byte;
 	int i, j;
 
 	BUG_ON(len >= HEX_CHARS);
 
-	data = mem;
-
 #ifdef __BIG_ENDIAN
 	for (i = 0, j = 0; i < len; i++) {
 #else
@@ -271,22 +391,10 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 #endif
 		byte = data[i];
 
-		hex[j]   = byte & 0x0f;
-		if (hex[j] >= 10)
-			hex[j] += 'a' - 10;
-		else
-			hex[j] += '0';
-		j++;
-
-		hex[j] = byte >> 4;
-		if (hex[j] >= 10)
-			hex[j] += 'a' - 10;
-		else
-			hex[j] += '0';
-		j++;
+		hex[j++] = hex2asc[byte & 0x0f];
+		hex[j++] = hex2asc[byte >> 4];
 	}
-	hex[j] = ' ';
-	j++;
+	hex[j++] = ' ';
 
 	return trace_seq_putmem(s, hex, j);
 }
@@ -308,6 +416,13 @@ trace_print_seq(struct seq_file *m, struct trace_seq *s)
 	trace_seq_reset(s);
 }
 
+/*
+ * flip the trace buffers between two trace descriptors.
+ * This usually is the buffers between the global_trace and
+ * the max_tr to record a snapshot of a current trace.
+ *
+ * The ftrace_max_lock must be held.
+ */
 static void
 flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
 {
@@ -329,6 +444,15 @@ flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
 	check_pages(tr2);
 }
 
+/**
+ * update_max_tr - snapshot all trace buffers from global_trace to max_tr
+ * @tr: tracer
+ * @tsk: the task with the latency
+ * @cpu: The cpu that initiated the trace.
+ *
+ * Flip the buffers between the @tr and the max_tr and record information
+ * about which task was the cause of this latency.
+ */
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
@@ -338,7 +462,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 	/* clear out all the previous traces */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = tr->data[i];
 		flip_trace(max_tr.data[i], data);
 		tracing_reset(data);
@@ -353,6 +477,8 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
  * @tr - tracer
  * @tsk - task with the latency
  * @cpu - the cpu of the buffer to copy.
+ *
+ * Flip the trace of a single CPU buffer between the @tr and the max_tr.
  */
 void
 update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
@@ -362,7 +488,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
-	for_each_possible_cpu(i)
+	for_each_tracing_cpu(i)
 		tracing_reset(max_tr.data[i]);
 
 	flip_trace(max_tr.data[cpu], data);
@@ -372,6 +498,12 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	__raw_spin_unlock(&ftrace_max_lock);
 }
 
+/**
+ * register_tracer - register a tracer with the ftrace system.
+ * @type - the plugin for the tracer
+ *
+ * Register a new plugin tracer.
+ */
 int register_tracer(struct tracer *type)
 {
 	struct tracer *t;
@@ -408,7 +540,7 @@ int register_tracer(struct tracer *type)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			data = tr->data[i];
 			if (!head_page(data))
 				continue;
@@ -427,7 +559,7 @@ int register_tracer(struct tracer *type)
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			data = tr->data[i];
 			if (!head_page(data))
 				continue;
@@ -480,6 +612,7 @@ void unregister_tracer(struct tracer *type)
 void tracing_reset(struct trace_array_cpu *data)
 {
 	data->trace_idx = 0;
+	data->overrun = 0;
 	data->trace_head = data->trace_tail = head_page(data);
 	data->trace_head_idx = 0;
 	data->trace_tail_idx = 0;
@@ -491,7 +624,12 @@ static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
 static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
 static int cmdline_idx;
 static DEFINE_SPINLOCK(trace_cmdline_lock);
-atomic_t trace_record_cmdline_disabled;
+
+/* trace in all context switches */
+atomic_t trace_record_cmdline_enabled __read_mostly;
+
+/* temporary disable recording */
+atomic_t trace_record_cmdline_disabled __read_mostly;
 
 static void trace_init_cmdlines(void)
 {
@@ -616,6 +754,7 @@ tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data)
 	if (data->trace_head == data->trace_tail &&
 	    idx_next == data->trace_tail_idx) {
 		/* overrun */
+		data->overrun++;
 		data->trace_tail_idx++;
 		if (data->trace_tail_idx >= ENTRIES_PER_PAGE) {
 			data->trace_tail =
@@ -638,7 +777,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
 	pc = preempt_count();
 
 	entry->preempt_count	= pc & 0xff;
-	entry->pid		= tsk->pid;
+	entry->pid		= (tsk) ? tsk->pid : 0;
 	entry->t		= ftrace_now(raw_smp_processor_id());
 	entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
@@ -695,6 +834,48 @@ __trace_special(void *__tr, void *__data,
 	trace_wake_up();
 }
 
+#ifdef CONFIG_MMIOTRACE
+void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data,
+						struct mmiotrace_rw *rw)
+{
+	struct trace_entry *entry;
+	unsigned long irq_flags;
+
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
+
+	entry			= tracing_get_trace_entry(tr, data);
+	tracing_generic_entry_update(entry, 0);
+	entry->type		= TRACE_MMIO_RW;
+	entry->mmiorw		= *rw;
+
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
+
+	trace_wake_up();
+}
+
+void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data,
+						struct mmiotrace_map *map)
+{
+	struct trace_entry *entry;
+	unsigned long irq_flags;
+
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
+
+	entry			= tracing_get_trace_entry(tr, data);
+	tracing_generic_entry_update(entry, 0);
+	entry->type		= TRACE_MMIO_MAP;
+	entry->mmiomap		= *map;
+
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
+
+	trace_wake_up();
+}
+#endif
+
 void __trace_stack(struct trace_array *tr,
 		   struct trace_array_cpu *data,
 		   unsigned long flags,
@@ -857,7 +1038,7 @@ find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 	int next_cpu = -1;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		if (!head_page(tr->data[cpu]))
 			continue;
 		ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
@@ -964,8 +1145,10 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 	mutex_lock(&trace_types_lock);
 
-	if (!current_trace || current_trace != iter->trace)
+	if (!current_trace || current_trace != iter->trace) {
+		mutex_unlock(&trace_types_lock);
 		return NULL;
+	}
 
 	atomic_inc(&trace_record_cmdline_disabled);
 
@@ -980,7 +1163,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		iter->prev_ent = NULL;
 		iter->prev_cpu = -1;
 
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			iter->next_idx[i] = 0;
 			iter->next_page[i] = NULL;
 		}
@@ -1097,7 +1280,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	if (type)
 		name = type->name;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		if (head_page(tr->data[cpu])) {
 			total += tr->data[cpu]->trace_idx;
 			if (tr->data[cpu]->trace_idx > tr->entries)
@@ -1169,12 +1352,12 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
-	if (hardirq && softirq)
+	if (hardirq && softirq) {
 		trace_seq_putc(s, 'H');
-	else {
-		if (hardirq)
+	} else {
+		if (hardirq) {
 			trace_seq_putc(s, 'h');
-		else {
+		} else {
 			if (softirq)
 				trace_seq_putc(s, 's');
 			else
@@ -1218,6 +1401,7 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 	char *comm;
 	int S, T;
 	int i;
+	unsigned state;
 
 	if (!next_entry)
 		next_entry = entry;
@@ -1248,11 +1432,11 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 		break;
 	case TRACE_CTX:
 	case TRACE_WAKE:
-		S = entry->ctx.prev_state < sizeof(state_to_char) ?
-			state_to_char[entry->ctx.prev_state] : 'X';
 		T = entry->ctx.next_state < sizeof(state_to_char) ?
 			state_to_char[entry->ctx.next_state] : 'X';
 
+		state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0;
+		S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X';
 		comm = trace_find_cmdline(entry->ctx.next_pid);
 		trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n",
 				 entry->ctx.prev_pid,
@@ -1526,7 +1710,7 @@ static int trace_empty(struct trace_iterator *iter)
 	struct trace_array_cpu *data;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		data = iter->tr->data[cpu];
 
 		if (head_page(data) && data->trace_idx &&
@@ -1539,6 +1723,9 @@ static int trace_empty(struct trace_iterator *iter)
 
 static int print_trace_line(struct trace_iterator *iter)
 {
+	if (iter->trace && iter->trace->print_line)
+		return iter->trace->print_line(iter);
+
 	if (trace_flags & TRACE_ITER_BIN)
 		return print_bin_fmt(iter);
 
@@ -1835,7 +2022,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 
 	raw_local_irq_disable();
 	__raw_spin_lock(&ftrace_max_lock);
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		/*
 		 * Increase/decrease the disabled counter if we are
 		 * about to flip a bit in the cpumask:
@@ -1916,8 +2103,8 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
 	int neg = 0;
 	int i;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
@@ -2006,18 +2193,21 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
-	long val;
 	char buf[64];
+	long val;
+	int ret;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	val = !!val;
 
@@ -2109,10 +2299,10 @@ tracing_max_lat_read(struct file *filp, char __user *ubuf,
 	char buf[64];
 	int r;
 
-	r = snprintf(buf, 64, "%ld\n",
+	r = snprintf(buf, sizeof(buf), "%ld\n",
 		     *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
-	if (r > 64)
-		r = 64;
+	if (r > sizeof(buf))
+		r = sizeof(buf);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -2121,18 +2311,21 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
 	long *ptr = filp->private_data;
-	long val;
 	char buf[64];
+	long val;
+	int ret;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	*ptr = val * 1000;
 
@@ -2159,10 +2352,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (!iter)
 		return -ENOMEM;
 
+	mutex_lock(&trace_types_lock);
 	iter->tr = &global_trace;
-
+	iter->trace = current_trace;
 	filp->private_data = iter;
 
+	if (iter->trace->pipe_open)
+		iter->trace->pipe_open(iter);
+	mutex_unlock(&trace_types_lock);
+
 	return 0;
 }
 
@@ -2186,8 +2384,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 		 * Always select as readable when in blocking mode
 		 */
 		return POLLIN | POLLRDNORM;
-	}
-	else {
+	} else {
 		if (!trace_empty(iter))
 			return POLLIN | POLLRDNORM;
 		poll_wait(filp, &trace_wait, poll_table);
@@ -2232,12 +2429,25 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		return cnt;
 	}
 
+	mutex_lock(&trace_types_lock);
+	if (iter->trace->read) {
+		ret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
+		if (ret) {
+			read = ret;
+			goto out;
+		}
+	}
+
 	trace_seq_reset(&iter->seq);
 	start = 0;
 
 	while (trace_empty(iter)) {
-		if (!(trace_flags & TRACE_ITER_BLOCK))
-			return -EWOULDBLOCK;
+
+		if ((filp->f_flags & O_NONBLOCK)) {
+			read = -EAGAIN;
+			goto out;
+		}
+
 		/*
 		 * This is a make-shift waitqueue. The reason we don't use
 		 * an actual wait queue is because:
@@ -2250,13 +2460,22 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		set_current_state(TASK_INTERRUPTIBLE);
 		iter->tr->waiter = current;
 
-		/* sleep for one second, and try again. */
-		schedule_timeout(HZ);
+		mutex_unlock(&trace_types_lock);
+
+		/* sleep for 100 msecs, and try again. */
+		schedule_timeout(HZ/10);
+
+		mutex_lock(&trace_types_lock);
 
 		iter->tr->waiter = NULL;
 
-		if (signal_pending(current))
-			return -EINTR;
+		if (signal_pending(current)) {
+			read = -EINTR;
+			goto out;
+		}
+
+		if (iter->trace != current_trace)
+			goto out;
 
 		/*
 		 * We block until we read something and tracing is disabled.
@@ -2275,13 +2494,15 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	/* stop when tracing is finished */
 	if (trace_empty(iter))
-		return 0;
+		goto out;
 
 	if (cnt >= PAGE_SIZE)
 		cnt = PAGE_SIZE - 1;
 
-	memset(iter, 0, sizeof(*iter));
-	iter->tr = &global_trace;
+	/* reset all but tr, trace, and overruns */
+	memset(&iter->seq, 0,
+	       sizeof(struct trace_iterator) -
+	       offsetof(struct trace_iterator, seq));
 	iter->pos = -1;
 
 	/*
@@ -2298,7 +2519,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	ftrace_enabled = 0;
 #endif
 	smp_wmb();
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		data = iter->tr->data[cpu];
 
 		if (!head_page(data) || !data->trace_idx)
@@ -2311,6 +2532,11 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	for_each_cpu_mask(cpu, mask) {
 		data = iter->tr->data[cpu];
 		__raw_spin_lock(&data->lock);
+
+		if (data->overrun > iter->last_overrun[cpu])
+			iter->overrun[cpu] +=
+				data->overrun - iter->last_overrun[cpu];
+		iter->last_overrun[cpu] = data->overrun;
 	}
 
 	while (find_next_entry_inc(iter) != NULL) {
@@ -2358,9 +2584,108 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	if (ret)
 		read = -EFAULT;
 
+out:
+	mutex_unlock(&trace_types_lock);
+
 	return read;
 }
 
+static ssize_t
+tracing_entries_read(struct file *filp, char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = sprintf(buf, "%lu\n", tr->entries);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_entries_write(struct file *filp, const char __user *ubuf,
+		      size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	char buf[64];
+	int ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	/* must have at least 1 entry */
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&trace_types_lock);
+
+	if (current_trace != &no_tracer) {
+		cnt = -EBUSY;
+		pr_info("ftrace: set current_tracer to none"
+			" before modifying buffer size\n");
+		goto out;
+	}
+
+	if (val > global_trace.entries) {
+		long pages_requested;
+		unsigned long freeable_pages;
+
+		/* make sure we have enough memory before mapping */
+		pages_requested =
+			(val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE;
+
+		/* account for each buffer (and max_tr) */
+		pages_requested *= tracing_nr_buffers * 2;
+
+		/* Check for overflow */
+		if (pages_requested < 0) {
+			cnt = -ENOMEM;
+			goto out;
+		}
+
+		freeable_pages = determine_dirtyable_memory();
+
+		/* we only allow to request 1/4 of useable memory */
+		if (pages_requested >
+		    ((freeable_pages + tracing_pages_allocated) / 4)) {
+			cnt = -ENOMEM;
+			goto out;
+		}
+
+		while (global_trace.entries < val) {
+			if (trace_alloc_page()) {
+				cnt = -ENOMEM;
+				goto out;
+			}
+			/* double check that we don't go over the known pages */
+			if (tracing_pages_allocated > pages_requested)
+				break;
+		}
+
+	} else {
+		/* include the number of entries in val (inc of page entries) */
+		while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))
+			trace_free_page();
+	}
+
+	filp->f_pos += cnt;
+
+ out:
+	max_tr.entries = global_trace.entries;
+	mutex_unlock(&trace_types_lock);
+
+	return cnt;
+}
+
 static struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -2386,6 +2711,12 @@ static struct file_operations tracing_pipe_fops = {
 	.release	= tracing_release_pipe,
 };
 
+static struct file_operations tracing_entries_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_entries_read,
+	.write		= tracing_entries_write,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static ssize_t
@@ -2497,6 +2828,12 @@ static __init void tracer_init_debugfs(void)
 		pr_warning("Could not create debugfs "
 			   "'tracing_threash' entry\n");
 
+	entry = debugfs_create_file("trace_entries", 0644, d_tracer,
+				    &global_trace, &tracing_entries_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'tracing_threash' entry\n");
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 				    &ftrace_update_tot_cnt,
@@ -2510,22 +2847,17 @@ static __init void tracer_init_debugfs(void)
 #endif
 }
 
-/* dummy trace to disable tracing */
-static struct tracer no_tracer __read_mostly =
-{
-	.name		= "none",
-};
-
 static int trace_alloc_page(void)
 {
 	struct trace_array_cpu *data;
 	struct page *page, *tmp;
 	LIST_HEAD(pages);
 	void *array;
+	unsigned pages_allocated = 0;
 	int i;
 
 	/* first allocate a page for each CPU */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		array = (void *)__get_free_page(GFP_KERNEL);
 		if (array == NULL) {
 			printk(KERN_ERR "tracer: failed to allocate page"
@@ -2533,6 +2865,7 @@ static int trace_alloc_page(void)
 			goto free_pages;
 		}
 
+		pages_allocated++;
 		page = virt_to_page(array);
 		list_add(&page->lru, &pages);
 
@@ -2544,15 +2877,15 @@ static int trace_alloc_page(void)
 			       "for trace buffer!\n");
 			goto free_pages;
 		}
+		pages_allocated++;
 		page = virt_to_page(array);
 		list_add(&page->lru, &pages);
 #endif
 	}
 
 	/* Now that we successfully allocate a page per CPU, add them */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i];
-		data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 		page = list_entry(pages.next, struct page, lru);
 		list_del_init(&page->lru);
 		list_add_tail(&page->lru, &data->trace_pages);
@@ -2560,13 +2893,13 @@ static int trace_alloc_page(void)
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 		data = max_tr.data[i];
-		data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 		page = list_entry(pages.next, struct page, lru);
 		list_del_init(&page->lru);
 		list_add_tail(&page->lru, &data->trace_pages);
 		SetPageLRU(page);
 #endif
 	}
+	tracing_pages_allocated += pages_allocated;
 	global_trace.entries += ENTRIES_PER_PAGE;
 
 	return 0;
@@ -2579,6 +2912,57 @@ static int trace_alloc_page(void)
 	return -ENOMEM;
 }
 
+static int trace_free_page(void)
+{
+	struct trace_array_cpu *data;
+	struct page *page;
+	struct list_head *p;
+	int i;
+	int ret = 0;
+
+	/* free one page from each buffer */
+	for_each_tracing_cpu(i) {
+		data = global_trace.data[i];
+		p = data->trace_pages.next;
+		if (p == &data->trace_pages) {
+			/* should never happen */
+			WARN_ON(1);
+			tracing_disabled = 1;
+			ret = -1;
+			break;
+		}
+		page = list_entry(p, struct page, lru);
+		ClearPageLRU(page);
+		list_del(&page->lru);
+		tracing_pages_allocated--;
+		__free_page(page);
+
+		tracing_reset(data);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+		data = max_tr.data[i];
+		p = data->trace_pages.next;
+		if (p == &data->trace_pages) {
+			/* should never happen */
+			WARN_ON(1);
+			tracing_disabled = 1;
+			ret = -1;
+			break;
+		}
+		page = list_entry(p, struct page, lru);
+		ClearPageLRU(page);
+		list_del(&page->lru);
+		tracing_pages_allocated--;
+		__free_page(page);
+
+		tracing_reset(data);
+#endif
+	}
+	global_trace.entries -= ENTRIES_PER_PAGE;
+
+	return ret;
+}
+
 __init static int tracer_alloc_buffers(void)
 {
 	struct trace_array_cpu *data;
@@ -2590,8 +2974,12 @@ __init static int tracer_alloc_buffers(void)
 
 	global_trace.ctrl = tracer_enabled;
 
+	/* TODO: make the number of buffers hot pluggable with CPUS */
+	tracing_nr_buffers = num_possible_cpus();
+	tracing_buffer_mask = cpu_possible_map;
+
 	/* Allocate the first page for all buffers */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
 		max_tr.data[i] = &per_cpu(max_data, i);
 
@@ -2609,6 +2997,9 @@ __init static int tracer_alloc_buffers(void)
 		/* use the LRU flag to differentiate the two buffers */
 		ClearPageLRU(page);
 
+		data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+		max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
 /* Only allocate if we are actually using the max trace */
 #ifdef CONFIG_TRACER_MAX_TRACE
 		array = (void *)__get_free_page(GFP_KERNEL);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 47ec8a0bd552..fe5bac8e2115 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -5,6 +5,21 @@
 #include <asm/atomic.h>
 #include <linux/sched.h>
 #include <linux/clocksource.h>
+#include <linux/mmiotrace.h>
+
+enum trace_type {
+	__TRACE_FIRST_TYPE = 0,
+
+	TRACE_FN,
+	TRACE_CTX,
+	TRACE_WAKE,
+	TRACE_STACK,
+	TRACE_SPECIAL,
+	TRACE_MMIO_RW,
+	TRACE_MMIO_MAP,
+
+	__TRACE_LAST_TYPE
+};
 
 /*
  * Function trace entry - function address and parent function addres:
@@ -63,6 +78,8 @@ struct trace_entry {
 		struct ctx_switch_entry		ctx;
 		struct special_entry		special;
 		struct stack_entry		stack;
+		struct mmiotrace_rw		mmiorw;
+		struct mmiotrace_map		mmiomap;
 	};
 };
 
@@ -85,6 +102,7 @@ struct trace_array_cpu {
 	void			*trace_head; /* producer */
 	void			*trace_tail; /* consumer */
 	unsigned long		trace_idx;
+	unsigned long		overrun;
 	unsigned long		saved_latency;
 	unsigned long		critical_start;
 	unsigned long		critical_end;
@@ -122,14 +140,19 @@ struct tracer {
 	void			(*init)(struct trace_array *tr);
 	void			(*reset)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
+	void			(*pipe_open)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
 	void			(*start)(struct trace_iterator *iter);
 	void			(*stop)(struct trace_iterator *iter);
+	ssize_t			(*read)(struct trace_iterator *iter,
+					struct file *filp, char __user *ubuf,
+					size_t cnt, loff_t *ppos);
 	void			(*ctrl_update)(struct trace_array *tr);
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	int			(*selftest)(struct tracer *trace,
 					    struct trace_array *tr);
 #endif
+	int			(*print_line)(struct trace_iterator *iter);
 	struct tracer		*next;
 	int			print_max;
 };
@@ -144,10 +167,14 @@ struct trace_seq {
  * results to users and which routines might sleep, etc:
  */
 struct trace_iterator {
-	struct trace_seq	seq;
 	struct trace_array	*tr;
 	struct tracer		*trace;
+	void			*private;
+	long			last_overrun[NR_CPUS];
+	long			overrun[NR_CPUS];
 
+	/* The below is zeroed out in pipe_read */
+	struct trace_seq	seq;
 	struct trace_entry	*ent;
 	int			cpu;
 
@@ -205,6 +232,8 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 extern unsigned long tracing_max_latency;
 extern unsigned long tracing_thresh;
 
+extern atomic_t trace_record_cmdline_enabled;
+
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
@@ -250,6 +279,15 @@ extern unsigned long ftrace_update_tot_cnt;
 extern int DYN_FTRACE_TEST_NAME(void);
 #endif
 
+#ifdef CONFIG_MMIOTRACE
+extern void __trace_mmiotrace_rw(struct trace_array *tr,
+				struct trace_array_cpu *data,
+				struct mmiotrace_rw *rw);
+extern void __trace_mmiotrace_map(struct trace_array *tr,
+				struct trace_array_cpu *data,
+				struct mmiotrace_map *map);
+#endif
+
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 #ifdef CONFIG_FTRACE
 extern int trace_selftest_startup_function(struct tracer *trace,
@@ -282,9 +320,18 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
+extern long ns2usecs(cycle_t nsec);
 
 extern unsigned long trace_flags;
 
+/*
+ * trace_iterator_flags is an enumeration that defines bit
+ * positions into trace_flags that controls the output.
+ *
+ * NOTE: These bits must match the trace_options array in
+ *       trace.c.
+ */
 enum trace_iterator_flags {
 	TRACE_ITER_PRINT_PARENT		= 0x01,
 	TRACE_ITER_SYM_OFFSET		= 0x02,
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 4165d34bd28a..0a084656d7cf 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -29,12 +29,14 @@ static void function_reset(struct trace_array *tr)
 static void start_function_trace(struct trace_array *tr)
 {
 	function_reset(tr);
+	atomic_inc(&trace_record_cmdline_enabled);
 	tracing_start_function_trace();
 }
 
 static void stop_function_trace(struct trace_array *tr)
 {
 	tracing_stop_function_trace();
+	atomic_dec(&trace_record_cmdline_enabled);
 }
 
 static void function_trace_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
new file mode 100644
index 000000000000..79be4a18ec1e
--- /dev/null
+++ b/kernel/trace/trace_mmiotrace.c
@@ -0,0 +1,220 @@
+/*
+ * Memory mapped I/O tracing
+ *
+ * Copyright (C) 2008 Pekka Paalanen <pq@iki.fi>
+ */
+
+#define DEBUG 1
+
+#include <linux/kernel.h>
+#include <linux/mmiotrace.h>
+#include <linux/pci.h>
+
+#include "trace.h"
+
+static struct trace_array *mmio_trace_array;
+
+static void mmio_reset_data(struct trace_array *tr)
+{
+	int cpu;
+
+	tr->time_start = ftrace_now(tr->cpu);
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr->data[cpu]);
+}
+
+static void mmio_trace_init(struct trace_array *tr)
+{
+	pr_debug("in %s\n", __func__);
+	mmio_trace_array = tr;
+	if (tr->ctrl) {
+		mmio_reset_data(tr);
+		enable_mmiotrace();
+	}
+}
+
+static void mmio_trace_reset(struct trace_array *tr)
+{
+	pr_debug("in %s\n", __func__);
+	if (tr->ctrl)
+		disable_mmiotrace();
+	mmio_reset_data(tr);
+	mmio_trace_array = NULL;
+}
+
+static void mmio_trace_ctrl_update(struct trace_array *tr)
+{
+	pr_debug("in %s\n", __func__);
+	if (tr->ctrl) {
+		mmio_reset_data(tr);
+		enable_mmiotrace();
+	} else {
+		disable_mmiotrace();
+	}
+}
+
+static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
+{
+	int ret = 0;
+	int i;
+	resource_size_t start, end;
+	const struct pci_driver *drv = pci_dev_driver(dev);
+
+	/* XXX: incomplete checks for trace_seq_printf() return value */
+	ret += trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
+				dev->bus->number, dev->devfn,
+				dev->vendor, dev->device, dev->irq);
+	/*
+	 * XXX: is pci_resource_to_user() appropriate, since we are
+	 * supposed to interpret the __ioremap() phys_addr argument based on
+	 * these printed values?
+	 */
+	for (i = 0; i < 7; i++) {
+		pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+		ret += trace_seq_printf(s, " %llx",
+			(unsigned long long)(start |
+			(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
+	}
+	for (i = 0; i < 7; i++) {
+		pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+		ret += trace_seq_printf(s, " %llx",
+			dev->resource[i].start < dev->resource[i].end ?
+			(unsigned long long)(end - start) + 1 : 0);
+	}
+	if (drv)
+		ret += trace_seq_printf(s, " %s\n", drv->name);
+	else
+		ret += trace_seq_printf(s, " \n");
+	return ret;
+}
+
+/* XXX: This is not called for trace_pipe file! */
+static void mmio_print_header(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct pci_dev *dev = NULL;
+
+	trace_seq_printf(s, "VERSION 20070824\n");
+
+	for_each_pci_dev(dev)
+		mmio_print_pcidev(s, dev);
+	/* XXX: return value? What if header is very long? */
+}
+
+static int mmio_print_rw(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+	struct mmiotrace_rw *rw	= &entry->mmiorw;
+	struct trace_seq *s	= &iter->seq;
+	unsigned long long t	= ns2usecs(entry->t);
+	unsigned long usec_rem	= do_div(t, 1000000ULL);
+	unsigned secs		= (unsigned long)t;
+	int ret = 1;
+
+	switch (entry->mmiorw.opcode) {
+	case MMIO_READ:
+		ret = trace_seq_printf(s,
+			"R %d %lu.%06lu %d 0x%lx 0x%lx 0x%lx %d\n",
+			rw->width, secs, usec_rem, rw->map_id, rw->phys,
+			rw->value, rw->pc, 0);
+		break;
+	case MMIO_WRITE:
+		ret = trace_seq_printf(s,
+			"W %d %lu.%06lu %d 0x%lx 0x%lx 0x%lx %d\n",
+			rw->width, secs, usec_rem, rw->map_id, rw->phys,
+			rw->value, rw->pc, 0);
+		break;
+	case MMIO_UNKNOWN_OP:
+		ret = trace_seq_printf(s,
+			"UNKNOWN %lu.%06lu %d 0x%lx %02x,%02x,%02x 0x%lx %d\n",
+			secs, usec_rem, rw->map_id, rw->phys,
+			(rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff,
+			(rw->value >> 0) & 0xff, rw->pc, 0);
+		break;
+	default:
+		ret = trace_seq_printf(s, "rw what?\n");
+		break;
+	}
+	if (ret)
+		return 1;
+	return 0;
+}
+
+static int mmio_print_map(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+	struct mmiotrace_map *m	= &entry->mmiomap;
+	struct trace_seq *s	= &iter->seq;
+	unsigned long long t	= ns2usecs(entry->t);
+	unsigned long usec_rem	= do_div(t, 1000000ULL);
+	unsigned secs		= (unsigned long)t;
+	int ret = 1;
+
+	switch (entry->mmiorw.opcode) {
+	case MMIO_PROBE:
+		ret = trace_seq_printf(s,
+			"MAP %lu.%06lu %d 0x%lx 0x%lx 0x%lx 0x%lx %d\n",
+			secs, usec_rem, m->map_id, m->phys, m->virt, m->len,
+			0UL, entry->pid);
+		break;
+	case MMIO_UNPROBE:
+		ret = trace_seq_printf(s,
+			"UNMAP %lu.%06lu %d 0x%lx %d\n",
+			secs, usec_rem, m->map_id, 0UL, entry->pid);
+		break;
+	default:
+		ret = trace_seq_printf(s, "map what?\n");
+		break;
+	}
+	if (ret)
+		return 1;
+	return 0;
+}
+
+/* return 0 to abort printing without consuming current entry in pipe mode */
+static int mmio_print_line(struct trace_iterator *iter)
+{
+	switch (iter->ent->type) {
+	case TRACE_MMIO_RW:
+		return mmio_print_rw(iter);
+	case TRACE_MMIO_MAP:
+		return mmio_print_map(iter);
+	default:
+		return 1; /* ignore unknown entries */
+	}
+}
+
+static struct tracer mmio_tracer __read_mostly =
+{
+	.name		= "mmiotrace",
+	.init		= mmio_trace_init,
+	.reset		= mmio_trace_reset,
+	.open		= mmio_print_header,
+	.ctrl_update	= mmio_trace_ctrl_update,
+	.print_line	= mmio_print_line,
+};
+
+__init static int init_mmio_trace(void)
+{
+	return register_tracer(&mmio_tracer);
+}
+device_initcall(init_mmio_trace);
+
+void mmio_trace_rw(struct mmiotrace_rw *rw)
+{
+	struct trace_array *tr = mmio_trace_array;
+	struct trace_array_cpu *data = tr->data[smp_processor_id()];
+	__trace_mmiotrace_rw(tr, data, rw);
+}
+
+void mmio_trace_mapping(struct mmiotrace_map *map)
+{
+	struct trace_array *tr = mmio_trace_array;
+	struct trace_array_cpu *data;
+
+	preempt_disable();
+	data = tr->data[smp_processor_id()];
+	__trace_mmiotrace_map(tr, data, map);
+	preempt_enable();
+}
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 5671db0e1827..a3376478fc2c 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -29,8 +29,6 @@ ctx_switch_func(void *__rq, struct task_struct *prev, struct task_struct *next)
 	if (!tracer_enabled)
 		return;
 
-	tracing_record_cmdline(prev);
-
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
@@ -73,6 +71,9 @@ void
 ftrace_ctx_switch(void *__rq, struct task_struct *prev,
 		  struct task_struct *next)
 {
+	if (unlikely(atomic_read(&trace_record_cmdline_enabled)))
+		tracing_record_cmdline(prev);
+
 	/*
 	 * If tracer_switch_func only points to the local
 	 * switch func, it still needs the ptr passed to it.
@@ -134,11 +135,13 @@ static void sched_switch_reset(struct trace_array *tr)
 static void start_sched_trace(struct trace_array *tr)
 {
 	sched_switch_reset(tr);
+	atomic_inc(&trace_record_cmdline_enabled);
 	tracer_enabled = 1;
 }
 
 static void stop_sched_trace(struct trace_array *tr)
 {
+	atomic_dec(&trace_record_cmdline_enabled);
 	tracer_enabled = 0;
 }
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 94a01a32867f..00a47b5c4f5b 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -82,10 +82,12 @@ trace_test_buffer_cpu(struct trace_array *tr, struct trace_array_cpu *data)
  */
 static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 {
-	unsigned long cnt = 0;
-	int cpu;
-	int ret = 0;
+	unsigned long flags, cnt = 0;
+	int cpu, ret = 0;
 
+	/* Don't allow flipping of max traces now */
+	raw_local_irq_save(flags);
+	__raw_spin_lock(&ftrace_max_lock);
 	for_each_possible_cpu(cpu) {
 		if (!head_page(tr->data[cpu]))
 			continue;
@@ -96,6 +98,8 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 		if (ret)
 			break;
 	}
+	__raw_spin_unlock(&ftrace_max_lock);
+	raw_local_irq_restore(flags);
 
 	if (count)
 		*count = cnt;
@@ -406,11 +410,11 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 #ifdef CONFIG_SCHED_TRACER
 static int trace_wakeup_test_thread(void *data)
 {
-	struct completion *x = data;
-
 	/* Make this a RT thread, doesn't need to be too high */
+	struct sched_param param = { .sched_priority = 5 };
+	struct completion *x = data;
 
-	rt_mutex_setprio(current, MAX_RT_PRIO - 5);
+	sched_setscheduler(current, SCHED_FIFO, &param);
 
 	/* Make it know we have a new prio */
 	complete(x);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index bfeab3a52d12..8e268b391efe 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -136,7 +136,7 @@ config DETECT_SOFTLOCKUP
 	help
 	  Say Y here to enable the kernel to detect "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
-	  mode for more than 10 seconds, without giving other tasks a
+	  mode for more than 60 seconds, without giving other tasks a
 	  chance to run.
 
 	  When a soft-lockup is detected, the kernel will print the
@@ -148,6 +148,30 @@ config DETECT_SOFTLOCKUP
 	   can be detected via the NMI-watchdog, on platforms that
 	   support it.)
 
+config BOOTPARAM_SOFTLOCKUP_PANIC
+	bool "Panic (Reboot) On Soft Lockups"
+	depends on DETECT_SOFTLOCKUP
+	help
+	  Say Y here to enable the kernel to panic on "soft lockups",
+	  which are bugs that cause the kernel to loop in kernel
+	  mode for more than 60 seconds, without giving other tasks a
+	  chance to run.
+
+	  The panic can be used in combination with panic_timeout,
+	  to cause the system to reboot automatically after a
+	  lockup has been detected. This feature is useful for
+	  high-availability systems that have uptime guarantees and
+	  where a lockup must be resolved ASAP.
+
+	  Say N if unsure.
+
+config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
+	int
+	depends on DETECT_SOFTLOCKUP
+	range 0 1
+	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
+	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
+
 config SCHED_DEBUG
 	bool "Collect scheduler debugging info"
 	depends on DEBUG_KERNEL && PROC_FS
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/localversion-sched-devel.git b/localversion-sched-devel.git
new file mode 100644
index 000000000000..4060b7ac0145
--- /dev/null
+++ b/localversion-sched-devel.git
@@ -0,0 +1 @@
+-sched-devel.git
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5e00f1772c20..319d4c9dd260 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -126,8 +126,6 @@ static void background_writeout(unsigned long _min_pages);
 static struct prop_descriptor vm_completions;
 static struct prop_descriptor vm_dirties;
 
-static unsigned long determine_dirtyable_memory(void);
-
 /*
  * couple the period to the dirty_ratio:
  *
@@ -286,7 +284,13 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 #endif
 }
 
-static unsigned long determine_dirtyable_memory(void)
+/**
+ * determine_dirtyable_memory - amount of memory that may be used
+ *
+ * Returns the numebr of pages that can currently be freed and used
+ * by the kernel for direct mappings.
+ */
+unsigned long determine_dirtyable_memory(void)
 {
 	unsigned long x;
 
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 2a739adaa92b..e7ddbfa0e02f 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 9326c377822e..71be69e94f88 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/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>
diff --git a/tests/rcutorture.c b/tests/rcutorture.c
index 47894f919d4e..a17932d89ba9 100644
--- a/tests/rcutorture.c
+++ b/tests/rcutorture.c
@@ -191,6 +191,7 @@ 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;
 };
@@ -264,6 +265,7 @@ 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"
 };
@@ -303,6 +305,7 @@ 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"
 };
@@ -363,6 +366,7 @@ 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"
 };
@@ -376,6 +380,7 @@ 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"
 };
@@ -457,6 +462,7 @@ 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"
 };
@@ -481,6 +487,11 @@ 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();
@@ -493,12 +504,27 @@ 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
@@ -847,7 +873,9 @@ 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! */
 
@@ -867,7 +895,7 @@ 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++) {